{"task":"Video Instance Segmentation","dataset":"OVIS validation","metric_names":["mask AP","AP50","AP75","APho","APmo","AR1","APso","AR10"],"rows":[{"id":111386,"task":"Video Instance Segmentation","parent_task":null,"dataset":"OVIS validation","model_name":"DVIS-DAQ(VIT-L, Offline)","metrics":{"AP50":"83.8","AP75":"62.9","mask AP":"57.1"},"paper_url":"https://arxiv.org/abs/2404.00086v5","paper_title":"DVIS-DAQ: Improving Video Segmentation via Dynamic Anchor Queries","paper_date":"2024-03-29","code_links":[{"title":"zhang-tao-whu/DVIS","url":"https://github.com/zhang-tao-whu/DVIS"},{"title":"zhang-tao-whu/DVIS_Plus","url":"https://github.com/zhang-tao-whu/DVIS_Plus"},{"title":"skyworkai/daq-vs","url":"https://github.com/skyworkai/daq-vs"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APho\", \"APmo\", \"AR1\", \"APso\", \"AR10\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":111387,"task":"Video Instance Segmentation","parent_task":null,"dataset":"OVIS validation","model_name":"CAVIS(VIT-L, Offline)","metrics":{"AP50":"82.6","AP75":"63.5","AR1":"21.2","AR10":"61.8","mask AP":"57.1"},"paper_url":"https://arxiv.org/abs/2407.03010v1","paper_title":"Context-Aware Video Instance Segmentation","paper_date":"2024-07-03","code_links":[{"title":"Seung-Hun-Lee/CAVIS","url":"https://github.com/Seung-Hun-Lee/CAVIS"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APho\", \"APmo\", \"AR1\", \"APso\", \"AR10\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":111388,"task":"Video Instance Segmentation","parent_task":null,"dataset":"OVIS validation","model_name":"DVIS++(VIT-L,Offline)","metrics":{"AP50":"78.9","AP75":"58.5","mask AP":"53.4"},"paper_url":"https://arxiv.org/abs/2312.13305v1","paper_title":"DVIS++: Improved Decoupled Framework for Universal Video Segmentation","paper_date":"2023-12-20","code_links":[{"title":"zhang-tao-whu/DVIS_Plus","url":"https://github.com/zhang-tao-whu/DVIS_Plus"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APho\", \"APmo\", \"AR1\", \"APso\", \"AR10\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":111389,"task":"Video Instance Segmentation","parent_task":null,"dataset":"OVIS validation","model_name":"GLEE-Pro","metrics":{"AP75":"55.5","mask AP":"50.4"},"paper_url":"https://arxiv.org/abs/2312.09158v1","paper_title":"General Object Foundation Model for Images and Videos at Scale","paper_date":"2023-12-14","code_links":[{"title":"FoundationVision/GLEE","url":"https://github.com/FoundationVision/GLEE"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APho\", \"APmo\", \"AR1\", \"APso\", \"AR10\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":111390,"task":"Video Instance Segmentation","parent_task":null,"dataset":"OVIS validation","model_name":"DVIS(Swin-L, Offline)","metrics":{"AP50":"75.9","AP75":"53.0","AR1":"19.4","AR10":"55.3","mask AP":"49.9"},"paper_url":"https://arxiv.org/abs/2306.03413v3","paper_title":"DVIS: Decoupled Video Instance Segmentation Framework","paper_date":"2023-06-06","code_links":[{"title":"zhang-tao-whu/DVIS","url":"https://github.com/zhang-tao-whu/DVIS"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APho\", \"APmo\", \"AR1\", \"APso\", \"AR10\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":111391,"task":"Video Instance Segmentation","parent_task":null,"dataset":"OVIS validation","model_name":"DVIS++(VIT-L, Online)","metrics":{"AP50":"72.5","AP75":"55.0","APho":"27.1","APmo":"56.6","APso":"69.9","AR1":"20.8","AR10":"54.6","mask AP":"49.6"},"paper_url":"https://arxiv.org/abs/2312.13305v1","paper_title":"DVIS++: Improved Decoupled Framework for Universal Video Segmentation","paper_date":"2023-12-20","code_links":[{"title":"zhang-tao-whu/DVIS_Plus","url":"https://github.com/zhang-tao-whu/DVIS_Plus"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APho\", \"APmo\", \"AR1\", \"APso\", \"AR10\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":111392,"task":"Video Instance