{"task":"Video Object Segmentation","dataset":"M$^3$-VOS","metric_names":["Average IOU"],"rows":[{"id":16309,"task":"Video Object Segmentation","parent_task":"Video","dataset":"M$^3$-VOS","model_name":"ReVOS","metrics":{"Average IOU":"75.6"},"paper_url":"https://cvpr.thecvf.com/virtual/2025/poster/35147","paper_title":"M^3-VOS: Multi-Phase, Multi-Transition, and Multi-Scenery Video Object Segmentation","paper_date":"2025-06-15","code_links":[{"title":"zixuan-chen/M3VOS_Experiment","url":"https://github.com/zixuan-chen/M3VOS_Experiment"}],"metrics_order":"[\"Average IOU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":16310,"task":"Video Object Segmentation","parent_task":"Video","dataset":"M$^3$-VOS","model_name":"Cutie-base","metrics":{"Average IOU":"74.6"},"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":"[\"Average IOU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":16311,"task":"Video Object Segmentation","parent_task":"Video","dataset":"M$^3$-VOS","model_name":"XMem","metrics":{"Average IOU":"70.4"},"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":"[\"Average IOU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":16312,"task":"Video Object Segmentation","parent_task":"Video","dataset":"M$^3$-VOS","model_name":"SAM 2","metrics":{"Average IOU":"69.5"},"paper_url":"https://arxiv.org/abs/2408.00714v2","paper_title":"SAM 2: Segment Anything in Images and Videos","paper_date":"2024-08-01","code_links":[{"title":"facebookresearch/segment-anything","url":"https://github.com/facebookresearch/segment-anything"},{"title":"facebookresearch/sam2","url":"https://github.com/facebookresearch/sam2"},{"title":"yangchris11/samurai","url":"https://github.com/yangchris11/samurai"},{"title":"idea-research/grounded-sam-2","url":"https://github.com/idea-research/grounded-sam-2"},{"title":"ibaiGorordo/ONNX-SAM2-Segment-Anything","url":"https://github.com/ibaiGorordo/ONNX-SAM2-Segment-Anything"},{"title":"bowang-lab/medsam2","url":"https://github.com/bowang-lab/medsam2"},{"title":"TripleJoy/SAM2MOT","url":"https://github.com/TripleJoy/SAM2MOT"},{"title":"louisfinner/him2sam","url":"https://github.com/louisfinner/him2sam"},{"title":"MindCode-4/code-4","url":"https://github.com/MindCode-4/code-4/tree/main/sam"},{"title":"dcnieho/segment-anything-2","url":"https://github.com/dcnieho/segment-anything-2"},{"title":"MindSpore-scientific/code-7","url":"https://github.com/MindSpore-scientific/code-7/tree/main/SAM"}],"metrics_order":"[\"Average IOU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":87450,"task":"Video Object Segmentation","parent_task":null,"dataset":"M$^3$-VOS","model_name":"ReVOS","metrics":{"Average IOU":"75.6"},"paper_url":"https://cvpr.thecvf.com/virtual/2025/poster/35147","paper_title":"M^3-VOS: Multi-Phase, Multi-Transition, and Multi-Scenery Video Object Segmentation","paper_date":"2025-06-15","code_links":[{"title":"zixuan-chen/M3VOS_Experiment","url":"https://github.com/zixuan-chen/M3VOS_Experiment"}],"metrics_order":"[\"Average IOU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":87451,"task":"Video Object Segmentation","parent_task":null,"dataset":"M$^3$-VOS","model_name":"Cutie-base","metrics":{"Average IOU":"74.6"},"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":"[\"Average IOU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":87452,"task":"Video Object Segmentation","parent_task":null,"dataset":"M$^3$-VOS","model_name":"XMem","metrics":{"Average IOU":"70.4"},"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":"[\"Average IOU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":87453,"task":"Video Object Segmentation","parent_task":null,"dataset":"M$^3$-VOS","model_name":"SAM 2","metrics":{"Average IOU":"69.5"},"paper_url":"https://arxiv.org/abs/2408.00714v2","paper_title":"SAM 2: Segment Anything in Images and Videos","paper_date":"2024-08-01","code_links":[{"title":"facebookresearch/segment-anything","url":"https://github.com/facebookresearch/segment-anything"},{"title":"facebookresearch/sam2","url":"https://github.com/facebookresearch/sam2"},{"title":"yangchris11/samurai","url":"https://github.com/yangchris11/samurai"},{"title":"idea-research/grounded-sam-2","url":"https://github.com/idea-research/grounded-sam-2"},{"title":"ibaiGorordo/ONNX-SAM2-Segment-Anything","url":"https://github.com/ibaiGorordo/ONNX-SAM2-Segment-Anything"},{"title":"bowang-lab/medsam2","url":"https://github.com/bowang-lab/medsam2"},{"title":"TripleJoy/SAM2MOT","url":"https://github.com/TripleJoy/SAM2MOT"},{"title":"louisfinner/him2sam","url":"https://github.com/louisfinner/him2sam"},{"title":"MindCode-4/code-4","url":"https://github.com/MindCode-4/code-4/tree/main/sam"},{"title":"dcnieho/segment-anything-2","url":"https://github.com/dcnieho/segment-anything-2"},{"title":"MindSpore-scientific/code-7","url":"https://github.com/MindSpore-scientific/code-7/tree/main/SAM"}],"metrics_order":"[\"Average IOU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]}]}