{"task":"Human Instance Segmentation","dataset":"OCHuman","metric_names":["AP"],"rows":[{"id":86448,"task":"Human Instance Segmentation","parent_task":"Instance Segmentation","dataset":"OCHuman","model_name":"BBox-Mask-Pose 2x","metrics":{"AP":"32.4"},"paper_url":"https://arxiv.org/abs/2412.01562v1","paper_title":"Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle","paper_date":"2024-12-02","code_links":[{"title":"MiraPurkrabek/BBoxMaskPose","url":"https://github.com/MiraPurkrabek/BBoxMaskPose"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":86449,"task":"Human Instance Segmentation","parent_task":"Instance Segmentation","dataset":"OCHuman","model_name":"Crowd-SAM (ViT-L)","metrics":{"AP":"31.4"},"paper_url":"https://arxiv.org/abs/2407.11464v2","paper_title":"Crowd-SAM: SAM as a Smart Annotator for Object Detection in Crowded Scenes","paper_date":"2024-07-16","code_links":[{"title":"felixcaae/crowdsam","url":"https://github.com/felixcaae/crowdsam"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":86450,"task":"Human Instance Segmentation","parent_task":"Instance Segmentation","dataset":"OCHuman","model_name":"HQNet (ResNet-50)","metrics":{"AP":"31.1"},"paper_url":"https://arxiv.org/abs/2312.05525v3","paper_title":"You Only Learn One Query: Learning Unified Human Query for Single-Stage Multi-Person Multi-Task Human-Centric Perception","paper_date":"2023-12-09","code_links":[{"title":"lishuhuai527/coco-unihuman","url":"https://github.com/lishuhuai527/coco-unihuman"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":86451,"task":"Human Instance Segmentation","parent_task":"Instance Segmentation","dataset":"OCHuman","model_name":"BlendMask + CIS","metrics":{"AP":"29.8"},"paper_url":"https://arxiv.org/abs/2108.07199v1","paper_title":"Real-time Human-Centric Segmentation for Complex Video Scenes","paper_date":"2021-08-16","code_links":[{"title":"iigroup/hvisnet","url":"https://github.com/iigroup/hvisnet"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":86452,"task":"Human Instance Segmentation","parent_task":"Instance Segmentation","dataset":"OCHuman","model_name":"Mask2Former + Occlusion C&P","metrics":{"AP":"28.3"},"paper_url":"https://arxiv.org/abs/2210.03686v1","paper_title":"Humans need not label more humans: Occlusion Copy & Paste for Occluded Human Instance Segmentation","paper_date":"2022-10-07","code_links":[{"title":"levan92/occlusion-copy-paste","url":"https://github.com/levan92/occlusion-copy-paste"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":86453,"task":"Human Instance Segmentation","parent_task":"Instance Segmentation","dataset":"OCHuman","model_name":"CondInst + CIS","metrics":{"AP":"28.1"},"paper_url":"https://arxiv.org/abs/2108.07199v1","paper_title":"Real-time Human-Centric Segmentation for Complex Video Scenes","paper_date":"2021-08-16","code_links":[{"title":"iigroup/hvisnet","url":"https://github.com/iigroup/hvisnet"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":86454,"task":"Human Instance Segmentation","parent_task":"Instance Segmentation","dataset":"OCHuman","model_name":"Mask2Former","metrics":{"AP":"27.8"},"paper_url":"https://arxiv.org/abs/2303.06800v1","paper_title":"Object-Centric Multi-Task Learning for Human Instances","paper_date":"2023-03-13","code_links":[],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":86455,"task":"Human Instance Segmentation","parent_task":"Instance Segmentation","dataset":"OCHuman","model_name":"HCQNet","metrics":{"AP":"27.3"},"paper_url":"https://arxiv.org/abs/2303.06800v1","paper_title":"Object-Centric Multi-Task Learning for Human Instances","paper_date":"2023-03-13","code_links":[],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":86456,"task":"Human Instance Segmentation","parent_task":"Instance Segmentation","dataset":"OCHuman","model_name":"ExPoSeg","metrics":{"AP":"26.8"},"paper_url":"https://ieeexplore.ieee.org/document/8962018","paper_title":"PoSeg: Pose-Aware Refinement Network for Human Instance Segmentation","paper_date":"2020-01-07","code_links":[],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":86457,"task":"Human Instance Segmentation","parent_task":"Instance