Segmentation","parent_task":null,"dataset":"OVIS validation","model_name":"UNINEXT (ViT-H, Online)","metrics":{"AP50":"72.5","AP75":"52.2","mask AP":"49.0"},"paper_url":"https://arxiv.org/abs/2303.06674v2","paper_title":"Universal Instance Perception as Object Discovery and Retrieval","paper_date":"2023-03-12","code_links":[{"title":"MasterBin-IIAU/UNINEXT","url":"https://github.com/MasterBin-IIAU/UNINEXT"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APho\", \"APmo\", \"AR1\", \"APso\", \"AR10\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":111393,"task":"Video Instance Segmentation","parent_task":null,"dataset":"OVIS validation","model_name":"DVIS(Swin-L, Online)","metrics":{"AP50":"71.9","AP75":"49.2","AR1":"19.4","AR10":"52.5","mask AP":"47.1"},"paper_url":"https://arxiv.org/abs/2306.03413v3","paper_title":"DVIS: Decoupled Video Instance Segmentation Framework","paper_date":"2023-06-06","code_links":[{"title":"zhang-tao-whu/DVIS","url":"https://github.com/zhang-tao-whu/DVIS"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APho\", \"APmo\", \"AR1\", \"APso\", \"AR10\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":111394,"task":"Video Instance Segmentation","parent_task":null,"dataset":"OVIS validation","model_name":"CTVIS (Swin-L)","metrics":{"AP50":"71.5","AP75":"47.5","APho":"19.1","APmo":"52.1","mask AP":"46.9"},"paper_url":"https://arxiv.org/abs/2307.12616v1","paper_title":"CTVIS: Consistent Training for Online Video Instance Segmentation","paper_date":"2023-07-24","code_links":[{"title":"kainingying/ctvis","url":"https://github.com/kainingying/ctvis"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APho\", \"APmo\", \"AR1\", \"APso\", \"AR10\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":111395,"task":"Video Instance Segmentation","parent_task":null,"dataset":"OVIS validation","model_name":"RefineVIS (Swin-L, offline)","metrics":{"AP50":"70.4","AP75":"48.4","AR1":"19.1","AR10":"51.2","mask AP":"46"},"paper_url":"https://arxiv.org/abs/2306.04774v1","paper_title":"RefineVIS: Video Instance Segmentation with Temporal Attention Refinement","paper_date":"2023-06-07","code_links":[],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APho\", \"APmo\", \"AR1\", \"APso\", \"AR10\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":111396,"task":"Video Instance Segmentation","parent_task":null,"dataset":"OVIS validation","model_name":"GRAtt-VIS (Swin-L)","metrics":{"AP50":"69.1","AP75":"47.8","AR1":"19.2","AR10":"49.4","mask AP":"45.7"},"paper_url":"https://arxiv.org/abs/2305.17096v1","paper_title":"GRAtt-VIS: Gated Residual Attention for Auto Rectifying Video Instance Segmentation","paper_date":"2023-05-26","code_links":[{"title":"tanveer81/grattvis","url":"https://github.com/tanveer81/grattvis"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APho\", \"APmo\", \"AR1\", \"APso\", \"AR10\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":111397,"task":"Video Instance Segmentation","parent_task":null,"dataset":"OVIS validation","model_name":"GenVIS (Swin-L)","metrics":{"AP50":"69.2","AP75":"47.8","AR1":"18.9","AR10":"49.0","mask AP":"45.4"},"paper_url":"https://arxiv.org/abs/2211.08834v2","paper_title":"A Generalized Framework for Video Instance Segmentation","paper_date":"2022-11-16","code_links":[{"title":"miranheo/genvis","url":"https://github.com/miranheo/genvis"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APho\", \"APmo\", \"AR1\", \"APso\", \"AR10\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":111398,"task":"Video Instance Segmentation","parent_task":null,"dataset":"OVIS validation","model_name":"NOVIS (Swin-L)","metrics":{"AP50":"68.3","AP75":"43.8","AR1":"19.4","AR10":"46.9","mask AP":"43.5"},"paper_url":"https://arxiv.org/abs/2308.15266v2","paper_title":"NOVIS: A Case for End-to-End Near-Online Video Instance Segmentation","paper_date":"2023-08-29","code_links":[],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APho\", \"APmo\", \"AR1\", \"APso\", \"AR10\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":111399,"task":"Video