{"task":"Semi-Supervised Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","metric_names":["J&F","Jaccard (Mean)","Jaccard (Recall)","Jaccard (Decay)","F-measure (Mean)","F-measure (Recall)","F-measure (Decay)","FPS"],"rows":[{"id":16620,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"Cutie+ (base, MEGA)","metrics":{"F-measure (Mean)":"91.4","FPS":"17.9","J&F":"88.1","Jaccard (Mean)":"84.7"},"paper_url":"https://arxiv.org/abs/2310.12982v2","paper_title":"Putting the Object Back into Video Object Segmentation","paper_date":"2023-10-19","code_links":[{"title":"hkchengrex/Cutie","url":"https://github.com/hkchengrex/Cutie"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":16621,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"Cutie (base, MEGA)","metrics":{"F-measure (Mean)":"89.9","FPS":"36.4","J&F":"86.1","Jaccard (Mean)":"82.4"},"paper_url":"https://arxiv.org/abs/2310.12982v2","paper_title":"Putting the Object Back into Video Object Segmentation","paper_date":"2023-10-19","code_links":[{"title":"hkchengrex/Cutie","url":"https://github.com/hkchengrex/Cutie"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":16622,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"Cutie+ (base)","metrics":{"F-measure (Mean)":"89.2","FPS":"17.9","J&F":"85.9","Jaccard (Mean)":"82.6"},"paper_url":"https://arxiv.org/abs/2310.12982v2","paper_title":"Putting the Object Back into Video Object Segmentation","paper_date":"2023-10-19","code_links":[{"title":"hkchengrex/Cutie","url":"https://github.com/hkchengrex/Cutie"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":16623,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"SwinB-AOST (L'=3, MS)","metrics":{"F-measure (Mean)":"88.5","FPS":"1.3","J&F":"84.7","Jaccard (Mean)":"80.9"},"paper_url":"https://arxiv.org/abs/2203.11442v8","paper_title":"Scalable Video Object Segmentation with Identification Mechanism","paper_date":"2022-03-22","code_links":[{"title":"yoxu515/aot-benchmark","url":"https://github.com/yoxu515/aot-benchmark"},{"title":"z-x-yang/AOT","url":"https://github.com/z-x-yang/AOT"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":16624,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"SwinB-AOTv2-L","metrics":{"F-measure (Mean)":"87.9","FPS":"1.3","J&F":"84.5","Jaccard (Mean)":"81.0"},"paper_url":"https://arxiv.org/abs/2203.11442v8","paper_title":"Scalable Video Object Segmentation with Identification Mechanism","paper_date":"2022-03-22","code_links":[{"title":"yoxu515/aot-benchmark","url":"https://github.com/yoxu515/aot-benchmark"},{"title":"z-x-yang/AOT","url":"https://github.com/z-x-yang/AOT"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":16625,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"JIMD-R50","metrics":{"F-measure (Mean)":"87.4","J&F":"83.9","Jaccard (Mean)":"80.3"},"paper_url":"https://arxiv.org/abs/2409.14343v1","paper_title":"Memory Matching is not Enough: Jointly Improving Memory Matching and Decoding for Video Object Segmentation","paper_date":"2024-09-22","code_links":[],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":16626,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"XMem (BL30K, MS)","metrics":{"F-measure (Mean)":"87.0","J&F":"83.7","Jaccard (Mean)":"80.5"},"paper_url":"https://arxiv.org/abs/2207.07115v2","paper_title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","paper_date":"2022-07-14","code_links":[{"title":"hkchengrex/XMem","url":"https://github.com/hkchengrex/XMem"},{"title":"tianyuan168326/videosemanticcompression-pytorch","url":"https://github.com/tianyuan168326/videosemanticcompression-pytorch"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":16627,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"DEVA","metrics":{"F-measure (Mean)":"86.8","FPS":"25.3","J&F":"83.2","Jaccard (Mean)":"79.6"},"paper_url":"https://arxiv.org/abs/2309.03903v1","paper_title":"Tracking Anything with Decoupled Video Segmentation","paper_date":"2023-09-07","code_links":[{"title":"hkchengrex/Tracking-Anything-with-DEVA","url":"https://github.com/hkchengrex/Tracking-Anything-with-DEVA"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":16628,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"XMem (MS)","metrics":{"F-measure (Mean)":"86.4","J&F":"83.1","Jaccard (Mean)":"79.7"},"paper_url":"https://arxiv.org/abs/2207.07115v2","paper_title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","paper_date":"2022-07-14","code_links":[{"title":"hkchengrex/XMem","url":"https://github.com/hkchengrex/XMem"},{"title":"tianyuan168326/videosemanticcompression-pytorch","url":"https://github.com/tianyuan168326/videosemanticcompression-pytorch"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":16629,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"SwinB-DeAOT-L","metrics":{"F-measure (Mean)":"86.7","FPS":"15.4","J&F":"82.8","Jaccard (Mean)":"78.9"},"paper_url":"https://arxiv.org/abs/2210.09782v3","paper_title":"Decoupling Features in Hierarchical Propagation for Video Object Segmentation","paper_date":"2022-10-18","code_links":[{"title":"yoxu515/aot-benchmark","url":"https://github.com/yoxu515/aot-benchmark"},{"title":"z-x-yang/AOT","url":"https://github.com/z-x-yang/AOT"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":16630,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"SwinB-AOST (L'=3)","metrics":{"F-measure (Mean)":"86.6","FPS":"12.0","J&F":"82.7","Jaccard (Mean)":"78.8"},"paper_url":"https://arxiv.org/abs/2203.11442v8","paper_title":"Scalable Video Object Segmentation with Identification Mechanism","paper_date":"2022-03-22","code_links":[{"title":"yoxu515/aot-benchmark","url":"https://github.com/yoxu515/aot-benchmark"},{"title":"z-x-yang/AOT","url":"https://github.com/z-x-yang/AOT"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":16631,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"XMem (BL30K, 600p)","metrics":{"F-measure (Mean)":"85.8","J&F":"82.5","Jaccard (Mean)":"79.1"},"paper_url":"https://arxiv.org/abs/2207.07115v2","paper_title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","paper_date":"2022-07-14","code_links":[{"title":"hkchengrex/XMem","url":"https://github.com/hkchengrex/XMem"},{"title":"tianyuan168326/videosemanticcompression-pytorch","url":"https://github.com/tianyuan168326/videosemanticcompression-pytorch"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":16632,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"QDMN","metrics":{"F-measure (Mean)":"85.4","J&F":"81.9","Jaccard (Mean)":"78.1"},"paper_url":"https://arxiv.org/abs/2207.07922v1","paper_title":"Learning Quality-aware Dynamic Memory for Video Object Segmentation","paper_date":"2022-07-16","code_links":[{"title":"workforai/qdmn","url":"https://github.com/workforai/qdmn"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":16633,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"XMem (BL30K)","metrics":{"F-measure (Mean)":"84.7","J&F":"81.2","Jaccard (Mean)":"77.6"},"paper_url":"https://arxiv.org/abs/2207.07115v2","paper_title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","paper_date":"2022-07-14","code_links":[{"title":"hkchengrex/XMem","url":"https://github.com/hkchengrex/XMem"},{"title":"tianyuan168326/videosemanticcompression-pytorch","url":"https://github.com/tianyuan168326/videosemanticcompression-pytorch"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":16634,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"SwinB-AOT-L","metrics":{"F-measure (Mean)":"85.1","FPS":"12.1","J&F":"81.2","Jaccard (Mean)":"77.3"},"paper_url":"https://arxiv.org/abs/2106.02638v3","paper_title":"Associating Objects with Transformers for Video Object Segmentation","paper_date":"2021-06-04","code_links":[{"title":"yoxu515/aot-benchmark","url":"https://github.com/yoxu515/aot-benchmark"},{"title":"z-x-yang/AOT","url":"https://github.com/z-x-yang/AOT"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":16635,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"RPCMVOS-Full-Res","metrics":{"F-measure (Mean)":"84.3","J&F":"81","Jaccard (Mean)":"77.6"},"paper_url":"https://arxiv.org/abs/2112.02853v1","paper_title":"Reliable Propagation-Correction Modulation for Video Object Segmentation","paper_date":"2021-12-06","code_links":[{"title":"jerryx1110/rpcmvos","url":"https://github.com/jerryx1110/rpcmvos"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":16636,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"XMem","metrics":{"F-measure (Mean)":"84.5","J&F":"81.0","Jaccard (Mean)":"77.4"},"paper_url":"https://arxiv.org/abs/2207.07115v2","paper_title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","paper_date":"2022-07-14","code_links":[{"title":"hkchengrex/XMem","url":"https://github.com/hkchengrex/XMem"},{"title":"tianyuan168326/videosemanticcompression-pytorch","url":"https://github.com/tianyuan168326/videosemanticcompression-pytorch"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":16637,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"R50-DeAOT-L","metrics":{"F-measure (Mean)":"84.5","FPS":"27.0","J&F":"80.7","Jaccard (Mean)":"76.9"},"paper_url":"https://arxiv.org/abs/2210.09782v3","paper_title":"Decoupling Features in Hierarchical Propagation for Video Object Segmentation","paper_date":"2022-10-18","code_links":[{"title":"yoxu515/aot-benchmark","url":"https://github.com/yoxu515/aot-benchmark"},{"title":"z-x-yang/AOT","url":"https://github.com/z-x-yang/AOT"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":16638,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"STCN","metrics":{"F-measure (Decay)":"10.3","F-measure (Mean)":"83.5","F-measure (Recall)":"89.7","J&F":"79.9","Jaccard (Decay)":"10.5","Jaccard (Mean)":"76.3","Jaccard (Recall)":"85.5"},"paper_url":"https://arxiv.org/abs/2106.05210v2","paper_title":"Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation","paper_date":"2021-06-09","code_links":[{"title":"hkchengrex/STCN","url":"https://github.com/hkchengrex/STCN"},{"title":"limingxing00/rde-vos-cvpr2022","url":"https://github.com/limingxing00/rde-vos-cvpr2022"},{"title":"alipga/AMM_VOS","url":"https://github.com/alipga/AMM_VOS"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":16639,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"R50-AOST (L'=3)","metrics":{"F-measure (Mean)":"83.6","FPS":"17.5","J&F":"79.9","Jaccard (Mean)":"76.2"},"paper_url":"https://arxiv.org/abs/2203.11442v8","paper_title":"Scalable Video Object Segmentation with Identification Mechanism","paper_date":"2022-03-22","code_links":[{"title":"yoxu515/aot-benchmark","url":"https://github.com/yoxu515/aot-benchmark"},{"title":"z-x-yang/AOT","url":"https://github.com/z-x-yang/AOT"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":16640,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"XMem (DAVIS and YouTubeVOS only)","metrics":{"F-measure (Mean)":"83.4","J&F":"79.8","Jaccard (Mean)":"76.3"},"paper_url":"https://arxiv.org/abs/2207.07115v2","paper_title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","paper_date":"2022-07-14","code_links":[{"title":"hkchengrex/XMem","url":"https://github.com/hkchengrex/XMem"},{"title":"tianyuan168326/videosemanticcompression-pytorch","url":"https://github.com/tianyuan168326/videosemanticcompression-pytorch"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":16641,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"R50-AOT-L","metrics":{"F-measure (Mean)":"83.3","FPS":"18.0","J&F":"79.6","Jaccard (Mean)":"75.9"},"paper_url":"https://arxiv.org/abs/2106.02638v3","paper_title":"Associating Objects with Transformers for Video Object Segmentation","paper_date":"2021-06-04","code_links":[{"title":"yoxu515/aot-benchmark","url":"https://github.com/yoxu515/aot-benchmark"},{"title":"z-x-yang/AOT","url":"https://github.com/z-x-yang/AOT"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":16642,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"RPCMVOS","metrics":{"F-measure (Mean)":"82.6","J&F":"79.2","Jaccard (Mean)":"75.8"},"paper_url":"https://arxiv.org/abs/2112.02853v1","paper_title":"Reliable Propagation-Correction Modulation for Video Object Segmentation","paper_date":"2021-12-06","code_links":[{"title":"jerryx1110/rpcmvos","url":"https://github.com/jerryx1110/rpcmvos"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":16643,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"HMMN","metrics":{"F-measure (Mean)":"82.5","J&F":"78.6","Jaccard (Mean)":"74.7"},"paper_url":"https://arxiv.org/abs/2109.11404v1","paper_title":"Hierarchical Memory Matching Network for Video Object Segmentation","paper_date":"2021-09-23","code_links":[{"title":"hongje/hmmn","url":"https://github.com/hongje/hmmn"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":16644,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"AOT-L","metrics":{"F-measure (Mean)":"82.3","FPS":"18.7","J&F":"78.3","Jaccard (Mean)":"74.3"},"paper_url":"https://arxiv.org/abs/2106.02638v3","paper_title":"Associating Objects with Transformers for Video Object Segmentation","paper_date":"2021-06-04","code_links":[{"title":"yoxu515/aot-benchmark","url":"https://github.com/yoxu515/aot-benchmark"},{"title":"z-x-yang/AOT","url":"https://github.com/z-x-yang/AOT"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":16645,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"R50-AOST (L'=2)","metrics":{"F-measure (Mean)":"81.7","FPS":"24.3","J&F":"78.1","Jaccard (Mean)":"74.5"},"paper_url":"https://arxiv.org/abs/2203.11442v8","paper_title":"Scalable Video Object Segmentation with Identification Mechanism","paper_date":"2022-03-22","code_links":[{"title":"yoxu515/aot-benchmark","url":"https://github.com/yoxu515/aot-benchmark"},{"title":"z-x-yang/AOT","url":"https://github.com/z-x-yang/AOT"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":16646,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"CFBI+","metrics":{"F-measure (Mean)":"81.6","J&F":"78.0","Jaccard (Mean)":"74.4"},"paper_url":"https://arxiv.org/abs/2010.06349v2","paper_title":"Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration","paper_date":"2020-10-13","code_links":[{"title":"z-x-yang/CFBI","url":"https://github.com/z-x-yang/CFBI"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":16647,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"DeAOT-L","metrics":{"F-measure (Mean)":"81.7","FPS":"28.5","J&F":"77.9","Jaccard (Mean)":"74.1"},"paper_url":"https://arxiv.org/abs/2210.09782v3","paper_title":"Decoupling Features in Hierarchical Propagation for Video Object Segmentation","paper_date":"2022-10-18","code_links":[{"title":"yoxu515/aot-benchmark","url":"https://github.com/yoxu515/aot-benchmark"},{"title":"z-x-yang/AOT","url":"https://github.com/z-x-yang/AOT"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":16648,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"KMN","metrics":{"F-measure (Mean)":"80.3","J&F":"77.2","Jaccard (Mean)":"74.1"},"paper_url":"https://arxiv.org/abs/2007.08270v1","paper_title":"Kernelized Memory Network for Video Object Segmentation","paper_date":"2020-07-16","code_links":[{"title":"hkchengrex/Mask-Propagation","url":"https://github.com/hkchengrex/Mask-Propagation"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":16649,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"MiVOS","metrics":{"F-measure (Decay)":"14.5","F-measure (Mean)":"80.2","F-measure (Recall)":"87.6","J&F":"76.5","Jaccard (Decay)":"14.9","Jaccard (Mean)":"72.7","Jaccard (Recall)":"81.2"},"paper_url":"https://arxiv.org/abs/2103.07941v3","paper_title":"Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion","paper_date":"2021-03-14","code_links":[{"title":"hkchengrex/MiVOS","url":"https://github.com/hkchengrex/MiVOS"},{"title":"hkchengrex/Mask-Propagation","url":"https://github.com/hkchengrex/Mask-Propagation"},{"title":"hkchengrex/Scribble-to-Mask","url":"https://github.com/hkchengrex/Scribble-to-Mask"},{"title":"limingxing00/rde-vos-cvpr2022","url":"https://github.com/limingxing00/rde-vos-cvpr2022"},{"title":"Vujas-Eteph/CiVOS","url":"https://github.com/Vujas-Eteph/CiVOS"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":16650,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"DeAOT-B","metrics":{"F-measure (Mean)":"79.9","FPS":"40.9","J&F":"76.2","Jaccard (Mean)":"72.5"},"paper_url":"https://arxiv.org/abs/2210.09782v3","paper_title":"Decoupling Features in Hierarchical Propagation for Video Object Segmentation","paper_date":"2022-10-18","code_links":[{"title":"yoxu515/aot-benchmark","url":"https://github.com/yoxu515/aot-benchmark"},{"title":"z-x-yang/AOT","url":"https://github.com/z-x-yang/AOT"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":16651,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"AOT-B","metrics":{"F-measure (Mean)":"79.3","FPS":"29.6","J&F":"75.5","Jaccard (Mean)":"71.6"},"paper_url":"https://arxiv.org/abs/2106.02638v3","paper_title":"Associating Objects with Transformers for Video Object Segmentation","paper_date":"2021-06-04","code_links":[{"title":"yoxu515/aot-benchmark","url":"https://github.com/yoxu515/aot-benchmark"},{"title":"z-x-yang/AOT","url":"https://github.com/z-x-yang/AOT"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":16652,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"DeAOT-S","metrics":{"F-measure (Mean)":"79.0","FPS":"49.2","J&F":"75.4","Jaccard (Mean)":"71.9"},"paper_url":"https://arxiv.org/abs/2210.09782v3","paper_title":"Decoupling Features in Hierarchical Propagation for Video Object Segmentation","paper_date":"2022-10-18","code_links":[{"title":"yoxu515/aot-benchmark","url":"https://github.com/yoxu515/aot-benchmark"},{"title":"z-x-yang/AOT","url":"https://github.com/z-x-yang/AOT"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":16653,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"RMNet","metrics":{"F-measure (Mean)":"78.1","J&F":"75.0","Jaccard (Mean)":"71.9"},"paper_url":"https://arxiv.org/abs/2103.12934v2","paper_title":"Efficient Regional Memory Network for Video Object Segmentation","paper_date":"2021-03-24","code_links":[{"title":"hzxie/RMNet","url":"https://github.com/hzxie/RMNet"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":16654,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"CFBI","metrics":{"F-measure (Mean)":"78.5","J&F":"74.8","Jaccard (Mean)":"71.1"},"paper_url":"https://arxiv.org/abs/2003.08333v2","paper_title":"Collaborative Video Object Segmentation by Foreground-Background Integration","paper_date":"2020-03-18","code_links":[{"title":"PaddlePaddle/PaddleVideo","url":"https://github.com/PaddlePaddle/PaddleVideo/blob/develop/docs/en/model_zoo/segmentation/cfbi.md"},{"title":"z-x-yang/CFBI","url":"https://github.com/z-x-yang/CFBI"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":16655,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"AOT-S","metrics":{"F-measure (Mean)":"77.5","FPS":"40.0","J&F":"73.9","Jaccard (Mean)":"70.3"},"paper_url":"https://arxiv.org/abs/2106.02638v3","paper_title":"Associating Objects with Transformers for Video Object Segmentation","paper_date":"2021-06-04","code_links":[{"title":"yoxu515/aot-benchmark","url":"https://github.com/yoxu515/aot-benchmark"},{"title":"z-x-yang/AOT","url":"https://github.com/z-x-yang/AOT"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":16656,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"DeAOT-T","metrics":{"F-measure (Mean)":"77.3","FPS":"63.5","J&F":"73.7","Jaccard (Mean)":"70.0"},"paper_url":"https://arxiv.org/abs/2210.09782v3","paper_title":"Decoupling Features in Hierarchical Propagation for Video Object Segmentation","paper_date":"2022-10-18","code_links":[{"title":"yoxu515/aot-benchmark","url":"https://github.com/yoxu515/aot-benchmark"},{"title":"z-x-yang/AOT","url":"https://github.com/z-x-yang/AOT"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":16657,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"STM","metrics":{"F-measure (Decay)":"17.5","F-measure (Mean)":"75.2","F-measure (Recall)":"83.0","J&F":"72.2","Jaccard (Decay)":"16.9","Jaccard (Mean)":"69.3","Jaccard (Recall)":"78.0"},"paper_url":"https://arxiv.org/abs/1904.00607v2","paper_title":"Video Object Segmentation using Space-Time Memory Networks","paper_date":"2019-04-01","code_links":[{"title":"seoungwugoh/STM","url":"https://github.com/seoungwugoh/STM"},{"title":"hkchengrex/Mask-Propagation","url":"https://github.com/hkchengrex/Mask-Propagation"},{"title":"ywcmaike/TianchiVideoCharacterSegmentationPreliminary","url":"https://github.com/ywcmaike/TianchiVideoCharacterSegmentationPreliminary"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":16658,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"AOT-T","metrics":{"F-measure (Mean)":"75.7","FPS":"51.4","J&F":"72.0","Jaccard (Mean)":"68.3"},"paper_url":"https://arxiv.org/abs/2106.02638v3","paper_title":"Associating Objects with Transformers for Video Object Segmentation","paper_date":"2021-06-04","code_links":[{"title":"yoxu515/aot-benchmark","url":"https://github.com/yoxu515/aot-benchmark"},{"title":"z-x-yang/AOT","url":"https://github.com/z-x-yang/AOT"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":16659,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"PReMVOS","metrics":{"F-measure (Decay)":"20.6","F-measure (Mean)":"75.8","F-measure (Recall)":"84.3","J&F":"71.6","Jaccard (Decay)":"21.7","Jaccard (Mean)":"67.5","Jaccard (Recall)":"76.8"},"paper_url":"http://arxiv.org/abs/1807.09190v2","paper_title":"PReMVOS: Proposal-generation, Refinement and Merging for Video Object Segmentation","paper_date":"2018-07-24","code_links":[{"title":"JonathonLuiten/PReMVOS","url":"https://github.com/JonathonLuiten/PReMVOS"},{"title":"VisualComputingInstitute/mots_trackingonly_tools","url":"https://github.com/VisualComputingInstitute/mots_trackingonly_tools"},{"title":"gunpowder78/PReMVOS","url":"https://github.com/gunpowder78/PReMVOS"},{"title":"AyaLotfy/PReMVOS-trial","url":"https://github.com/AyaLotfy/PReMVOS-trial"},{"title":"AyaLotfy/premvos-tmp","url":"https://github.com/AyaLotfy/premvos-tmp"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":16660,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"MHP-VOS","metrics":{"F-measure (Decay)":"19.1","F-measure (Mean)":"72.7","F-measure (Recall)":"82.3","J&F":"69.5","Jaccard (Decay)":"18.0","Jaccard (Mean)":"66.4","Jaccard (Recall)":"76.0"},"paper_url":"http://arxiv.org/abs/1904.08141v1","paper_title":"MHP-VOS: Multiple Hypotheses Propagation for Video Object Segmentation","paper_date":"2019-04-17","code_links":[{"title":"shuangjiexu/MHP-VOS","url":"https://github.com/shuangjiexu/MHP-VOS"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":16661,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"CINM","metrics":{"F-measure (Decay)":"20.0","F-measure (Mean)":"70.5","F-measure (Recall)":"79.6","J&F":"67.5","Jaccard (Decay)":"20.0","Jaccard (Mean)":"64.5","Jaccard (Recall)":"73.8"},"paper_url":"http://arxiv.org/abs/1803.09453v1","paper_title":"CNN in MRF: Video Object Segmentation via Inference in A CNN-Based Higher-Order Spatio-Temporal MRF","paper_date":"2018-03-26","code_links":[],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":16662,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"LSMVOS","metrics":{"F-measure (Decay)":"16.5","F-measure (Mean)":"71.2","F-measure (Recall)":"81.4","J&F":"67.4","Jaccard (Decay)":"16.9","Jaccard (Mean)":"63.7","Jaccard (Recall)":"72.7"},"paper_url":"https://arxiv.org/abs/2009.00771v1","paper_title":"LSMVOS: Long-Short-Term Similarity Matching for Video Object","paper_date":"2020-09-02","code_links":[{"title":"wudao001/LSMVOS","url":"https://github.com/wudao001/LSMVOS"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":16663,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"Lucid","metrics":{"F-measure (Decay)":"19.5","F-measure (Mean)":"69.9","F-measure (Recall)":"80.1","J&F":"66.6","Jaccard (Decay)":"19.5","Jaccard (Mean)":"63.4","Jaccard (Recall)":"74.0"},"paper_url":"http://arxiv.org/abs/1703.09554v5","paper_title":"Lucid Data Dreaming for Video Object Segmentation","paper_date":"2017-03-28","code_links":[{"title":"omkar13/MaskTrack","url":"https://github.com/omkar13/MaskTrack"},{"title":"ankhoreva/LucidDataDreaming","url":"https://github.com/ankhoreva/LucidDataDreaming"},{"title":"yelantingfeng/pyLucid","url":"https://github.com/yelantingfeng/pyLucid"},{"title":"birdman9390/MetaMaskTrack","url":"https://github.com/birdman9390/MetaMaskTrack"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":16664,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"e-OSVOS","metrics":{"F-measure (Mean)":"68.6","J&F":"64.8","Jaccard (Decay)":"22.1","Jaccard (Mean)":"60.9"},"paper_url":"https://arxiv.org/abs/2012.01866v1","paper_title":"Make One-Shot Video Object Segmentation Efficient Again","paper_date":"2020-12-03","code_links":[{"title":"timmeinhardt/trackformer","url":"https://github.com/timmeinhardt/trackformer"},{"title":"acaelles97/devis","url":"https://github.com/acaelles97/devis"},{"title":"dvl-tum/e-osvos","url":"https://github.com/dvl-tum/e-osvos"},{"title":"MindSpore-paper-code-2/code2","url":"https://github.com/MindSpore-paper-code-2/code2/tree/main/OSVOS"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":16665,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"SSM-VOS","metrics":{"F-measure (Decay)":"25.3","F-measure (Mean)":"63.8","J&F":"62.0","Jaccard (Decay)":"23.5","Jaccard (Mean)":"60.2"},"paper_url":"https://ieeexplore.ieee.org/document/9356697","paper_title":"Separable Structure Modeling for Semi-supervised Video Object Segmentation","paper_date":"2021-02-18","code_links":[{"title":"li-plus/SSM-VOS","url":"https://github.com/li-plus/SSM-VOS"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":16666,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"FEELVOS","metrics":{"F-measure (Decay)":"33.5","F-measure (Mean)":"60.9","F-measure (Recall)":"68.5","J&F":"57.8","Jaccard (Decay)":"29.8","Jaccard (Mean)":"55.1","Jaccard (Recall)":"62.6"},"paper_url":"http://arxiv.org/abs/1902.09513v2","paper_title":"FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation","paper_date":"2019-02-25","code_links":[{"title":"tensorflow/models","url":"https://github.com/tensorflow/models"},{"title":"tensorflow/models","url":"https://github.com/tensorflow/models/tree/master/research/feelvos"},{"title":"kim-younghan/FEELVOS","url":"https://github.com/kim-younghan/FEELVOS"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":16667,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"OSVOS-S","metrics":{"F-measure (Decay)":"21.9","F-measure (Mean)":"62.1","F-measure (Recall)":"70.5","J&F":"57.5","Jaccard (Decay)":"24.1","Jaccard (Mean)":"52.9","Jaccard (Recall)":"60.2"},"paper_url":"http://arxiv.org/abs/1709.06031v2","paper_title":"Video Object Segmentation Without Temporal Information","paper_date":"2017-09-18","code_links":[],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":16668,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"RANet","metrics":{"F-measure (Decay)":"22.1","F-measure (Mean)":"57.3","F-measure (Recall)":"67.7","J&F":"55.4","Jaccard (Decay)":"21.9","Jaccard (Mean)":"53.4","Jaccard (Recall)":"61.9"},"paper_url":"https://arxiv.org/abs/1908.06647v4","paper_title":"RANet: Ranking Attention Network for Fast Video Object Segmentation","paper_date":"2019-08-19","code_links":[{"title":"Storife/RANet","url":"https://github.com/Storife/RANet"},{"title":"v1viswan/RANet_modifications","url":"https://github.com/v1viswan/RANet_modifications"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":16669,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"Siam R-CNN","metrics":{"F-measure (Decay)":"20.2","F-measure (Mean)":"58.6","F-measure (Recall)":"62.3","J&F":"53.3","Jaccard (Decay)":"21.8","Jaccard (Mean)":"48.0","Jaccard (Recall)":"53.9"},"paper_url":"https://arxiv.org/abs/1911.12836v2","paper_title":"Siam R-CNN: Visual Tracking by Re-Detection","paper_date":"2019-11-28","code_links":[{"title":"VisualComputingInstitute/SiamR-CNN","url":"https://github.com/VisualComputingInstitute/SiamR-CNN"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":16670,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"RGMP","metrics":{"F-measure (Decay)":"37.2","F-measure (Mean)":"54.4","F-measure (Recall)":"61.9","J&F":"52.8","Jaccard (Decay)":"34.3","Jaccard (Mean)":"51.3","Jaccard (Recall)":"59.0"},"paper_url":"http://openaccess.thecvf.com/content_cvpr_2018/html/Oh_Fast_Video_Object_CVPR_2018_paper.html","paper_title":"Fast Video Object Segmentation by Reference-Guided Mask Propagation","paper_date":"2018-06-01","code_links":[{"title":"seoungwugoh/RGMP","url":"https://github.com/seoungwugoh/RGMP"},{"title":"xanderchf/RGMP","url":"https://github.com/xanderchf/RGMP"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":16671,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"OnAVOS","metrics":{"F-measure (Decay)":"23.4","F-measure (Recall)":"60.3","J&F":"52.8","Jaccard (Decay)":"23.0","Jaccard (Mean)":"49.9","Jaccard (Recall)":"54.3"},"paper_url":"http://arxiv.org/abs/1706.09364v2","paper_title":"Online Adaptation of Convolutional Neural Networks for Video Object Segmentation","paper_date":"2017-06-28","code_links":[],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":16672,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"AGAME","metrics":{"F-measure (Decay)":"27.6","F-measure (Mean)":"55.3","F-measure (Recall)":"61.1","J&F":"52.3","Jaccard (Decay)":"28.9","Jaccard (Mean)":"49.2","Jaccard (Recall)":"53.2"},"paper_url":"http://arxiv.org/abs/1811.11611v2","paper_title":"A Generative Appearance Model for End-to-end Video Object Segmentation","paper_date":"2018-11-28","code_links":[{"title":"joakimjohnander/agame-vos","url":"https://github.com/joakimjohnander/agame-vos"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":16673,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"CapsuleVOS","metrics":{"F-measure (Mean)":"55.2","F-measure (Recall)":"64.6","J&F":"51.3","Jaccard (Mean)":"47.4","Jaccard (Recall)":"54.1"},"paper_url":"https://arxiv.org/abs/1910.00132v1","paper_title":"CapsuleVOS: Semi-Supervised Video Object Segmentation Using Capsule Routing","paper_date":"2019-09-30","code_links":[{"title":"KevinDuarte/CapsuleVOS","url":"https://github.com/KevinDuarte/CapsuleVOS"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":16674,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"OSVOS","metrics":{"F-measure (Decay)":"19.8","F-measure (Recall)":"59.7","J&F":"50.9","Jaccard (Decay)":"19.2","Jaccard (Mean)":"47.0","Jaccard (Recall)":"52.1"},"paper_url":"http://arxiv.org/abs/1611.05198v4","paper_title":"One-Shot Video Object Segmentation","paper_date":"2016-11-16","code_links":[{"title":"kmaninis/OSVOS-PyTorch","url":"https://github.com/kmaninis/OSVOS-PyTorch"},{"title":"scaelles/OSVOS-TensorFlow","url":"https://github.com/scaelles/OSVOS-TensorFlow"},{"title":"kmaninis/OSVOS-caffe","url":"https://github.com/kmaninis/OSVOS-caffe"},{"title":"xiuyu0000/new_papers_codes","url":"https://github.com/xiuyu0000/new_papers_codes/tree/main/OSVOS"},{"title":"code-implementation1/Code6","url":"https://github.com/code-implementation1/Code6/tree/main/OSVOS"},{"title":"MS-Mind/MS-Code-06","url":"https://github.com/MS-Mind/MS-Code-06/tree/main/OSVOS"},{"title":"2023-MindSpore-1/ms-code-215","url":"https://github.com/2023-MindSpore-1/ms-code-215/tree/main/OSVOS"},{"title":"Mind23-2/MindCode-5","url":"https://github.com/Mind23-2/MindCode-5/tree/main/OSVOS"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":16675,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"RVOS","metrics":{"F-measure (Decay)":"36.7","F-measure (Mean)":"52.6","F-measure (Recall)":"61.7","J&F":"50.3","Jaccard (Decay)":"35.7","Jaccard (Mean)":"47.9","Jaccard (Recall)":"54.4"},"paper_url":"https://arxiv.org/abs/1903.05612v2","paper_title":"RVOS: End-to-End Recurrent Network for Video Object Segmentation","paper_date":"2019-03-13","code_links":[{"title":"imatge-upc/rvos","url":"https://github.com/imatge-upc/rvos"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":16676,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"FAVOS","metrics":{"F-measure (Decay)":"19.8","F-measure (Mean)":"44.2","F-measure (Recall)":"51.1","J&F":"43.6","Jaccard (Decay)":"18.1","Jaccard (Mean)":"42.9","Jaccard (Recall)":"48.1"},"paper_url":"http://arxiv.org/abs/1806.02323v1","paper_title":"Fast and Accurate Online Video Object Segmentation via Tracking Parts","paper_date":"2018-06-06","code_links":[{"title":"guanfuchen/video_obj","url":"https://github.com/guanfuchen/video_obj"},{"title":"JingchunCheng/FAVOS","url":"https://github.com/JingchunCheng/FAVOS"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":16677,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"SiamMask","metrics":{"F-measure (Decay)":"22.4","F-measure (Mean)":"45.8","F-measure (Recall)":"45.3","J&F":"43.2","Jaccard (Decay)":"21.9","Jaccard (Mean)":"40.6","Jaccard (Recall)":"44.5"},"paper_url":"https://arxiv.org/abs/1812.05050v2","paper_title":"Fast Online Object Tracking and Segmentation: A Unifying Approach","paper_date":"2018-12-12","code_links":[{"title":"foolwood/SiamMask","url":"https://github.com/foolwood/SiamMask"},{"title":"shallowtoil/DROL","url":"https://github.com/shallowtoil/DROL"},{"title":"ezelikman/anonymal","url":"https://github.com/ezelikman/anonymal"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":16678,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"OSMN","metrics":{"F-measure (Decay)":"17.4","F-measure (Recall)":"47.4","J&F":"41.3","Jaccard (Decay)":"19.0","Jaccard (Mean)":"37.7","Jaccard (Recall)":"38.9"},"paper_url":"http://arxiv.org/abs/1802.01218v1","paper_title":"Efficient Video Object Segmentation via Network Modulation","paper_date":"2018-02-04","code_links":[{"title":"linjieyangsc/video_seg","url":"https://github.com/linjieyangsc/video_seg"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":87761,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"Cutie+ (base, MEGA)","metrics":{"F-measure (Mean)":"91.4","FPS":"17.9","J&F":"88.1","Jaccard (Mean)":"84.7"},"paper_url":"https://arxiv.org/abs/2310.12982v2","paper_title":"Putting the Object Back into Video Object Segmentation","paper_date":"2023-10-19","code_links":[{"title":"hkchengrex/Cutie","url":"https://github.com/hkchengrex/Cutie"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":87762,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"Cutie (base, MEGA)","metrics":{"F-measure (Mean)":"89.9","FPS":"36.4","J&F":"86.1","Jaccard (Mean)":"82.4"},"paper_url":"https://arxiv.org/abs/2310.12982v2","paper_title":"Putting the Object Back into Video Object Segmentation","paper_date":"2023-10-19","code_links":[{"title":"hkchengrex/Cutie","url":"https://github.com/hkchengrex/Cutie"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":87763,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"Cutie+ (base)","metrics":{"F-measure (Mean)":"89.2","FPS":"17.9","J&F":"85.9","Jaccard (Mean)":"82.6"},"paper_url":"https://arxiv.org/abs/2310.12982v2","paper_title":"Putting the Object Back into Video Object Segmentation","paper_date":"2023-10-19","code_links":[{"title":"hkchengrex/Cutie","url":"https://github.com/hkchengrex/Cutie"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":87764,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"SwinB-AOST (L'=3, MS)","metrics":{"F-measure (Mean)":"88.5","FPS":"1.3","J&F":"84.7","Jaccard (Mean)":"80.9"},"paper_url":"https://arxiv.org/abs/2203.11442v8","paper_title":"Scalable Video Object Segmentation with Identification Mechanism","paper_date":"2022-03-22","code_links":[{"title":"yoxu515/aot-benchmark","url":"https://github.com/yoxu515/aot-benchmark"},{"title":"z-x-yang/AOT","url":"https://github.com/z-x-yang/AOT"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":87765,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"SwinB-AOTv2-L","metrics":{"F-measure (Mean)":"87.9","FPS":"1.3","J&F":"84.5","Jaccard (Mean)":"81.0"},"paper_url":"https://arxiv.org/abs/2203.11442v8","paper_title":"Scalable Video Object Segmentation with Identification Mechanism","paper_date":"2022-03-22","code_links":[{"title":"yoxu515/aot-benchmark","url":"https://github.com/yoxu515/aot-benchmark"},{"title":"z-x-yang/AOT","url":"https://github.com/z-x-yang/AOT"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":87766,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"JIMD-R50","metrics":{"F-measure (Mean)":"87.4","J&F":"83.9","Jaccard (Mean)":"80.3"},"paper_url":"https://arxiv.org/abs/2409.14343v1","paper_title":"Memory Matching is not Enough: Jointly Improving Memory Matching and Decoding for Video Object Segmentation","paper_date":"2024-09-22","code_links":[],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":87767,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"XMem (BL30K, MS)","metrics":{"F-measure (Mean)":"87.0","J&F":"83.7","Jaccard (Mean)":"80.5"},"paper_url":"https://arxiv.org/abs/2207.07115v2","paper_title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","paper_date":"2022-07-14","code_links":[{"title":"hkchengrex/XMem","url":"https://github.com/hkchengrex/XMem"},{"title":"tianyuan168326/videosemanticcompression-pytorch","url":"https://github.com/tianyuan168326/videosemanticcompression-pytorch"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":87768,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"DEVA","metrics":{"F-measure (Mean)":"86.8","FPS":"25.3","J&F":"83.2","Jaccard (Mean)":"79.6"},"paper_url":"https://arxiv.org/abs/2309.03903v1","paper_title":"Tracking Anything with Decoupled Video Segmentation","paper_date":"2023-09-07","code_links":[{"title":"hkchengrex/Tracking-Anything-with-DEVA","url":"https://github.com/hkchengrex/Tracking-Anything-with-DEVA"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":87769,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"XMem (MS)","metrics":{"F-measure (Mean)":"86.4","J&F":"83.1","Jaccard (Mean)":"79.7"},"paper_url":"https://arxiv.org/abs/2207.07115v2","paper_title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","paper_date":"2022-07-14","code_links":[{"title":"hkchengrex/XMem","url":"https://github.com/hkchengrex/XMem"},{"title":"tianyuan168326/videosemanticcompression-pytorch","url":"https://github.com/tianyuan168326/videosemanticcompression-pytorch"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":87770,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"SwinB-DeAOT-L","metrics":{"F-measure (Mean)":"86.7","FPS":"15.4","J&F":"82.8","Jaccard (Mean)":"78.9"},"paper_url":"https://arxiv.org/abs/2210.09782v3","paper_title":"Decoupling Features in Hierarchical Propagation for Video Object Segmentation","paper_date":"2022-10-18","code_links":[{"title":"yoxu515/aot-benchmark","url":"https://github.com/yoxu515/aot-benchmark"},{"title":"z-x-yang/AOT","url":"https://github.com/z-x-yang/AOT"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":87771,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"SwinB-AOST (L'=3)","metrics":{"F-measure (Mean)":"86.6","FPS":"12.0","J&F":"82.7","Jaccard (Mean)":"78.8"},"paper_url":"https://arxiv.org/abs/2203.11442v8","paper_title":"Scalable Video Object Segmentation with Identification Mechanism","paper_date":"2022-03-22","code_links":[{"title":"yoxu515/aot-benchmark","url":"https://github.com/yoxu515/aot-benchmark"},{"title":"z-x-yang/AOT","url":"https://github.com/z-x-yang/AOT"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":87772,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"XMem (BL30K, 600p)","metrics":{"F-measure (Mean)":"85.8","J&F":"82.5","Jaccard (Mean)":"79.1"},"paper_url":"https://arxiv.org/abs/2207.07115v2","paper_title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","paper_date":"2022-07-14","code_links":[{"title":"hkchengrex/XMem","url":"https://github.com/hkchengrex/XMem"},{"title":"tianyuan168326/videosemanticcompression-pytorch","url":"https://github.com/tianyuan168326/videosemanticcompression-pytorch"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":87773,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"QDMN","metrics":{"F-measure (Mean)":"85.4","J&F":"81.9","Jaccard (Mean)":"78.1"},"paper_url":"https://arxiv.org/abs/2207.07922v1","paper_title":"Learning Quality-aware Dynamic Memory for Video Object Segmentation","paper_date":"2022-07-16","code_links":[{"title":"workforai/qdmn","url":"https://github.com/workforai/qdmn"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":87774,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"XMem (BL30K)","metrics":{"F-measure (Mean)":"84.7","J&F":"81.2","Jaccard (Mean)":"77.6"},"paper_url":"https://arxiv.org/abs/2207.07115v2","paper_title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","paper_date":"2022-07-14","code_links":[{"title":"hkchengrex/XMem","url":"https://github.com/hkchengrex/XMem"},{"title":"tianyuan168326/videosemanticcompression-pytorch","url":"https://github.com/tianyuan168326/videosemanticcompression-pytorch"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":87775,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"SwinB-AOT-L","metrics":{"F-measure (Mean)":"85.1","FPS":"12.1","J&F":"81.2","Jaccard (Mean)":"77.3"},"paper_url":"https://arxiv.org/abs/2106.02638v3","paper_title":"Associating Objects with Transformers for Video Object Segmentation","paper_date":"2021-06-04","code_links":[{"title":"yoxu515/aot-benchmark","url":"https://github.com/yoxu515/aot-benchmark"},{"title":"z-x-yang/AOT","url":"https://github.com/z-x-yang/AOT"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":87776,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"RPCMVOS-Full-Res","metrics":{"F-measure (Mean)":"84.3","J&F":"81","Jaccard (Mean)":"77.6"},"paper_url":"https://arxiv.org/abs/2112.02853v1","paper_title":"Reliable Propagation-Correction Modulation for Video Object Segmentation","paper_date":"2021-12-06","code_links":[{"title":"jerryx1110/rpcmvos","url":"https://github.com/jerryx1110/rpcmvos"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":87777,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"XMem","metrics":{"F-measure (Mean)":"84.5","J&F":"81.0","Jaccard (Mean)":"77.4"},"paper_url":"https://arxiv.org/abs/2207.07115v2","paper_title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","paper_date":"2022-07-14","code_links":[{"title":"hkchengrex/XMem","url":"https://github.com/hkchengrex/XMem"},{"title":"tianyuan168326/videosemanticcompression-pytorch","url":"https://github.com/tianyuan168326/videosemanticcompression-pytorch"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":87778,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"R50-DeAOT-L","metrics":{"F-measure (Mean)":"84.5","FPS":"27.0","J&F":"80.7","Jaccard (Mean)":"76.9"},"paper_url":"https://arxiv.org/abs/2210.09782v3","paper_title":"Decoupling Features in Hierarchical Propagation for Video Object Segmentation","paper_date":"2022-10-18","code_links":[{"title":"yoxu515/aot-benchmark","url":"https://github.com/yoxu515/aot-benchmark"},{"title":"z-x-yang/AOT","url":"https://github.com/z-x-yang/AOT"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":87779,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"STCN","metrics":{"F-measure (Decay)":"10.3","F-measure (Mean)":"83.5","F-measure (Recall)":"89.7","J&F":"79.9","Jaccard (Decay)":"10.5","Jaccard (Mean)":"76.3","Jaccard (Recall)":"85.5"},"paper_url":"https://arxiv.org/abs/2106.05210v2","paper_title":"Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation","paper_date":"2021-06-09","code_links":[{"title":"hkchengrex/STCN","url":"https://github.com/hkchengrex/STCN"},{"title":"limingxing00/rde-vos-cvpr2022","url":"https://github.com/limingxing00/rde-vos-cvpr2022"},{"title":"alipga/AMM_VOS","url":"https://github.com/alipga/AMM_VOS"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":87780,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"R50-AOST (L'=3)","metrics":{"F-measure (Mean)":"83.6","FPS":"17.5","J&F":"79.9","Jaccard (Mean)":"76.2"},"paper_url":"https://arxiv.org/abs/2203.11442v8","paper_title":"Scalable Video Object Segmentation with Identification Mechanism","paper_date":"2022-03-22","code_links":[{"title":"yoxu515/aot-benchmark","url":"https://github.com/yoxu515/aot-benchmark"},{"title":"z-x-yang/AOT","url":"https://github.com/z-x-yang/AOT"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":87781,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"XMem (DAVIS and YouTubeVOS only)","metrics":{"F-measure (Mean)":"83.4","J&F":"79.8","Jaccard (Mean)":"76.3"},"paper_url":"https://arxiv.org/abs/2207.07115v2","paper_title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","paper_date":"2022-07-14","code_links":[{"title":"hkchengrex/XMem","url":"https://github.com/hkchengrex/XMem"},{"title":"tianyuan168326/videosemanticcompression-pytorch","url":"https://github.com/tianyuan168326/videosemanticcompression-pytorch"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":87782,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"R50-AOT-L","metrics":{"F-measure (Mean)":"83.3","FPS":"18.0","J&F":"79.6","Jaccard (Mean)":"75.9"},"paper_url":"https://arxiv.org/abs/2106.02638v3","paper_title":"Associating Objects with Transformers for Video Object Segmentation","paper_date":"2021-06-04","code_links":[{"title":"yoxu515/aot-benchmark","url":"https://github.com/yoxu515/aot-benchmark"},{"title":"z-x-yang/AOT","url":"https://github.com/z-x-yang/AOT"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":87783,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"RPCMVOS","metrics":{"F-measure (Mean)":"82.6","J&F":"79.2","Jaccard (Mean)":"75.8"},"paper_url":"https://arxiv.org/abs/2112.02853v1","paper_title":"Reliable Propagation-Correction Modulation for Video Object Segmentation","paper_date":"2021-12-06","code_links":[{"title":"jerryx1110/rpcmvos","url":"https://github.com/jerryx1110/rpcmvos"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":87784,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"HMMN","metrics":{"F-measure (Mean)":"82.5","J&F":"78.6","Jaccard (Mean)":"74.7"},"paper_url":"https://arxiv.org/abs/2109.11404v1","paper_title":"Hierarchical Memory Matching Network for Video Object Segmentation","paper_date":"2021-09-23","code_links":[{"title":"hongje/hmmn","url":"https://github.com/hongje/hmmn"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":87785,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"AOT-L","metrics":{"F-measure (Mean)":"82.3","FPS":"18.7","J&F":"78.3","Jaccard (Mean)":"74.3"},"paper_url":"https://arxiv.org/abs/2106.02638v3","paper_title":"Associating Objects with Transformers for Video Object Segmentation","paper_date":"2021-06-04","code_links":[{"title":"yoxu515/aot-benchmark","url":"https://github.com/yoxu515/aot-benchmark"},{"title":"z-x-yang/AOT","url":"https://github.com/z-x-yang/AOT"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":87786,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"R50-AOST (L'=2)","metrics":{"F-measure (Mean)":"81.7","FPS":"24.3","J&F":"78.1","Jaccard (Mean)":"74.5"},"paper_url":"https://arxiv.org/abs/2203.11442v8","paper_title":"Scalable Video Object Segmentation with Identification Mechanism","paper_date":"2022-03-22","code_links":[{"title":"yoxu515/aot-benchmark","url":"https://github.com/yoxu515/aot-benchmark"},{"title":"z-x-yang/AOT","url":"https://github.com/z-x-yang/AOT"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":87787,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"CFBI+","metrics":{"F-measure (Mean)":"81.6","J&F":"78.0","Jaccard (Mean)":"74.4"},"paper_url":"https://arxiv.org/abs/2010.06349v2","paper_title":"Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration","paper_date":"2020-10-13","code_links":[{"title":"z-x-yang/CFBI","url":"https://github.com/z-x-yang/CFBI"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":87788,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"DeAOT-L","metrics":{"F-measure (Mean)":"81.7","FPS":"28.5","J&F":"77.9","Jaccard (Mean)":"74.1"},"paper_url":"https://arxiv.org/abs/2210.09782v3","paper_title":"Decoupling Features in Hierarchical Propagation for Video Object Segmentation","paper_date":"2022-10-18","code_links":[{"title":"yoxu515/aot-benchmark","url":"https://github.com/yoxu515/aot-benchmark"},{"title":"z-x-yang/AOT","url":"https://github.com/z-x-yang/AOT"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":87789,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"KMN","metrics":{"F-measure (Mean)":"80.3","J&F":"77.2","Jaccard (Mean)":"74.1"},"paper_url":"https://arxiv.org/abs/2007.08270v1","paper_title":"Kernelized Memory Network for Video Object Segmentation","paper_date":"2020-07-16","code_links":[{"title":"hkchengrex/Mask-Propagation","url":"https://github.com/hkchengrex/Mask-Propagation"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":87790,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"MiVOS","metrics":{"F-measure (Decay)":"14.5","F-measure (Mean)":"80.2","F-measure (Recall)":"87.6","J&F":"76.5","Jaccard (Decay)":"14.9","Jaccard (Mean)":"72.7","Jaccard (Recall)":"81.2"},"paper_url":"https://arxiv.org/abs/2103.07941v3","paper_title":"Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion","paper_date":"2021-03-14","code_links":[{"title":"hkchengrex/MiVOS","url":"https://github.com/hkchengrex/MiVOS"},{"title":"hkchengrex/Mask-Propagation","url":"https://github.com/hkchengrex/Mask-Propagation"},{"title":"hkchengrex/Scribble-to-Mask","url":"https://github.com/hkchengrex/Scribble-to-Mask"},{"title":"limingxing00/rde-vos-cvpr2022","url":"https://github.com/limingxing00/rde-vos-cvpr2022"},{"title":"Vujas-Eteph/CiVOS","url":"https://github.com/Vujas-Eteph/CiVOS"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":87791,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"DeAOT-B","metrics":{"F-measure (Mean)":"79.9","FPS":"40.9","J&F":"76.2","Jaccard (Mean)":"72.5"},"paper_url":"https://arxiv.org/abs/2210.09782v3","paper_title":"Decoupling Features in Hierarchical Propagation for Video Object Segmentation","paper_date":"2022-10-18","code_links":[{"title":"yoxu515/aot-benchmark","url":"https://github.com/yoxu515/aot-benchmark"},{"title":"z-x-yang/AOT","url":"https://github.com/z-x-yang/AOT"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":87792,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"AOT-B","metrics":{"F-measure (Mean)":"79.3","FPS":"29.6","J&F":"75.5","Jaccard (Mean)":"71.6"},"paper_url":"https://arxiv.org/abs/2106.02638v3","paper_title":"Associating Objects with Transformers for Video Object Segmentation","paper_date":"2021-06-04","code_links":[{"title":"yoxu515/aot-benchmark","url":"https://github.com/yoxu515/aot-benchmark"},{"title":"z-x-yang/AOT","url":"https://github.com/z-x-yang/AOT"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":87793,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"DeAOT-S","metrics":{"F-measure (Mean)":"79.0","FPS":"49.2","J&F":"75.4","Jaccard (Mean)":"71.9"},"paper_url":"https://arxiv.org/abs/2210.09782v3","paper_title":"Decoupling Features in Hierarchical Propagation for Video Object Segmentation","paper_date":"2022-10-18","code_links":[{"title":"yoxu515/aot-benchmark","url":"https://github.com/yoxu515/aot-benchmark"},{"title":"z-x-yang/AOT","url":"https://github.com/z-x-yang/AOT"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":87794,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"RMNet","metrics":{"F-measure (Mean)":"78.1","J&F":"75.0","Jaccard (Mean)":"71.9"},"paper_url":"https://arxiv.org/abs/2103.12934v2","paper_title":"Efficient Regional Memory Network for Video Object Segmentation","paper_date":"2021-03-24","code_links":[{"title":"hzxie/RMNet","url":"https://github.com/hzxie/RMNet"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":87795,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"CFBI","metrics":{"F-measure (Mean)":"78.5","J&F":"74.8","Jaccard (Mean)":"71.1"},"paper_url":"https://arxiv.org/abs/2003.08333v2","paper_title":"Collaborative Video Object Segmentation by Foreground-Background Integration","paper_date":"2020-03-18","code_links":[{"title":"PaddlePaddle/PaddleVideo","url":"https://github.com/PaddlePaddle/PaddleVideo/blob/develop/docs/en/model_zoo/segmentation/cfbi.md"},{"title":"z-x-yang/CFBI","url":"https://github.com/z-x-yang/CFBI"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":87796,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"AOT-S","metrics":{"F-measure (Mean)":"77.5","FPS":"40.0","J&F":"73.9","Jaccard (Mean)":"70.3"},"paper_url":"https://arxiv.org/abs/2106.02638v3","paper_title":"Associating Objects with Transformers for Video Object Segmentation","paper_date":"2021-06-04","code_links":[{"title":"yoxu515/aot-benchmark","url":"https://github.com/yoxu515/aot-benchmark"},{"title":"z-x-yang/AOT","url":"https://github.com/z-x-yang/AOT"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":87797,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"DeAOT-T","metrics":{"F-measure (Mean)":"77.3","FPS":"63.5","J&F":"73.7","Jaccard (Mean)":"70.0"},"paper_url":"https://arxiv.org/abs/2210.09782v3","paper_title":"Decoupling Features in Hierarchical Propagation for Video Object Segmentation","paper_date":"2022-10-18","code_links":[{"title":"yoxu515/aot-benchmark","url":"https://github.com/yoxu515/aot-benchmark"},{"title":"z-x-yang/AOT","url":"https://github.com/z-x-yang/AOT"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":87798,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"STM","metrics":{"F-measure (Decay)":"17.5","F-measure (Mean)":"75.2","F-measure (Recall)":"83.0","J&F":"72.2","Jaccard (Decay)":"16.9","Jaccard (Mean)":"69.3","Jaccard (Recall)":"78.0"},"paper_url":"https://arxiv.org/abs/1904.00607v2","paper_title":"Video Object Segmentation using Space-Time Memory Networks","paper_date":"2019-04-01","code_links":[{"title":"seoungwugoh/STM","url":"https://github.com/seoungwugoh/STM"},{"title":"hkchengrex/Mask-Propagation","url":"https://github.com/hkchengrex/Mask-Propagation"},{"title":"ywcmaike/TianchiVideoCharacterSegmentationPreliminary","url":"https://github.com/ywcmaike/TianchiVideoCharacterSegmentationPreliminary"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":87799,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"AOT-T","metrics":{"F-measure (Mean)":"75.7","FPS":"51.4","J&F":"72.0","Jaccard (Mean)":"68.3"},"paper_url":"https://arxiv.org/abs/2106.02638v3","paper_title":"Associating Objects with Transformers for Video Object Segmentation","paper_date":"2021-06-04","code_links":[{"title":"yoxu515/aot-benchmark","url":"https://github.com/yoxu515/aot-benchmark"},{"title":"z-x-yang/AOT","url":"https://github.com/z-x-yang/AOT"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":87800,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"PReMVOS","metrics":{"F-measure (Decay)":"20.6","F-measure (Mean)":"75.8","F-measure (Recall)":"84.3","J&F":"71.6","Jaccard (Decay)":"21.7","Jaccard (Mean)":"67.5","Jaccard (Recall)":"76.8"},"paper_url":"http://arxiv.org/abs/1807.09190v2","paper_title":"PReMVOS: Proposal-generation, Refinement and Merging for Video Object Segmentation","paper_date":"2018-07-24","code_links":[{"title":"JonathonLuiten/PReMVOS","url":"https://github.com/JonathonLuiten/PReMVOS"},{"title":"VisualComputingInstitute/mots_trackingonly_tools","url":"https://github.com/VisualComputingInstitute/mots_trackingonly_tools"},{"title":"gunpowder78/PReMVOS","url":"https://github.com/gunpowder78/PReMVOS"},{"title":"AyaLotfy/PReMVOS-trial","url":"https://github.com/AyaLotfy/PReMVOS-trial"},{"title":"AyaLotfy/premvos-tmp","url":"https://github.com/AyaLotfy/premvos-tmp"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":87801,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"MHP-VOS","metrics":{"F-measure (Decay)":"19.1","F-measure (Mean)":"72.7","F-measure (Recall)":"82.3","J&F":"69.5","Jaccard (Decay)":"18.0","Jaccard (Mean)":"66.4","Jaccard (Recall)":"76.0"},"paper_url":"http://arxiv.org/abs/1904.08141v1","paper_title":"MHP-VOS: Multiple Hypotheses Propagation for Video Object Segmentation","paper_date":"2019-04-17","code_links":[{"title":"shuangjiexu/MHP-VOS","url":"https://github.com/shuangjiexu/MHP-VOS"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":87802,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"CINM","metrics":{"F-measure (Decay)":"20.0","F-measure (Mean)":"70.5","F-measure (Recall)":"79.6","J&F":"67.5","Jaccard (Decay)":"20.0","Jaccard (Mean)":"64.5","Jaccard (Recall)":"73.8"},"paper_url":"http://arxiv.org/abs/1803.09453v1","paper_title":"CNN in MRF: Video Object Segmentation via Inference in A CNN-Based Higher-Order Spatio-Temporal MRF","paper_date":"2018-03-26","code_links":[],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":87803,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"LSMVOS","metrics":{"F-measure (Decay)":"16.5","F-measure (Mean)":"71.2","F-measure (Recall)":"81.4","J&F":"67.4","Jaccard (Decay)":"16.9","Jaccard (Mean)":"63.7","Jaccard (Recall)":"72.7"},"paper_url":"https://arxiv.org/abs/2009.00771v1","paper_title":"LSMVOS: Long-Short-Term Similarity Matching for Video Object","paper_date":"2020-09-02","code_links":[{"title":"wudao001/LSMVOS","url":"https://github.com/wudao001/LSMVOS"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":87804,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"Lucid","metrics":{"F-measure (Decay)":"19.5","F-measure (Mean)":"69.9","F-measure (Recall)":"80.1","J&F":"66.6","Jaccard (Decay)":"19.5","Jaccard (Mean)":"63.4","Jaccard (Recall)":"74.0"},"paper_url":"http://arxiv.org/abs/1703.09554v5","paper_title":"Lucid Data Dreaming for Video Object Segmentation","paper_date":"2017-03-28","code_links":[{"title":"omkar13/MaskTrack","url":"https://github.com/omkar13/MaskTrack"},{"title":"ankhoreva/LucidDataDreaming","url":"https://github.com/ankhoreva/LucidDataDreaming"},{"title":"yelantingfeng/pyLucid","url":"https://github.com/yelantingfeng/pyLucid"},{"title":"birdman9390/MetaMaskTrack","url":"https://github.com/birdman9390/MetaMaskTrack"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":87805,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"e-OSVOS","metrics":{"F-measure (Mean)":"68.6","J&F":"64.8","Jaccard (Decay)":"22.1","Jaccard (Mean)":"60.9"},"paper_url":"https://arxiv.org/abs/2012.01866v1","paper_title":"Make One-Shot Video Object Segmentation Efficient Again","paper_date":"2020-12-03","code_links":[{"title":"timmeinhardt/trackformer","url":"https://github.com/timmeinhardt/trackformer"},{"title":"acaelles97/devis","url":"https://github.com/acaelles97/devis"},{"title":"dvl-tum/e-osvos","url":"https://github.com/dvl-tum/e-osvos"},{"title":"MindSpore-paper-code-2/code2","url":"https://github.com/MindSpore-paper-code-2/code2/tree/main/OSVOS"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":87806,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"SSM-VOS","metrics":{"F-measure (Decay)":"25.3","F-measure (Mean)":"63.8","J&F":"62.0","Jaccard (Decay)":"23.5","Jaccard (Mean)":"60.2"},"paper_url":"https://ieeexplore.ieee.org/document/9356697","paper_title":"Separable Structure Modeling for Semi-supervised Video Object Segmentation","paper_date":"2021-02-18","code_links":[{"title":"li-plus/SSM-VOS","url":"https://github.com/li-plus/SSM-VOS"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":87807,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"FEELVOS","metrics":{"F-measure (Decay)":"33.5","F-measure (Mean)":"60.9","F-measure (Recall)":"68.5","J&F":"57.8","Jaccard (Decay)":"29.8","Jaccard (Mean)":"55.1","Jaccard (Recall)":"62.6"},"paper_url":"http://arxiv.org/abs/1902.09513v2","paper_title":"FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation","paper_date":"2019-02-25","code_links":[{"title":"tensorflow/models","url":"https://github.com/tensorflow/models"},{"title":"tensorflow/models","url":"https://github.com/tensorflow/models/tree/master/research/feelvos"},{"title":"kim-younghan/FEELVOS","url":"https://github.com/kim-younghan/FEELVOS"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":87808,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"OSVOS-S","metrics":{"F-measure (Decay)":"21.9","F-measure (Mean)":"62.1","F-measure (Recall)":"70.5","J&F":"57.5","Jaccard (Decay)":"24.1","Jaccard (Mean)":"52.9","Jaccard (Recall)":"60.2"},"paper_url":"http://arxiv.org/abs/1709.06031v2","paper_title":"Video Object Segmentation Without Temporal Information","paper_date":"2017-09-18","code_links":[],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":87809,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"RANet","metrics":{"F-measure (Decay)":"22.1","F-measure (Mean)":"57.3","F-measure (Recall)":"67.7","J&F":"55.4","Jaccard (Decay)":"21.9","Jaccard (Mean)":"53.4","Jaccard (Recall)":"61.9"},"paper_url":"https://arxiv.org/abs/1908.06647v4","paper_title":"RANet: Ranking Attention Network for Fast Video Object Segmentation","paper_date":"2019-08-19","code_links":[{"title":"Storife/RANet","url":"https://github.com/Storife/RANet"},{"title":"v1viswan/RANet_modifications","url":"https://github.com/v1viswan/RANet_modifications"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":87810,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"Siam R-CNN","metrics":{"F-measure (Decay)":"20.2","F-measure (Mean)":"58.6","F-measure (Recall)":"62.3","J&F":"53.3","Jaccard (Decay)":"21.8","Jaccard (Mean)":"48.0","Jaccard (Recall)":"53.9"},"paper_url":"https://arxiv.org/abs/1911.12836v2","paper_title":"Siam R-CNN: Visual Tracking by Re-Detection","paper_date":"2019-11-28","code_links":[{"title":"VisualComputingInstitute/SiamR-CNN","url":"https://github.com/VisualComputingInstitute/SiamR-CNN"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":87811,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"RGMP","metrics":{"F-measure (Decay)":"37.2","F-measure (Mean)":"54.4","F-measure (Recall)":"61.9","J&F":"52.8","Jaccard (Decay)":"34.3","Jaccard (Mean)":"51.3","Jaccard (Recall)":"59.0"},"paper_url":"http://openaccess.thecvf.com/content_cvpr_2018/html/Oh_Fast_Video_Object_CVPR_2018_paper.html","paper_title":"Fast Video Object Segmentation by Reference-Guided Mask Propagation","paper_date":"2018-06-01","code_links":[{"title":"seoungwugoh/RGMP","url":"https://github.com/seoungwugoh/RGMP"},{"title":"xanderchf/RGMP","url":"https://github.com/xanderchf/RGMP"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":87812,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"OnAVOS","metrics":{"F-measure (Decay)":"23.4","F-measure (Recall)":"60.3","J&F":"52.8","Jaccard (Decay)":"23.0","Jaccard (Mean)":"49.9","Jaccard (Recall)":"54.3"},"paper_url":"http://arxiv.org/abs/1706.09364v2","paper_title":"Online Adaptation of Convolutional Neural Networks for Video Object Segmentation","paper_date":"2017-06-28","code_links":[],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":87813,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"AGAME","metrics":{"F-measure (Decay)":"27.6","F-measure (Mean)":"55.3","F-measure (Recall)":"61.1","J&F":"52.3","Jaccard (Decay)":"28.9","Jaccard (Mean)":"49.2","Jaccard (Recall)":"53.2"},"paper_url":"http://arxiv.org/abs/1811.11611v2","paper_title":"A Generative Appearance Model for End-to-end Video Object Segmentation","paper_date":"2018-11-28","code_links":[{"title":"joakimjohnander/agame-vos","url":"https://github.com/joakimjohnander/agame-vos"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":87814,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"CapsuleVOS","metrics":{"F-measure (Mean)":"55.2","F-measure (Recall)":"64.6","J&F":"51.3","Jaccard (Mean)":"47.4","Jaccard (Recall)":"54.1"},"paper_url":"https://arxiv.org/abs/1910.00132v1","paper_title":"CapsuleVOS: Semi-Supervised Video Object Segmentation Using Capsule Routing","paper_date":"2019-09-30","code_links":[{"title":"KevinDuarte/CapsuleVOS","url":"https://github.com/KevinDuarte/CapsuleVOS"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":87815,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"OSVOS","metrics":{"F-measure (Decay)":"19.8","F-measure (Recall)":"59.7","J&F":"50.9","Jaccard (Decay)":"19.2","Jaccard (Mean)":"47.0","Jaccard (Recall)":"52.1"},"paper_url":"http://arxiv.org/abs/1611.05198v4","paper_title":"One-Shot Video Object Segmentation","paper_date":"2016-11-16","code_links":[{"title":"kmaninis/OSVOS-PyTorch","url":"https://github.com/kmaninis/OSVOS-PyTorch"},{"title":"scaelles/OSVOS-TensorFlow","url":"https://github.com/scaelles/OSVOS-TensorFlow"},{"title":"kmaninis/OSVOS-caffe","url":"https://github.com/kmaninis/OSVOS-caffe"},{"title":"xiuyu0000/new_papers_codes","url":"https://github.com/xiuyu0000/new_papers_codes/tree/main/OSVOS"},{"title":"code-implementation1/Code6","url":"https://github.com/code-implementation1/Code6/tree/main/OSVOS"},{"title":"MS-Mind/MS-Code-06","url":"https://github.com/MS-Mind/MS-Code-06/tree/main/OSVOS"},{"title":"2023-MindSpore-1/ms-code-215","url":"https://github.com/2023-MindSpore-1/ms-code-215/tree/main/OSVOS"},{"title":"Mind23-2/MindCode-5","url":"https://github.com/Mind23-2/MindCode-5/tree/main/OSVOS"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":87816,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"RVOS","metrics":{"F-measure (Decay)":"36.7","F-measure (Mean)":"52.6","F-measure (Recall)":"61.7","J&F":"50.3","Jaccard (Decay)":"35.7","Jaccard (Mean)":"47.9","Jaccard (Recall)":"54.4"},"paper_url":"https://arxiv.org/abs/1903.05612v2","paper_title":"RVOS: End-to-End Recurrent Network for Video Object Segmentation","paper_date":"2019-03-13","code_links":[{"title":"imatge-upc/rvos","url":"https://github.com/imatge-upc/rvos"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":87817,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"FAVOS","metrics":{"F-measure (Decay)":"19.8","F-measure (Mean)":"44.2","F-measure (Recall)":"51.1","J&F":"43.6","Jaccard (Decay)":"18.1","Jaccard (Mean)":"42.9","Jaccard (Recall)":"48.1"},"paper_url":"http://arxiv.org/abs/1806.02323v1","paper_title":"Fast and Accurate Online Video Object Segmentation via Tracking Parts","paper_date":"2018-06-06","code_links":[{"title":"guanfuchen/video_obj","url":"https://github.com/guanfuchen/video_obj"},{"title":"JingchunCheng/FAVOS","url":"https://github.com/JingchunCheng/FAVOS"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":87818,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"SiamMask","metrics":{"F-measure (Decay)":"22.4","F-measure (Mean)":"45.8","F-measure (Recall)":"45.3","J&F":"43.2","Jaccard (Decay)":"21.9","Jaccard (Mean)":"40.6","Jaccard (Recall)":"44.5"},"paper_url":"https://arxiv.org/abs/1812.05050v2","paper_title":"Fast Online Object Tracking and Segmentation: A Unifying Approach","paper_date":"2018-12-12","code_links":[{"title":"foolwood/SiamMask","url":"https://github.com/foolwood/SiamMask"},{"title":"shallowtoil/DROL","url":"https://github.com/shallowtoil/DROL"},{"title":"ezelikman/anonymal","url":"https://github.com/ezelikman/anonymal"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":87819,"task":"Semi-Supervised Video Object Segmentation","parent_task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model_name":"OSMN","metrics":{"F-measure (Decay)":"17.4","F-measure (Recall)":"47.4","J&F":"41.3","Jaccard (Decay)":"19.0","Jaccard (Mean)":"37.7","Jaccard (Recall)":"38.9"},"paper_url":"http://arxiv.org/abs/1802.01218v1","paper_title":"Efficient Video Object Segmentation via Network Modulation","paper_date":"2018-02-04","code_links":[{"title":"linjieyangsc/video_seg","url":"https://github.com/linjieyangsc/video_seg"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":107172,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"Cutie+ (base, MEGA)","metrics":{"F-measure (Mean)":"91.4","FPS":"17.9","J&F":"88.1","Jaccard (Mean)":"84.7"},"paper_url":"https://arxiv.org/abs/2310.12982v2","paper_title":"Putting the Object Back into Video Object Segmentation","paper_date":"2023-10-19","code_links":[{"title":"hkchengrex/Cutie","url":"https://github.com/hkchengrex/Cutie"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":107173,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"Cutie (base, MEGA)","metrics":{"F-measure (Mean)":"89.9","FPS":"36.4","J&F":"86.1","Jaccard (Mean)":"82.4"},"paper_url":"https://arxiv.org/abs/2310.12982v2","paper_title":"Putting the Object Back into Video Object Segmentation","paper_date":"2023-10-19","code_links":[{"title":"hkchengrex/Cutie","url":"https://github.com/hkchengrex/Cutie"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":107174,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"Cutie+ (base)","metrics":{"F-measure (Mean)":"89.2","FPS":"17.9","J&F":"85.9","Jaccard (Mean)":"82.6"},"paper_url":"https://arxiv.org/abs/2310.12982v2","paper_title":"Putting the Object Back into Video Object Segmentation","paper_date":"2023-10-19","code_links":[{"title":"hkchengrex/Cutie","url":"https://github.com/hkchengrex/Cutie"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":107175,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"SwinB-AOST (L'=3, MS)","metrics":{"F-measure (Mean)":"88.5","FPS":"1.3","J&F":"84.7","Jaccard (Mean)":"80.9"},"paper_url":"https://arxiv.org/abs/2203.11442v8","paper_title":"Scalable Video Object Segmentation with Identification Mechanism","paper_date":"2022-03-22","code_links":[{"title":"yoxu515/aot-benchmark","url":"https://github.com/yoxu515/aot-benchmark"},{"title":"z-x-yang/AOT","url":"https://github.com/z-x-yang/AOT"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":107176,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"SwinB-AOTv2-L","metrics":{"F-measure (Mean)":"87.9","FPS":"1.3","J&F":"84.5","Jaccard (Mean)":"81.0"},"paper_url":"https://arxiv.org/abs/2203.11442v8","paper_title":"Scalable Video Object Segmentation with Identification Mechanism","paper_date":"2022-03-22","code_links":[{"title":"yoxu515/aot-benchmark","url":"https://github.com/yoxu515/aot-benchmark"},{"title":"z-x-yang/AOT","url":"https://github.com/z-x-yang/AOT"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":107177,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"JIMD-R50","metrics":{"F-measure (Mean)":"87.4","J&F":"83.9","Jaccard (Mean)":"80.3"},"paper_url":"https://arxiv.org/abs/2409.14343v1","paper_title":"Memory Matching is not Enough: Jointly Improving Memory Matching and Decoding for Video Object Segmentation","paper_date":"2024-09-22","code_links":[],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":107178,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"XMem (BL30K, MS)","metrics":{"F-measure (Mean)":"87.0","J&F":"83.7","Jaccard (Mean)":"80.5"},"paper_url":"https://arxiv.org/abs/2207.07115v2","paper_title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","paper_date":"2022-07-14","code_links":[{"title":"hkchengrex/XMem","url":"https://github.com/hkchengrex/XMem"},{"title":"tianyuan168326/videosemanticcompression-pytorch","url":"https://github.com/tianyuan168326/videosemanticcompression-pytorch"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":107179,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"DEVA","metrics":{"F-measure (Mean)":"86.8","FPS":"25.3","J&F":"83.2","Jaccard (Mean)":"79.6"},"paper_url":"https://arxiv.org/abs/2309.03903v1","paper_title":"Tracking Anything with Decoupled Video Segmentation","paper_date":"2023-09-07","code_links":[{"title":"hkchengrex/Tracking-Anything-with-DEVA","url":"https://github.com/hkchengrex/Tracking-Anything-with-DEVA"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":107180,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"XMem (MS)","metrics":{"F-measure (Mean)":"86.4","J&F":"83.1","Jaccard (Mean)":"79.7"},"paper_url":"https://arxiv.org/abs/2207.07115v2","paper_title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","paper_date":"2022-07-14","code_links":[{"title":"hkchengrex/XMem","url":"https://github.com/hkchengrex/XMem"},{"title":"tianyuan168326/videosemanticcompression-pytorch","url":"https://github.com/tianyuan168326/videosemanticcompression-pytorch"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":107181,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"SwinB-DeAOT-L","metrics":{"F-measure (Mean)":"86.7","FPS":"15.4","J&F":"82.8","Jaccard (Mean)":"78.9"},"paper_url":"https://arxiv.org/abs/2210.09782v3","paper_title":"Decoupling Features in Hierarchical Propagation for Video Object Segmentation","paper_date":"2022-10-18","code_links":[{"title":"yoxu515/aot-benchmark","url":"https://github.com/yoxu515/aot-benchmark"},{"title":"z-x-yang/AOT","url":"https://github.com/z-x-yang/AOT"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":107182,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"SwinB-AOST (L'=3)","metrics":{"F-measure (Mean)":"86.6","FPS":"12.0","J&F":"82.7","Jaccard (Mean)":"78.8"},"paper_url":"https://arxiv.org/abs/2203.11442v8","paper_title":"Scalable Video Object Segmentation with Identification Mechanism","paper_date":"2022-03-22","code_links":[{"title":"yoxu515/aot-benchmark","url":"https://github.com/yoxu515/aot-benchmark"},{"title":"z-x-yang/AOT","url":"https://github.com/z-x-yang/AOT"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":107183,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"XMem (BL30K, 600p)","metrics":{"F-measure (Mean)":"85.8","J&F":"82.5","Jaccard (Mean)":"79.1"},"paper_url":"https://arxiv.org/abs/2207.07115v2","paper_title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","paper_date":"2022-07-14","code_links":[{"title":"hkchengrex/XMem","url":"https://github.com/hkchengrex/XMem"},{"title":"tianyuan168326/videosemanticcompression-pytorch","url":"https://github.com/tianyuan168326/videosemanticcompression-pytorch"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":107184,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"QDMN","metrics":{"F-measure (Mean)":"85.4","J&F":"81.9","Jaccard (Mean)":"78.1"},"paper_url":"https://arxiv.org/abs/2207.07922v1","paper_title":"Learning Quality-aware Dynamic Memory for Video Object Segmentation","paper_date":"2022-07-16","code_links":[{"title":"workforai/qdmn","url":"https://github.com/workforai/qdmn"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":107185,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"XMem (BL30K)","metrics":{"F-measure (Mean)":"84.7","J&F":"81.2","Jaccard (Mean)":"77.6"},"paper_url":"https://arxiv.org/abs/2207.07115v2","paper_title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","paper_date":"2022-07-14","code_links":[{"title":"hkchengrex/XMem","url":"https://github.com/hkchengrex/XMem"},{"title":"tianyuan168326/videosemanticcompression-pytorch","url":"https://github.com/tianyuan168326/videosemanticcompression-pytorch"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":107186,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"SwinB-AOT-L","metrics":{"F-measure (Mean)":"85.1","FPS":"12.1","J&F":"81.2","Jaccard (Mean)":"77.3"},"paper_url":"https://arxiv.org/abs/2106.02638v3","paper_title":"Associating Objects with Transformers for Video Object Segmentation","paper_date":"2021-06-04","code_links":[{"title":"yoxu515/aot-benchmark","url":"https://github.com/yoxu515/aot-benchmark"},{"title":"z-x-yang/AOT","url":"https://github.com/z-x-yang/AOT"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":107187,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"RPCMVOS-Full-Res","metrics":{"F-measure (Mean)":"84.3","J&F":"81","Jaccard (Mean)":"77.6"},"paper_url":"https://arxiv.org/abs/2112.02853v1","paper_title":"Reliable Propagation-Correction Modulation for Video Object Segmentation","paper_date":"2021-12-06","code_links":[{"title":"jerryx1110/rpcmvos","url":"https://github.com/jerryx1110/rpcmvos"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":107188,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"XMem","metrics":{"F-measure (Mean)":"84.5","J&F":"81.0","Jaccard (Mean)":"77.4"},"paper_url":"https://arxiv.org/abs/2207.07115v2","paper_title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","paper_date":"2022-07-14","code_links":[{"title":"hkchengrex/XMem","url":"https://github.com/hkchengrex/XMem"},{"title":"tianyuan168326/videosemanticcompression-pytorch","url":"https://github.com/tianyuan168326/videosemanticcompression-pytorch"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":107189,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"R50-DeAOT-L","metrics":{"F-measure (Mean)":"84.5","FPS":"27.0","J&F":"80.7","Jaccard (Mean)":"76.9"},"paper_url":"https://arxiv.org/abs/2210.09782v3","paper_title":"Decoupling Features in Hierarchical Propagation for Video Object Segmentation","paper_date":"2022-10-18","code_links":[{"title":"yoxu515/aot-benchmark","url":"https://github.com/yoxu515/aot-benchmark"},{"title":"z-x-yang/AOT","url":"https://github.com/z-x-yang/AOT"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":107190,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"STCN","metrics":{"F-measure (Decay)":"10.3","F-measure (Mean)":"83.5","F-measure (Recall)":"89.7","J&F":"79.9","Jaccard (Decay)":"10.5","Jaccard (Mean)":"76.3","Jaccard (Recall)":"85.5"},"paper_url":"https://arxiv.org/abs/2106.05210v2","paper_title":"Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation","paper_date":"2021-06-09","code_links":[{"title":"hkchengrex/STCN","url":"https://github.com/hkchengrex/STCN"},{"title":"limingxing00/rde-vos-cvpr2022","url":"https://github.com/limingxing00/rde-vos-cvpr2022"},{"title":"alipga/AMM_VOS","url":"https://github.com/alipga/AMM_VOS"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":107191,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"R50-AOST (L'=3)","metrics":{"F-measure (Mean)":"83.6","FPS":"17.5","J&F":"79.9","Jaccard (Mean)":"76.2"},"paper_url":"https://arxiv.org/abs/2203.11442v8","paper_title":"Scalable Video Object Segmentation with Identification Mechanism","paper_date":"2022-03-22","code_links":[{"title":"yoxu515/aot-benchmark","url":"https://github.com/yoxu515/aot-benchmark"},{"title":"z-x-yang/AOT","url":"https://github.com/z-x-yang/AOT"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":107192,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"XMem (DAVIS and YouTubeVOS only)","metrics":{"F-measure (Mean)":"83.4","J&F":"79.8","Jaccard (Mean)":"76.3"},"paper_url":"https://arxiv.org/abs/2207.07115v2","paper_title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","paper_date":"2022-07-14","code_links":[{"title":"hkchengrex/XMem","url":"https://github.com/hkchengrex/XMem"},{"title":"tianyuan168326/videosemanticcompression-pytorch","url":"https://github.com/tianyuan168326/videosemanticcompression-pytorch"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":107193,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"R50-AOT-L","metrics":{"F-measure (Mean)":"83.3","FPS":"18.0","J&F":"79.6","Jaccard (Mean)":"75.9"},"paper_url":"https://arxiv.org/abs/2106.02638v3","paper_title":"Associating Objects with Transformers for Video Object Segmentation","paper_date":"2021-06-04","code_links":[{"title":"yoxu515/aot-benchmark","url":"https://github.com/yoxu515/aot-benchmark"},{"title":"z-x-yang/AOT","url":"https://github.com/z-x-yang/AOT"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":107194,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"RPCMVOS","metrics":{"F-measure (Mean)":"82.6","J&F":"79.2","Jaccard (Mean)":"75.8"},"paper_url":"https://arxiv.org/abs/2112.02853v1","paper_title":"Reliable Propagation-Correction Modulation for Video Object Segmentation","paper_date":"2021-12-06","code_links":[{"title":"jerryx1110/rpcmvos","url":"https://github.com/jerryx1110/rpcmvos"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":107195,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"HMMN","metrics":{"F-measure (Mean)":"82.5","J&F":"78.6","Jaccard (Mean)":"74.7"},"paper_url":"https://arxiv.org/abs/2109.11404v1","paper_title":"Hierarchical Memory Matching Network for Video Object Segmentation","paper_date":"2021-09-23","code_links":[{"title":"hongje/hmmn","url":"https://github.com/hongje/hmmn"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":107196,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"AOT-L","metrics":{"F-measure (Mean)":"82.3","FPS":"18.7","J&F":"78.3","Jaccard (Mean)":"74.3"},"paper_url":"https://arxiv.org/abs/2106.02638v3","paper_title":"Associating Objects with Transformers for Video Object Segmentation","paper_date":"2021-06-04","code_links":[{"title":"yoxu515/aot-benchmark","url":"https://github.com/yoxu515/aot-benchmark"},{"title":"z-x-yang/AOT","url":"https://github.com/z-x-yang/AOT"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":107197,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"R50-AOST (L'=2)","metrics":{"F-measure (Mean)":"81.7","FPS":"24.3","J&F":"78.1","Jaccard (Mean)":"74.5"},"paper_url":"https://arxiv.org/abs/2203.11442v8","paper_title":"Scalable Video Object Segmentation with Identification Mechanism","paper_date":"2022-03-22","code_links":[{"title":"yoxu515/aot-benchmark","url":"https://github.com/yoxu515/aot-benchmark"},{"title":"z-x-yang/AOT","url":"https://github.com/z-x-yang/AOT"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":107198,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"CFBI+","metrics":{"F-measure (Mean)":"81.6","J&F":"78.0","Jaccard (Mean)":"74.4"},"paper_url":"https://arxiv.org/abs/2010.06349v2","paper_title":"Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration","paper_date":"2020-10-13","code_links":[{"title":"z-x-yang/CFBI","url":"https://github.com/z-x-yang/CFBI"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":107199,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"DeAOT-L","metrics":{"F-measure (Mean)":"81.7","FPS":"28.5","J&F":"77.9","Jaccard (Mean)":"74.1"},"paper_url":"https://arxiv.org/abs/2210.09782v3","paper_title":"Decoupling Features in Hierarchical Propagation for Video Object Segmentation","paper_date":"2022-10-18","code_links":[{"title":"yoxu515/aot-benchmark","url":"https://github.com/yoxu515/aot-benchmark"},{"title":"z-x-yang/AOT","url":"https://github.com/z-x-yang/AOT"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":107200,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"KMN","metrics":{"F-measure (Mean)":"80.3","J&F":"77.2","Jaccard (Mean)":"74.1"},"paper_url":"https://arxiv.org/abs/2007.08270v1","paper_title":"Kernelized Memory Network for Video Object Segmentation","paper_date":"2020-07-16","code_links":[{"title":"hkchengrex/Mask-Propagation","url":"https://github.com/hkchengrex/Mask-Propagation"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":107201,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"MiVOS","metrics":{"F-measure (Decay)":"14.5","F-measure (Mean)":"80.2","F-measure (Recall)":"87.6","J&F":"76.5","Jaccard (Decay)":"14.9","Jaccard (Mean)":"72.7","Jaccard (Recall)":"81.2"},"paper_url":"https://arxiv.org/abs/2103.07941v3","paper_title":"Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion","paper_date":"2021-03-14","code_links":[{"title":"hkchengrex/MiVOS","url":"https://github.com/hkchengrex/MiVOS"},{"title":"hkchengrex/Mask-Propagation","url":"https://github.com/hkchengrex/Mask-Propagation"},{"title":"hkchengrex/Scribble-to-Mask","url":"https://github.com/hkchengrex/Scribble-to-Mask"},{"title":"limingxing00/rde-vos-cvpr2022","url":"https://github.com/limingxing00/rde-vos-cvpr2022"},{"title":"Vujas-Eteph/CiVOS","url":"https://github.com/Vujas-Eteph/CiVOS"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":107202,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"DeAOT-B","metrics":{"F-measure (Mean)":"79.9","FPS":"40.9","J&F":"76.2","Jaccard (Mean)":"72.5"},"paper_url":"https://arxiv.org/abs/2210.09782v3","paper_title":"Decoupling Features in Hierarchical Propagation for Video Object Segmentation","paper_date":"2022-10-18","code_links":[{"title":"yoxu515/aot-benchmark","url":"https://github.com/yoxu515/aot-benchmark"},{"title":"z-x-yang/AOT","url":"https://github.com/z-x-yang/AOT"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":107203,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"AOT-B","metrics":{"F-measure (Mean)":"79.3","FPS":"29.6","J&F":"75.5","Jaccard (Mean)":"71.6"},"paper_url":"https://arxiv.org/abs/2106.02638v3","paper_title":"Associating Objects with Transformers for Video Object Segmentation","paper_date":"2021-06-04","code_links":[{"title":"yoxu515/aot-benchmark","url":"https://github.com/yoxu515/aot-benchmark"},{"title":"z-x-yang/AOT","url":"https://github.com/z-x-yang/AOT"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":107204,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"DeAOT-S","metrics":{"F-measure (Mean)":"79.0","FPS":"49.2","J&F":"75.4","Jaccard (Mean)":"71.9"},"paper_url":"https://arxiv.org/abs/2210.09782v3","paper_title":"Decoupling Features in Hierarchical Propagation for Video Object Segmentation","paper_date":"2022-10-18","code_links":[{"title":"yoxu515/aot-benchmark","url":"https://github.com/yoxu515/aot-benchmark"},{"title":"z-x-yang/AOT","url":"https://github.com/z-x-yang/AOT"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":107205,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"RMNet","metrics":{"F-measure (Mean)":"78.1","J&F":"75.0","Jaccard (Mean)":"71.9"},"paper_url":"https://arxiv.org/abs/2103.12934v2","paper_title":"Efficient Regional Memory Network for Video Object Segmentation","paper_date":"2021-03-24","code_links":[{"title":"hzxie/RMNet","url":"https://github.com/hzxie/RMNet"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":107206,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"CFBI","metrics":{"F-measure (Mean)":"78.5","J&F":"74.8","Jaccard (Mean)":"71.1"},"paper_url":"https://arxiv.org/abs/2003.08333v2","paper_title":"Collaborative Video Object Segmentation by Foreground-Background Integration","paper_date":"2020-03-18","code_links":[{"title":"PaddlePaddle/PaddleVideo","url":"https://github.com/PaddlePaddle/PaddleVideo/blob/develop/docs/en/model_zoo/segmentation/cfbi.md"},{"title":"z-x-yang/CFBI","url":"https://github.com/z-x-yang/CFBI"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":107207,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"AOT-S","metrics":{"F-measure (Mean)":"77.5","FPS":"40.0","J&F":"73.9","Jaccard (Mean)":"70.3"},"paper_url":"https://arxiv.org/abs/2106.02638v3","paper_title":"Associating Objects with Transformers for Video Object Segmentation","paper_date":"2021-06-04","code_links":[{"title":"yoxu515/aot-benchmark","url":"https://github.com/yoxu515/aot-benchmark"},{"title":"z-x-yang/AOT","url":"https://github.com/z-x-yang/AOT"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":107208,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"DeAOT-T","metrics":{"F-measure (Mean)":"77.3","FPS":"63.5","J&F":"73.7","Jaccard (Mean)":"70.0"},"paper_url":"https://arxiv.org/abs/2210.09782v3","paper_title":"Decoupling Features in Hierarchical Propagation for Video Object Segmentation","paper_date":"2022-10-18","code_links":[{"title":"yoxu515/aot-benchmark","url":"https://github.com/yoxu515/aot-benchmark"},{"title":"z-x-yang/AOT","url":"https://github.com/z-x-yang/AOT"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":107209,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"STM","metrics":{"F-measure (Decay)":"17.5","F-measure (Mean)":"75.2","F-measure (Recall)":"83.0","J&F":"72.2","Jaccard (Decay)":"16.9","Jaccard (Mean)":"69.3","Jaccard (Recall)":"78.0"},"paper_url":"https://arxiv.org/abs/1904.00607v2","paper_title":"Video Object Segmentation using Space-Time Memory Networks","paper_date":"2019-04-01","code_links":[{"title":"seoungwugoh/STM","url":"https://github.com/seoungwugoh/STM"},{"title":"hkchengrex/Mask-Propagation","url":"https://github.com/hkchengrex/Mask-Propagation"},{"title":"ywcmaike/TianchiVideoCharacterSegmentationPreliminary","url":"https://github.com/ywcmaike/TianchiVideoCharacterSegmentationPreliminary"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":107210,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"AOT-T","metrics":{"F-measure (Mean)":"75.7","FPS":"51.4","J&F":"72.0","Jaccard (Mean)":"68.3"},"paper_url":"https://arxiv.org/abs/2106.02638v3","paper_title":"Associating Objects with Transformers for Video Object Segmentation","paper_date":"2021-06-04","code_links":[{"title":"yoxu515/aot-benchmark","url":"https://github.com/yoxu515/aot-benchmark"},{"title":"z-x-yang/AOT","url":"https://github.com/z-x-yang/AOT"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":107211,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"PReMVOS","metrics":{"F-measure (Decay)":"20.6","F-measure (Mean)":"75.8","F-measure (Recall)":"84.3","J&F":"71.6","Jaccard (Decay)":"21.7","Jaccard (Mean)":"67.5","Jaccard (Recall)":"76.8"},"paper_url":"http://arxiv.org/abs/1807.09190v2","paper_title":"PReMVOS: Proposal-generation, Refinement and Merging for