Segmentation","dataset":"OCHuman","model_name":"RTMDet-ins-l","metrics":{"AP":"26.5"},"paper_url":"https://arxiv.org/abs/2412.01562v1","paper_title":"Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle","paper_date":"2024-12-02","code_links":[{"title":"MiraPurkrabek/BBoxMaskPose","url":"https://github.com/MiraPurkrabek/BBoxMaskPose"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":86458,"task":"Human Instance Segmentation","parent_task":"Instance Segmentation","dataset":"OCHuman","model_name":"JoPoSeg","metrics":{"AP":"26.4"},"paper_url":"https://ieeexplore.ieee.org/document/8962018","paper_title":"PoSeg: Pose-Aware Refinement Network for Human Instance Segmentation","paper_date":"2020-01-07","code_links":[],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":86459,"task":"Human Instance Segmentation","parent_task":"Instance Segmentation","dataset":"OCHuman","model_name":"BaseNet-DPS","metrics":{"AP":"25.5"},"paper_url":"https://arxiv.org/abs/2303.06800v1","paper_title":"Object-Centric Multi-Task Learning for Human Instances","paper_date":"2023-03-13","code_links":[],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":86460,"task":"Human Instance Segmentation","parent_task":"Instance Segmentation","dataset":"OCHuman","model_name":"Pose2Seg","metrics":{"AP":"23.8"},"paper_url":"http://arxiv.org/abs/1803.10683v3","paper_title":"Pose2Seg: Detection Free Human Instance Segmentation","paper_date":"2018-03-28","code_links":[{"title":"open-mmlab/mmpose","url":"https://github.com/open-mmlab/mmpose"},{"title":"liruilong940607/Pose2Seg","url":"https://github.com/liruilong940607/Pose2Seg"},{"title":"liruilong940607/OCHumanApi","url":"https://github.com/liruilong940607/OCHumanApi"},{"title":"Jittor/InstanceSegmentation-jittor","url":"https://github.com/Jittor/InstanceSegmentation-jittor"},{"title":"ligaoqi2/Pose2Seg-single-person-video-demo","url":"https://github.com/ligaoqi2/Pose2Seg-single-person-video-demo"},{"title":"jacksonlli/ProjectQuarantine_HumanSegmentation","url":"https://github.com/jacksonlli/ProjectQuarantine_HumanSegmentation"},{"title":"hz-ants/Pose2Seg","url":"https://github.com/hz-ants/Pose2Seg"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":86461,"task":"Human Instance Segmentation","parent_task":"Instance Segmentation","dataset":"OCHuman","model_name":"PolarMask + CIS","metrics":{"AP":"23.4"},"paper_url":"https://arxiv.org/abs/2108.07199v1","paper_title":"Real-time Human-Centric Segmentation for Complex Video Scenes","paper_date":"2021-08-16","code_links":[{"title":"iigroup/hvisnet","url":"https://github.com/iigroup/hvisnet"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":86462,"task":"Human Instance Segmentation","parent_task":"Instance Segmentation","dataset":"OCHuman","model_name":"ResNet-101-FPN + TTG v1","metrics":{"AP":"22.42"},"paper_url":"https://arxiv.org/abs/2212.06242v1","paper_title":"Test-time Adaptation vs. Training-time Generalization: A Case Study in Human Instance Segmentation using Keypoints Estimation","paper_date":"2022-12-12","code_links":[],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":86463,"task":"Human Instance Segmentation","parent_task":"Instance Segmentation","dataset":"OCHuman","model_name":"BCNet","metrics":{"AP":"20.6"},"paper_url":"https://arxiv.org/abs/2208.04438v2","paper_title":"Occlusion-Aware Instance Segmentation via BiLayer Network Architectures","paper_date":"2022-08-08","code_links":[{"title":"lkeab/BCNet","url":"https://github.com/lkeab/BCNet"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":86464,"task":"Human Instance Segmentation","parent_task":"Instance Segmentation","dataset":"OCHuman","model_name":"CaSe","metrics":{"AP":"18.0"},"paper_url":"https://www.ecva.net/papers/eccv_2020/papers_ECCV/html/2678_ECCV_2020_paper.php","paper_title":"Count- and Similarity-aware R-CNN for Pedestrian Detection","paper_date":null,"code_links":[],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":86465,"task":"Human Instance Segmentation","parent_task":"Instance Segmentation","dataset":"OCHuman","model_name":"Mask RCNN","metrics":{"AP":"16.9"},"paper_url":"https://www.ecva.net/papers/eccv_2020/papers_ECCV/html/2678_ECCV_2020_paper.php","paper_title":"Count- and