Instance Segmentation","parent_task":null,"dataset":"OVIS validation","model_name":"TarViS (Swin-L)","metrics":{"AP50":"67.8","AP75":"44.6","AR1":"18.0","AR10":"50.4","mask AP":"43.2"},"paper_url":"https://arxiv.org/abs/2301.02657v2","paper_title":"TarViS: A Unified Approach for Target-based Video Segmentation","paper_date":"2023-01-06","code_links":[{"title":"Ali2500/TarViS","url":"https://github.com/Ali2500/TarViS"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APho\", \"APmo\", \"AR1\", \"APso\", \"AR10\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":111400,"task":"Video Instance Segmentation","parent_task":null,"dataset":"OVIS validation","model_name":"MDQE(SwinL)","metrics":{"AP50":"67.8","AP75":"44.3","APho":"21.6","APmo":"49.3","APso":"65.1","AR1":"18.3","AR10":"46.5","mask AP":"42.6"},"paper_url":"https://arxiv.org/abs/2303.14395v1","paper_title":"MDQE: Mining Discriminative Query Embeddings to Segment Occluded Instances on Challenging Videos","paper_date":"2023-03-25","code_links":[{"title":"minghanli/mdqe_cvpr2023","url":"https://github.com/minghanli/mdqe_cvpr2023"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APho\", \"APmo\", \"AR1\", \"APso\", \"AR10\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":111401,"task":"Video Instance Segmentation","parent_task":null,"dataset":"OVIS validation","model_name":"IDOL (Swin-L)","metrics":{"AP50":"65.7","AP75":"45.2","AR1":"17.9","AR10":"49.6","mask AP":"42.6"},"paper_url":"https://arxiv.org/abs/2207.10661v1","paper_title":"In Defense of Online Models for Video Instance Segmentation","paper_date":"2022-07-21","code_links":[{"title":"wjf5203/vnext","url":"https://github.com/wjf5203/vnext"},{"title":"mkimhi/RISE","url":"https://github.com/mkimhi/RISE"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APho\", \"APmo\", \"AR1\", \"APso\", \"AR10\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":111402,"task":"Video Instance Segmentation","parent_task":null,"dataset":"OVIS validation","model_name":"ROVIS (Swin-L)","metrics":{"AP50":"64.7","AP75":"42.6","AR1":"18.4","AR10":"49.1","mask AP":"42.6"},"paper_url":"https://arxiv.org/abs/2211.09108v1","paper_title":"Robust Online Video Instance Segmentation with Track Queries","paper_date":"2022-11-16","code_links":[{"title":"zitongzhan/mmtracking","url":"https://github.com/zitongzhan/mmtracking/tree/zitongzhan/rovis/configs/vis/rovis"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APho\", \"APmo\", \"AR1\", \"APso\", \"AR10\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":111403,"task":"Video Instance Segmentation","parent_task":null,"dataset":"OVIS validation","model_name":"UniVS(Swin-L)","metrics":{"mask AP":"41.7"},"paper_url":"https://arxiv.org/abs/2402.18115v2","paper_title":"UniVS: Unified and Universal Video Segmentation with Prompts as Queries","paper_date":"2024-02-28","code_links":[{"title":"minghanli/univs","url":"https://github.com/minghanli/univs"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APho\", \"APmo\", \"AR1\", \"APso\", \"AR10\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":111404,"task":"Video Instance Segmentation","parent_task":null,"dataset":"OVIS validation","model_name":"DVIS++(R50, Offline)","metrics":{"AP50":"68.9","AP75":"40.9","AR1":"16.8","AR10":"47.3","mask AP":"41.2"},"paper_url":"https://arxiv.org/abs/2312.13305v1","paper_title":"DVIS++: Improved Decoupled Framework for Universal Video Segmentation","paper_date":"2023-12-20","code_links":[{"title":"zhang-tao-whu/DVIS_Plus","url":"https://github.com/zhang-tao-whu/DVIS_Plus"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APho\", \"APmo\", \"AR1\", \"APso\", \"AR10\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":111405,"task":"Video Instance Segmentation","parent_task":null,"dataset":"OVIS validation","model_name":"BoxVIS(Swin-L & Box-sup)","metrics":{"AP50":"68.4","AP75":"39.9","APho":"20.9","APmo":"45.8","APso":"59.4","mask AP":"40.6"},"paper_url":"https://arxiv.org/abs/2303.14618v2","paper_title":"BoxVIS: Video Instance Segmentation with Box Annotations","paper_date":"2023-03-26","code_links":[{"title":"minghanli/boxvis","url":"https://github.com/minghanli/boxvis"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APho\", \"APmo\", \"AR1\", \"APso\", \"AR10\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":111406,"task":"Video Instance Segmentation","parent_task":null,"dataset":"OVIS validation","model_name":"MinVIS (Swin-L)","metrics":{"AP50":"61.5","AP75":"41.3","AR1":"18.1","AR10":"43.3","mask AP":"39.4"},"paper_url":"https://arxiv.org/abs/2208.02245v1","paper_title":"MinVIS: A Minimal Video Instance Segmentation Framework without Video-based Training","paper_date":"2022-08-03","code_links":[{"title":"nvlabs/minvis","url":"https://github.com/nvlabs/minvis"},{"title":"kimhanjung/visage","url":"https://github.com/kimhanjung/visage"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APho\", \"APmo\", \"AR1\", \"APso\", \"AR10\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":111407,"task":"Video Instance Segmentation","parent_task":null,"dataset":"OVIS validation","model_name":"DVIS++(R50, Online)","metrics":{"AP50":"62.8","AP75":"37.3","AR1":"15.8","AR10":"42.9","mask AP":"37.2"},"paper_url":"https://arxiv.org/abs/2312.13305v1","paper_title":"DVIS++: Improved Decoupled Framework for Universal Video Segmentation","paper_date":"2023-12-20","code_links":[{"title":"zhang-tao-whu/DVIS_Plus","url":"https://github.com/zhang-tao-whu/DVIS_Plus"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APho\", \"APmo\", \"AR1\", \"APso\", \"AR10\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":111408,"task":"Video Instance Segmentation","parent_task":null,"dataset":"OVIS validation","model_name":"GRAtt-VIS (ResNet-50)","metrics":{"AP50":"60.8","AP75":"36.8","AR1":"16.8","AR10":"40.1","mask AP":"36.2"},"paper_url":"https://arxiv.org/abs/2305.17096v1","paper_title":"GRAtt-VIS: Gated Residual Attention for Auto Rectifying Video Instance Segmentation","paper_date":"2023-05-26","code_links":[{"title":"tanveer81/grattvis","url":"https://github.com/tanveer81/grattvis"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APho\", \"APmo\", \"AR1\", \"APso\", \"AR10\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":111409,"task":"Video Instance Segmentation","parent_task":null,"dataset":"OVIS validation","model_name":"CTVIS (ResNet-50)","metrics":{"AP50":"60.8","AP75":"34.9","APho":"16.1","APmo":"41.9","mask AP":"35.5"},"paper_url":"https://arxiv.org/abs/2307.12616v1","paper_title":"CTVIS: Consistent Training for Online Video Instance Segmentation","paper_date":"2023-07-24","code_links":[{"title":"kainingying/ctvis","url":"https://github.com/kainingying/ctvis"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APho\", \"APmo\", \"AR1\", \"APso\", \"AR10\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":111410,"task":"Video Instance Segmentation","parent_task":null,"dataset":"OVIS validation","model_name":"DeVIS (Swin-L)","metrics":{"AP50":"59.3","AP75":"38.3","AR1":"16.6","AR10":"39.8","mask AP":"35.5"},"paper_url":"https://arxiv.org/abs/2207.11103v1","paper_title":"DeVIS: Making Deformable Transformers Work for Video Instance Segmentation","paper_date":"2022-07-22","code_links":[{"title":"acaelles97/devis","url":"https://github.com/acaelles97/devis"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APho\", \"APmo\", \"AR1\", \"APso\", \"AR10\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":111411,"task":"Video Instance Segmentation","parent_task":null,"dataset":"OVIS validation","model_name":"UNINEXT (ResNet-50, Online)","metrics":{"AP50":"55.5","AP75":"35.6","mask AP":"34.0"},"paper_url":"https://arxiv.org/abs/2303.06674v2","paper_title":"Universal Instance Perception as Object Discovery and