Video Object Segmentation","paper_date":"2018-07-24","code_links":[{"title":"JonathonLuiten/PReMVOS","url":"https://github.com/JonathonLuiten/PReMVOS"},{"title":"VisualComputingInstitute/mots_trackingonly_tools","url":"https://github.com/VisualComputingInstitute/mots_trackingonly_tools"},{"title":"gunpowder78/PReMVOS","url":"https://github.com/gunpowder78/PReMVOS"},{"title":"AyaLotfy/PReMVOS-trial","url":"https://github.com/AyaLotfy/PReMVOS-trial"},{"title":"AyaLotfy/premvos-tmp","url":"https://github.com/AyaLotfy/premvos-tmp"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":107212,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"MHP-VOS","metrics":{"F-measure (Decay)":"19.1","F-measure (Mean)":"72.7","F-measure (Recall)":"82.3","J&F":"69.5","Jaccard (Decay)":"18.0","Jaccard (Mean)":"66.4","Jaccard (Recall)":"76.0"},"paper_url":"http://arxiv.org/abs/1904.08141v1","paper_title":"MHP-VOS: Multiple Hypotheses Propagation for Video Object Segmentation","paper_date":"2019-04-17","code_links":[{"title":"shuangjiexu/MHP-VOS","url":"https://github.com/shuangjiexu/MHP-VOS"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":107213,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"CINM","metrics":{"F-measure (Decay)":"20.0","F-measure (Mean)":"70.5","F-measure (Recall)":"79.6","J&F":"67.5","Jaccard (Decay)":"20.0","Jaccard (Mean)":"64.5","Jaccard (Recall)":"73.8"},"paper_url":"http://arxiv.org/abs/1803.09453v1","paper_title":"CNN in MRF: Video Object Segmentation via Inference in A CNN-Based Higher-Order Spatio-Temporal MRF","paper_date":"2018-03-26","code_links":[],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":107214,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"LSMVOS","metrics":{"F-measure (Decay)":"16.5","F-measure (Mean)":"71.2","F-measure (Recall)":"81.4","J&F":"67.4","Jaccard (Decay)":"16.9","Jaccard (Mean)":"63.7","Jaccard (Recall)":"72.7"},"paper_url":"https://arxiv.org/abs/2009.00771v1","paper_title":"LSMVOS: Long-Short-Term Similarity Matching for Video Object","paper_date":"2020-09-02","code_links":[{"title":"wudao001/LSMVOS","url":"https://github.com/wudao001/LSMVOS"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":107215,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"Lucid","metrics":{"F-measure (Decay)":"19.5","F-measure (Mean)":"69.9","F-measure (Recall)":"80.1","J&F":"66.6","Jaccard (Decay)":"19.5","Jaccard (Mean)":"63.4","Jaccard (Recall)":"74.0"},"paper_url":"http://arxiv.org/abs/1703.09554v5","paper_title":"Lucid Data Dreaming for Video Object Segmentation","paper_date":"2017-03-28","code_links":[{"title":"omkar13/MaskTrack","url":"https://github.com/omkar13/MaskTrack"},{"title":"ankhoreva/LucidDataDreaming","url":"https://github.com/ankhoreva/LucidDataDreaming"},{"title":"yelantingfeng/pyLucid","url":"https://github.com/yelantingfeng/pyLucid"},{"title":"birdman9390/MetaMaskTrack","url":"https://github.com/birdman9390/MetaMaskTrack"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":107216,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"e-OSVOS","metrics":{"F-measure (Mean)":"68.6","J&F":"64.8","Jaccard (Decay)":"22.1","Jaccard (Mean)":"60.9"},"paper_url":"https://arxiv.org/abs/2012.01866v1","paper_title":"Make One-Shot Video Object Segmentation Efficient Again","paper_date":"2020-12-03","code_links":[{"title":"timmeinhardt/trackformer","url":"https://github.com/timmeinhardt/trackformer"},{"title":"acaelles97/devis","url":"https://github.com/acaelles97/devis"},{"title":"dvl-tum/e-osvos","url":"https://github.com/dvl-tum/e-osvos"},{"title":"MindSpore-paper-code-2/code2","url":"https://github.com/MindSpore-paper-code-2/code2/tree/main/OSVOS"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":107217,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"SSM-VOS","metrics":{"F-measure (Decay)":"25.3","F-measure (Mean)":"63.8","J&F":"62.0","Jaccard (Decay)":"23.5","Jaccard (Mean)":"60.2"},"paper_url":"https://ieeexplore.ieee.org/document/9356697","paper_title":"Separable Structure Modeling for Semi-supervised Video Object Segmentation","paper_date":"2021-02-18","code_links":[{"title":"li-plus/SSM-VOS","url":"https://github.com/li-plus/SSM-VOS"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":107218,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"FEELVOS","metrics":{"F-measure (Decay)":"33.5","F-measure (Mean)":"60.9","F-measure (Recall)":"68.5","J&F":"57.8","Jaccard (Decay)":"29.8","Jaccard (Mean)":"55.1","Jaccard (Recall)":"62.6"},"paper_url":"http://arxiv.org/abs/1902.09513v2","paper_title":"FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation","paper_date":"2019-02-25","code_links":[{"title":"tensorflow/models","url":"https://github.com/tensorflow/models"},{"title":"tensorflow/models","url":"https://github.com/tensorflow/models/tree/master/research/feelvos"},{"title":"kim-younghan/FEELVOS","url":"https://github.com/kim-younghan/FEELVOS"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":107219,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"OSVOS-S","metrics":{"F-measure (Decay)":"21.9","F-measure (Mean)":"62.1","F-measure (Recall)":"70.5","J&F":"57.5","Jaccard (Decay)":"24.1","Jaccard (Mean)":"52.9","Jaccard (Recall)":"60.2"},"paper_url":"http://arxiv.org/abs/1709.06031v2","paper_title":"Video Object Segmentation Without Temporal Information","paper_date":"2017-09-18","code_links":[],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":107220,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"RANet","metrics":{"F-measure (Decay)":"22.1","F-measure (Mean)":"57.3","F-measure (Recall)":"67.7","J&F":"55.4","Jaccard (Decay)":"21.9","Jaccard (Mean)":"53.4","Jaccard (Recall)":"61.9"},"paper_url":"https://arxiv.org/abs/1908.06647v4","paper_title":"RANet: Ranking Attention Network for Fast Video Object Segmentation","paper_date":"2019-08-19","code_links":[{"title":"Storife/RANet","url":"https://github.com/Storife/RANet"},{"title":"v1viswan/RANet_modifications","url":"https://github.com/v1viswan/RANet_modifications"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":107221,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"Siam R-CNN","metrics":{"F-measure (Decay)":"20.2","F-measure (Mean)":"58.6","F-measure (Recall)":"62.3","J&F":"53.3","Jaccard (Decay)":"21.8","Jaccard (Mean)":"48.0","Jaccard (Recall)":"53.9"},"paper_url":"https://arxiv.org/abs/1911.12836v2","paper_title":"Siam R-CNN: Visual Tracking by Re-Detection","paper_date":"2019-11-28","code_links":[{"title":"VisualComputingInstitute/SiamR-CNN","url":"https://github.com/VisualComputingInstitute/SiamR-CNN"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":107222,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"RGMP","metrics":{"F-measure (Decay)":"37.2","F-measure (Mean)":"54.4","F-measure (Recall)":"61.9","J&F":"52.8","Jaccard (Decay)":"34.3","Jaccard (Mean)":"51.3","Jaccard (Recall)":"59.0"},"paper_url":"http://openaccess.thecvf.com/content_cvpr_2018/html/Oh_Fast_Video_Object_CVPR_2018_paper.html","paper_title":"Fast Video Object Segmentation by Reference-Guided Mask Propagation","paper_date":"2018-06-01","code_links":[{"title":"seoungwugoh/RGMP","url":"https://github.com/seoungwugoh/RGMP"},{"title":"xanderchf/RGMP","url":"https://github.com/xanderchf/RGMP"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":107223,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"OnAVOS","metrics":{"F-measure (Decay)":"23.4","F-measure (Recall)":"60.3","J&F":"52.8","Jaccard (Decay)":"23.0","Jaccard (Mean)":"49.9","Jaccard (Recall)":"54.3"},"paper_url":"http://arxiv.org/abs/1706.09364v2","paper_title":"Online Adaptation of Convolutional Neural Networks for Video Object Segmentation","paper_date":"2017-06-28","code_links":[],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":107224,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"AGAME","metrics":{"F-measure (Decay)":"27.6","F-measure (Mean)":"55.3","F-measure (Recall)":"61.1","J&F":"52.3","Jaccard (Decay)":"28.9","Jaccard (Mean)":"49.2","Jaccard (Recall)":"53.2"},"paper_url":"http://arxiv.org/abs/1811.11611v2","paper_title":"A Generative Appearance Model for End-to-end Video Object Segmentation","paper_date":"2018-11-28","code_links":[{"title":"joakimjohnander/agame-vos","url":"https://github.com/joakimjohnander/agame-vos"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":107225,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"CapsuleVOS","metrics":{"F-measure (Mean)":"55.2","F-measure (Recall)":"64.6","J&F":"51.3","Jaccard (Mean)":"47.4","Jaccard (Recall)":"54.1"},"paper_url":"https://arxiv.org/abs/1910.00132v1","paper_title":"CapsuleVOS: Semi-Supervised Video Object Segmentation Using Capsule Routing","paper_date":"2019-09-30","code_links":[{"title":"KevinDuarte/CapsuleVOS","url":"https://github.com/KevinDuarte/CapsuleVOS"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":107226,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"OSVOS","metrics":{"F-measure (Decay)":"19.8","F-measure (Recall)":"59.7","J&F":"50.9","Jaccard (Decay)":"19.2","Jaccard (Mean)":"47.0","Jaccard (Recall)":"52.1"},"paper_url":"http://arxiv.org/abs/1611.05198v4","paper_title":"One-Shot Video Object Segmentation","paper_date":"2016-11-16","code_links":[{"title":"kmaninis/OSVOS-PyTorch","url":"https://github.com/kmaninis/OSVOS-PyTorch"},{"title":"scaelles/OSVOS-TensorFlow","url":"https://github.com/scaelles/OSVOS-TensorFlow"},{"title":"kmaninis/OSVOS-caffe","url":"https://github.com/kmaninis/OSVOS-caffe"},{"title":"xiuyu0000/new_papers_codes","url":"https://github.com/xiuyu0000/new_papers_codes/tree/main/OSVOS"},{"title":"code-implementation1/Code6","url":"https://github.com/code-implementation1/Code6/tree/main/OSVOS"},{"title":"MS-Mind/MS-Code-06","url":"https://github.com/MS-Mind/MS-Code-06/tree/main/OSVOS"},{"title":"2023-MindSpore-1/ms-code-215","url":"https://github.com/2023-MindSpore-1/ms-code-215/tree/main/OSVOS"},{"title":"Mind23-2/MindCode-5","url":"https://github.com/Mind23-2/MindCode-5/tree/main/OSVOS"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":107227,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"RVOS","metrics":{"F-measure (Decay)":"36.7","F-measure (Mean)":"52.6","F-measure (Recall)":"61.7","J&F":"50.3","Jaccard (Decay)":"35.7","Jaccard (Mean)":"47.9","Jaccard (Recall)":"54.4"},"paper_url":"https://arxiv.org/abs/1903.05612v2","paper_title":"RVOS: End-to-End Recurrent Network for Video Object Segmentation","paper_date":"2019-03-13","code_links":[{"title":"imatge-upc/rvos","url":"https://github.com/imatge-upc/rvos"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":107228,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"FAVOS","metrics":{"F-measure (Decay)":"19.8","F-measure (Mean)":"44.2","F-measure (Recall)":"51.1","J&F":"43.6","Jaccard (Decay)":"18.1","Jaccard (Mean)":"42.9","Jaccard (Recall)":"48.1"},"paper_url":"http://arxiv.org/abs/1806.02323v1","paper_title":"Fast and Accurate Online Video Object Segmentation via Tracking Parts","paper_date":"2018-06-06","code_links":[{"title":"guanfuchen/video_obj","url":"https://github.com/guanfuchen/video_obj"},{"title":"JingchunCheng/FAVOS","url":"https://github.com/JingchunCheng/FAVOS"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":107229,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"SiamMask","metrics":{"F-measure (Decay)":"22.4","F-measure (Mean)":"45.8","F-measure (Recall)":"45.3","J&F":"43.2","Jaccard (Decay)":"21.9","Jaccard (Mean)":"40.6","Jaccard (Recall)":"44.5"},"paper_url":"https://arxiv.org/abs/1812.05050v2","paper_title":"Fast Online Object Tracking and Segmentation: A Unifying Approach","paper_date":"2018-12-12","code_links":[{"title":"foolwood/SiamMask","url":"https://github.com/foolwood/SiamMask"},{"title":"shallowtoil/DROL","url":"https://github.com/shallowtoil/DROL"},{"title":"ezelikman/anonymal","url":"https://github.com/ezelikman/anonymal"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":107230,"task":"Semi-Supervised Video Object Segmentation","parent_task":null,"dataset":"DAVIS 2017 (test-dev)","model_name":"OSMN","metrics":{"F-measure (Decay)":"17.4","F-measure (Recall)":"47.4","J&F":"41.3","Jaccard (Decay)":"19.0","Jaccard (Mean)":"37.7","Jaccard (Recall)":"38.9"},"paper_url":"http://arxiv.org/abs/1802.01218v1","paper_title":"Efficient Video Object Segmentation via Network Modulation","paper_date":"2018-02-04","code_links":[{"title":"linjieyangsc/video_seg","url":"https://github.com/linjieyangsc/video_seg"}],"metrics_order":"[\"J&F\", \"Jaccard (Mean)\", \"Jaccard (Recall)\", \"Jaccard (Decay)\", \"F-measure (Mean)\", \"F-measure (Recall)\", \"F-measure (Decay)\", \"FPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]}]}