Similarity-aware R-CNN for Pedestrian Detection","paper_date":null,"code_links":[],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":154754,"task":"Human Instance Segmentation","parent_task":null,"dataset":"OCHuman","model_name":"BBox-Mask-Pose 2x","metrics":{"AP":"32.4"},"paper_url":"https://arxiv.org/abs/2412.01562v1","paper_title":"Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle","paper_date":"2024-12-02","code_links":[{"title":"MiraPurkrabek/BBoxMaskPose","url":"https://github.com/MiraPurkrabek/BBoxMaskPose"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":154755,"task":"Human Instance Segmentation","parent_task":null,"dataset":"OCHuman","model_name":"Crowd-SAM (ViT-L)","metrics":{"AP":"31.4"},"paper_url":"https://arxiv.org/abs/2407.11464v2","paper_title":"Crowd-SAM: SAM as a Smart Annotator for Object Detection in Crowded Scenes","paper_date":"2024-07-16","code_links":[{"title":"felixcaae/crowdsam","url":"https://github.com/felixcaae/crowdsam"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":154756,"task":"Human Instance Segmentation","parent_task":null,"dataset":"OCHuman","model_name":"HQNet (ResNet-50)","metrics":{"AP":"31.1"},"paper_url":"https://arxiv.org/abs/2312.05525v3","paper_title":"You Only Learn One Query: Learning Unified Human Query for Single-Stage Multi-Person Multi-Task Human-Centric Perception","paper_date":"2023-12-09","code_links":[{"title":"lishuhuai527/coco-unihuman","url":"https://github.com/lishuhuai527/coco-unihuman"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":154757,"task":"Human Instance Segmentation","parent_task":null,"dataset":"OCHuman","model_name":"BlendMask + CIS","metrics":{"AP":"29.8"},"paper_url":"https://arxiv.org/abs/2108.07199v1","paper_title":"Real-time Human-Centric Segmentation for Complex Video Scenes","paper_date":"2021-08-16","code_links":[{"title":"iigroup/hvisnet","url":"https://github.com/iigroup/hvisnet"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":154758,"task":"Human Instance Segmentation","parent_task":null,"dataset":"OCHuman","model_name":"Mask2Former + Occlusion C&P","metrics":{"AP":"28.3"},"paper_url":"https://arxiv.org/abs/2210.03686v1","paper_title":"Humans need not label more humans: Occlusion Copy & Paste for Occluded Human Instance Segmentation","paper_date":"2022-10-07","code_links":[{"title":"levan92/occlusion-copy-paste","url":"https://github.com/levan92/occlusion-copy-paste"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":154759,"task":"Human Instance Segmentation","parent_task":null,"dataset":"OCHuman","model_name":"CondInst + CIS","metrics":{"AP":"28.1"},"paper_url":"https://arxiv.org/abs/2108.07199v1","paper_title":"Real-time Human-Centric Segmentation for Complex Video Scenes","paper_date":"2021-08-16","code_links":[{"title":"iigroup/hvisnet","url":"https://github.com/iigroup/hvisnet"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":154760,"task":"Human Instance Segmentation","parent_task":null,"dataset":"OCHuman","model_name":"Mask2Former","metrics":{"AP":"27.8"},"paper_url":"https://arxiv.org/abs/2303.06800v1","paper_title":"Object-Centric Multi-Task Learning for Human Instances","paper_date":"2023-03-13","code_links":[],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":154761,"task":"Human Instance Segmentation","parent_task":null,"dataset":"OCHuman","model_name":"HCQNet","metrics":{"AP":"27.3"},"paper_url":"https://arxiv.org/abs/2303.06800v1","paper_title":"Object-Centric Multi-Task Learning for Human Instances","paper_date":"2023-03-13","code_links":[],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":154762,"task":"Human Instance Segmentation","parent_task":null,"dataset":"OCHuman","model_name":"ExPoSeg","metrics":{"AP":"26.8"},"paper_url":"https://ieeexplore.ieee.org/document/8962018","paper_title":"PoSeg: Pose-Aware Refinement Network for Human Instance Segmentation","paper_date":"2020-01-07","code_links":[],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":154763,"task":"Human Instance