Retrieval","paper_date":"2023-03-12","code_links":[{"title":"MasterBin-IIAU/UNINEXT","url":"https://github.com/MasterBin-IIAU/UNINEXT"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APho\", \"APmo\", \"AR1\", \"APso\", \"AR10\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":111412,"task":"Video Instance Segmentation","parent_task":null,"dataset":"OVIS validation","model_name":"TarViS  (Swin-T)","metrics":{"AP50":"55.0","AP75":"34.4","AR1":"16.1","AR10":"40.9","mask AP":"34.0"},"paper_url":"https://arxiv.org/abs/2301.02657v2","paper_title":"TarViS: A Unified Approach for Target-based Video Segmentation","paper_date":"2023-01-06","code_links":[{"title":"Ali2500/TarViS","url":"https://github.com/Ali2500/TarViS"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APho\", \"APmo\", \"AR1\", \"APso\", \"AR10\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":111413,"task":"Video Instance Segmentation","parent_task":null,"dataset":"OVIS validation","model_name":"NOVIS (ResNet-50)","metrics":{"AP50":"56.2","AP75":"32.6","AR1":"15.7","AR10":"37.1","mask AP":"32.7"},"paper_url":"https://arxiv.org/abs/2308.15266v2","paper_title":"NOVIS: A Case for End-to-End Near-Online Video Instance Segmentation","paper_date":"2023-08-29","code_links":[],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APho\", \"APmo\", \"AR1\", \"APso\", \"AR10\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":111414,"task":"Video Instance Segmentation","parent_task":null,"dataset":"OVIS validation","model_name":"TarViS (ResNet-50)","metrics":{"AP50":"52.5","AP75":"30.4","AR1":"15.9","AR10":"39.9","mask AP":"31.1"},"paper_url":"https://arxiv.org/abs/2301.02657v2","paper_title":"TarViS: A Unified Approach for Target-based Video Segmentation","paper_date":"2023-01-06","code_links":[{"title":"Ali2500/TarViS","url":"https://github.com/Ali2500/TarViS"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APho\", \"APmo\", \"AR1\", \"APso\", \"AR10\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":111415,"task":"Video Instance Segmentation","parent_task":null,"dataset":"OVIS validation","model_name":"IDOL (ResNet-50)","metrics":{"AP50":"51.3","AP75":"30","AR1":"15","AR10":"37.5","mask AP":"30.2"},"paper_url":"https://arxiv.org/abs/2207.10661v1","paper_title":"In Defense of Online Models for Video Instance Segmentation","paper_date":"2022-07-21","code_links":[{"title":"wjf5203/vnext","url":"https://github.com/wjf5203/vnext"},{"title":"mkimhi/RISE","url":"https://github.com/mkimhi/RISE"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APho\", \"APmo\", \"AR1\", \"APso\", \"AR10\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":111416,"task":"Video Instance Segmentation","parent_task":null,"dataset":"OVIS validation","model_name":"Tube-Link(ResNet-50)","metrics":{"AP50":"51.5","AP75":"30.2","AR1":"15.5","AR10":"34.5","mask AP":"29.5"},"paper_url":"https://arxiv.org/abs/2303.12782v3","paper_title":"Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentation","paper_date":"2023-03-22","code_links":[{"title":"lxtgh/tube-link","url":"https://github.com/lxtgh/tube-link"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APho\", \"APmo\", \"AR1\", \"APso\", \"AR10\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":111417,"task":"Video Instance Segmentation","parent_task":null,"dataset":"OVIS validation","model_name":"VITA (Swin-L)","metrics":{"AP50":"51.9","AP75":"24.9","AR1":"14.9","AR10":"33.0","mask AP":"27.7"},"paper_url":"https://arxiv.org/abs/2206.04403v2","paper_title":"VITA: Video Instance Segmentation via Object Token Association","paper_date":"2022-06-09","code_links":[{"title":"sukjunhwang/vita","url":"https://github.com/sukjunhwang/vita"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APho\", \"APmo\", \"AR1\", \"APso\", \"AR10\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":111418,"task":"Video Instance Segmentation","parent_task":null,"dataset":"OVIS validation","model_name":"DeVIS (ResNet-50)","metrics":{"AP50":"47.6","AP75":"20.8","AR1":"12.0","AR10":"28.9","mask AP":"23.7"},"paper_url":"https://arxiv.org/abs/2207.11103v1","paper_title":"DeVIS: Making Deformable Transformers Work for Video Instance Segmentation","paper_date":"2022-07-22","code_links":[{"title":"acaelles97/devis","url":"https://github.com/acaelles97/devis"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APho\", \"APmo\", \"AR1\", \"APso\", \"AR10\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":111419,"task":"Video Instance Segmentation","parent_task":null,"dataset":"OVIS validation","model_name":"InstanceFormer (Swin-L)","metrics":{"AP50":"42.5","AP75":"21.61","AR1":"12.9","AR10":"29.3","mask AP":"22.8"},"paper_url":"https://arxiv.org/abs/2208.10547v1","paper_title":"InstanceFormer: An Online Video Instance Segmentation Framework","paper_date":"2022-08-22","code_links":[{"title":"rajatkoner08/instanceformer","url":"https://github.com/rajatkoner08/instanceformer"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APho\", \"APmo\", \"AR1\", \"APso\", \"AR10\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":111420,"task":"Video Instance Segmentation","parent_task":null,"dataset":"OVIS validation","model_name":"InstanceFormer(ResNet-50)","metrics":{"AP50":"40.7","AP75":"18.1","AR1":"12","AR10":"27.1","mask AP":"20.0"},"paper_url":"https://arxiv.org/abs/2208.10547v1","paper_title":"InstanceFormer: An Online Video Instance Segmentation Framework","paper_date":"2022-08-22","code_links":[{"title":"rajatkoner08/instanceformer","url":"https://github.com/rajatkoner08/instanceformer"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APho\", \"APmo\", \"AR1\", \"APso\", \"AR10\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":111421,"task":"Video Instance Segmentation","parent_task":null,"dataset":"OVIS validation","model_name":"CrossVIS (ResNet-50, calibration)","metrics":{"AP50":"35.5","AP75":"16.9","mask AP":"18.1"},"paper_url":"https://arxiv.org/abs/2104.05970v1","paper_title":"Crossover Learning for Fast Online Video Instance Segmentation","paper_date":"2021-04-13","code_links":[{"title":"hustvl/CrossVIS","url":"https://github.com/hustvl/CrossVIS"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APho\", \"APmo\", \"AR1\", \"APso\", \"AR10\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":111422,"task":"Video Instance Segmentation","parent_task":null,"dataset":"OVIS validation","model_name":"TeViT (ResNet-50)","metrics":{"AP50":"34.9","AP75":"15.0","mask AP":"17.4"},"paper_url":"https://arxiv.org/abs/2204.08412v1","paper_title":"Temporally Efficient Vision Transformer for Video Instance Segmentation","paper_date":"2022-04-18","code_links":[{"title":"hustvl/QueryInst","url":"https://github.com/hustvl/QueryInst"},{"title":"hustvl/tevit","url":"https://github.com/hustvl/tevit"},{"title":"2023-MindSpore-1/ms-code-144","url":"https://github.com/2023-MindSpore-1/ms-code-144"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APho\", \"APmo\", \"AR1\", \"APso\", \"AR10\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":111423,"task":"Video Instance Segmentation","parent_task":null,"dataset":"OVIS validation","model_name":"STMask(R101-DCN-FPN)","metrics":{"AP50":"35.4","AP75":"15.2","APho":"23.7","APmo":"14.7","APso":"11.1","AR1":"8.4","AR10":"23.1","mask AP":"17.3"},"paper_url":"https://arxiv.org/abs/2104.05606v1","paper_title":"Spatial Feature Calibration and Temporal Fusion for Effective One-stage Video Instance Segmentation","paper_date":"2021-04-06","code_links":[{"title":"MinghanLi/STMask","url":"https://github.com/MinghanLi/STMask"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APho\", \"APmo\", \"AR1\", \"APso\", \"AR10\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":111424,"task":"Video Instance Segmentation","parent_task":null,"dataset":"OVIS validation","model_name":"Mask2Former-VIS","metrics":{"AP50":"36.9","AP75":"14.1","AR1":"9.9","AR10":"24.7","mask AP":"16.6"},"paper_url":"https://arxiv.org/abs/2112.10764v1","paper_title":"Mask2Former for Video Instance Segmentation","paper_date":"2021-12-20","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection"},{"title":"facebookresearch/Mask2Former","url":"https://github.com/facebookresearch/Mask2Former"},{"title":"alibaba/EasyCV","url":"https://github.com/alibaba/EasyCV"},{"title":"nihalsid/mask2former","url":"https://github.com/nihalsid/mask2former"},{"title":"pwc-1/Paper-5","url":"https://github.com/pwc-1/Paper-5/tree/main/mask2former"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APho\", \"APmo\", \"AR1\", \"APso\", \"AR10\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":111425,"task":"Video Instance Segmentation","parent_task":null,"dataset":"OVIS validation","model_name":"STC (ResNet-50)","metrics":{"AP50":"33.5","AP75":"13.4","mask AP":"15.5"},"paper_url":"https://arxiv.org/abs/2202.03747v2","paper_title":"STC: Spatio-Temporal Contrastive Learning for Video Instance Segmentation","paper_date":"2022-02-08","code_links":[],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APho\", \"APmo\", \"AR1\", \"APso\", \"AR10\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":111426,"task":"Video Instance Segmentation","parent_task":null,"dataset":"OVIS validation","model_name":"CMaskTrack R-CNN (ResNet-50)","metrics":{"AP50":"33.9","AP75":"13.1","APho":"4.1","APmo":"18.7","APso":"28.6","mask AP":"15.4"},"paper_url":"https://arxiv.org/abs/2102.01558v6","paper_title":"Occluded Video Instance Segmentation: A Benchmark","paper_date":"2021-02-02","code_links":[{"title":"haochenheheda/lvvis","url":"https://github.com/haochenheheda/lvvis"},{"title":"qjy981010/CMaskTrack-RCNN","url":"https://github.com/qjy981010/CMaskTrack-RCNN"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APho\", \"APmo\", \"AR1\", \"APso\", \"AR10\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":111427,"task":"Video Instance Segmentation","parent_task":null,"dataset":"OVIS validation","model_name":"D2Conv3D (ResNet-50)","metrics":{"AP50":"33.8","AP75":"13.7","mask AP":"15.2"},"paper_url":"https://openaccess.thecvf.com/content/WACV2022/html/Schmidt_D2Conv3D_Dynamic_Dilated_Convolutions_for_Object_Segmentation_in_Videos_WACV_2022_paper.html","paper_title":"D2Conv3D: Dynamic Dilated Convolutions for Object Segmentation in Videos","paper_date":"2021-11-15","code_links":[{"title":"schmiddo/d2conv3d","url":"https://github.com/schmiddo/d2conv3d"},{"title":"2023-MindSpore-4/Code5","url":"https://github.com/2023-MindSpore-4/Code5/tree/main/D2Co"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APho\", \"APmo\", \"AR1\", \"APso\", \"AR10\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":111428,"task":"Video Instance Segmentation","parent_task":null,"dataset":"OVIS validation","model_name":"CrossVIS (ResNet-50)","metrics":{"AP50":"32.7","AP75":"12.1","mask AP":"14.9"},"paper_url":"https://arxiv.org/abs/2104.05970v1","paper_title":"Crossover Learning for Fast Online Video Instance Segmentation","paper_date":"2021-04-13","code_links":[{"title":"hustvl/CrossVIS","url":"https://github.com/hustvl/CrossVIS"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APho\", \"APmo\", \"AR1\", \"APso\", \"AR10\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":111429,"task":"Video Instance Segmentation","parent_task":null,"dataset":"OVIS validation","model_name":"CSipMask (ResNet-50)","metrics":{"AP50":"29.9","AP75":"12.5","APho":"2.7","APmo":"12.8","APso":"23","mask AP":"14.3"},"paper_url":"https://arxiv.org/abs/2102.01558v6","paper_title":"Occluded Video Instance Segmentation: A Benchmark","paper_date":"2021-02-02","code_links":[{"title":"haochenheheda/lvvis","url":"https://github.com/haochenheheda/lvvis"},{"title":"qjy981010/CMaskTrack-RCNN","url":"https://github.com/qjy981010/CMaskTrack-RCNN"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APho\", \"APmo\", \"AR1\", \"APso\", \"AR10\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]}]}