Segmentation","parent_task":null,"dataset":"OCHuman","model_name":"RTMDet-ins-l","metrics":{"AP":"26.5"},"paper_url":"https://arxiv.org/abs/2412.01562v1","paper_title":"Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle","paper_date":"2024-12-02","code_links":[{"title":"MiraPurkrabek/BBoxMaskPose","url":"https://github.com/MiraPurkrabek/BBoxMaskPose"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":154764,"task":"Human Instance Segmentation","parent_task":null,"dataset":"OCHuman","model_name":"JoPoSeg","metrics":{"AP":"26.4"},"paper_url":"https://ieeexplore.ieee.org/document/8962018","paper_title":"PoSeg: Pose-Aware Refinement Network for Human Instance Segmentation","paper_date":"2020-01-07","code_links":[],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":154765,"task":"Human Instance Segmentation","parent_task":null,"dataset":"OCHuman","model_name":"BaseNet-DPS","metrics":{"AP":"25.5"},"paper_url":"https://arxiv.org/abs/2303.06800v1","paper_title":"Object-Centric Multi-Task Learning for Human Instances","paper_date":"2023-03-13","code_links":[],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":154766,"task":"Human Instance Segmentation","parent_task":null,"dataset":"OCHuman","model_name":"Pose2Seg","metrics":{"AP":"23.8"},"paper_url":"http://arxiv.org/abs/1803.10683v3","paper_title":"Pose2Seg: Detection Free Human Instance Segmentation","paper_date":"2018-03-28","code_links":[{"title":"open-mmlab/mmpose","url":"https://github.com/open-mmlab/mmpose"},{"title":"liruilong940607/Pose2Seg","url":"https://github.com/liruilong940607/Pose2Seg"},{"title":"liruilong940607/OCHumanApi","url":"https://github.com/liruilong940607/OCHumanApi"},{"title":"Jittor/InstanceSegmentation-jittor","url":"https://github.com/Jittor/InstanceSegmentation-jittor"},{"title":"ligaoqi2/Pose2Seg-single-person-video-demo","url":"https://github.com/ligaoqi2/Pose2Seg-single-person-video-demo"},{"title":"jacksonlli/ProjectQuarantine_HumanSegmentation","url":"https://github.com/jacksonlli/ProjectQuarantine_HumanSegmentation"},{"title":"hz-ants/Pose2Seg","url":"https://github.com/hz-ants/Pose2Seg"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":154767,"task":"Human Instance Segmentation","parent_task":null,"dataset":"OCHuman","model_name":"PolarMask + CIS","metrics":{"AP":"23.4"},"paper_url":"https://arxiv.org/abs/2108.07199v1","paper_title":"Real-time Human-Centric Segmentation for Complex Video Scenes","paper_date":"2021-08-16","code_links":[{"title":"iigroup/hvisnet","url":"https://github.com/iigroup/hvisnet"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":154768,"task":"Human Instance Segmentation","parent_task":null,"dataset":"OCHuman","model_name":"ResNet-101-FPN + TTG v1","metrics":{"AP":"22.42"},"paper_url":"https://arxiv.org/abs/2212.06242v1","paper_title":"Test-time Adaptation vs. Training-time Generalization: A Case Study in Human Instance Segmentation using Keypoints Estimation","paper_date":"2022-12-12","code_links":[],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":154769,"task":"Human Instance Segmentation","parent_task":null,"dataset":"OCHuman","model_name":"BCNet","metrics":{"AP":"20.6"},"paper_url":"https://arxiv.org/abs/2208.04438v2","paper_title":"Occlusion-Aware Instance Segmentation via BiLayer Network Architectures","paper_date":"2022-08-08","code_links":[{"title":"lkeab/BCNet","url":"https://github.com/lkeab/BCNet"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":154770,"task":"Human Instance Segmentation","parent_task":null,"dataset":"OCHuman","model_name":"CaSe","metrics":{"AP":"18.0"},"paper_url":"https://www.ecva.net/papers/eccv_2020/papers_ECCV/html/2678_ECCV_2020_paper.php","paper_title":"Count- and Similarity-aware R-CNN for Pedestrian Detection","paper_date":null,"code_links":[],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":154771,"task":"Human Instance Segmentation","parent_task":null,"dataset":"OCHuman","model_name":"Mask RCNN","metrics":{"AP":"16.9"},"paper_url":"https://www.ecva.net/papers/eccv_2020/papers_ECCV/html/2678_ECCV_2020_paper.php","paper_title":"Count- and Similarity-aware R-CNN for Pedestrian Detection","paper_date":null,"code_links":[],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]}]}