{"task":"Human-Object Interaction Detection","dataset":"V-COCO","metric_names":["AP(S1)","AP(S2)","Time Per Frame(ms)","MAP"],"rows":[{"id":49843,"task":"Human-Object Interaction Detection","parent_task":null,"dataset":"V-COCO","model_name":"RLIPv2","metrics":{"AP(S1)":"72.1","AP(S2)":"74.1"},"paper_url":"https://arxiv.org/abs/2308.09351v1","paper_title":"RLIPv2: Fast Scaling of Relational Language-Image Pre-training","paper_date":"2023-08-18","code_links":[{"title":"jacobyuan7/rlipv2","url":"https://github.com/jacobyuan7/rlipv2"},{"title":"jacobyuan7/rlip","url":"https://github.com/jacobyuan7/rlip"},{"title":"jacobyuan7/ocn-hoi-benchmark","url":"https://github.com/jacobyuan7/ocn-hoi-benchmark"}],"metrics_order":"[\"AP(S1)\", \"AP(S2)\", \"Time Per Frame(ms)\", \"MAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":49844,"task":"Human-Object Interaction Detection","parent_task":null,"dataset":"V-COCO","model_name":"MUREN","metrics":{"AP(S1)":"68.8","AP(S2)":"71.0"},"paper_url":"https://arxiv.org/abs/2304.04997v1","paper_title":"Relational Context Learning for Human-Object Interaction Detection","paper_date":"2023-04-11","code_links":[{"title":"OreoChocolate/MUREN","url":"https://github.com/OreoChocolate/MUREN"}],"metrics_order":"[\"AP(S1)\", \"AP(S2)\", \"Time Per Frame(ms)\", \"MAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":49845,"task":"Human-Object Interaction Detection","parent_task":null,"dataset":"V-COCO","model_name":"STIP","metrics":{"AP(S1)":"66.0","AP(S2)":"70.7","Time Per Frame(ms)":"74"},"paper_url":"https://arxiv.org/abs/2206.06291v1","paper_title":"Exploring Structure-aware Transformer over Interaction Proposals for Human-Object Interaction Detection","paper_date":"2022-06-13","code_links":[{"title":"zyong812/stip","url":"https://github.com/zyong812/stip"}],"metrics_order":"[\"AP(S1)\", \"AP(S2)\", \"Time Per Frame(ms)\", \"MAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":49846,"task":"Human-Object Interaction Detection","parent_task":null,"dataset":"V-COCO","model_name":"DiffHOI","metrics":{"AP(S1)":"65.7","AP(S2)":"68.2"},"paper_url":"https://arxiv.org/abs/2305.12252v1","paper_title":"Boosting Human-Object Interaction Detection with Text-to-Image Diffusion Model","paper_date":"2023-05-20","code_links":[{"title":"IDEA-Research/DiffHOI","url":"https://github.com/IDEA-Research/DiffHOI"}],"metrics_order":"[\"AP(S1)\", \"AP(S2)\", \"Time Per Frame(ms)\", \"MAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":49847,"task":"Human-Object Interaction Detection","parent_task":null,"dataset":"V-COCO","model_name":"OCN  (ResNet101)","metrics":{"AP(S1)":"65.3","AP(S2)":"67.1"},"paper_url":"https://arxiv.org/abs/2202.00259v1","paper_title":"Detecting Human-Object Interactions with Object-Guided Cross-Modal Calibrated Semantics","paper_date":"2022-02-01","code_links":[{"title":"jacobyuan7/ocn-hoi-benchmark","url":"https://github.com/jacobyuan7/ocn-hoi-benchmark"}],"metrics_order":"[\"AP(S1)\", \"AP(S2)\", \"Time Per Frame(ms)\", \"MAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":49848,"task":"Human-Object Interaction Detection","parent_task":null,"dataset":"V-COCO","model_name":"OCN  (ResNet50)","metrics":{"AP(S1)":"64.2","AP(S2)":"66.3","Time Per Frame(ms)":"43"},"paper_url":"https://arxiv.org/abs/2202.00259v1","paper_title":"Detecting Human-Object Interactions with Object-Guided Cross-Modal Calibrated Semantics","paper_date":"2022-02-01","code_links":[{"title":"jacobyuan7/ocn-hoi-benchmark","url":"https://github.com/jacobyuan7/ocn-hoi-benchmark"}],"metrics_order":"[\"AP(S1)\", \"AP(S2)\", \"Time Per Frame(ms)\", \"MAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":49849,"task":"Human-Object Interaction Detection","parent_task":null,"dataset":"V-COCO","model_name":"CDN (ResNet101)","metrics":{"AP(S1)":"63.91","AP(S2)":"65.89"},"paper_url":"https://arxiv.org/abs/2108.05077v2","paper_title":"Mining the Benefits of Two-stage and One-stage HOI Detection","paper_date":"2021-08-11","code_links":[{"title":"YueLiao/CDN","url":"https://github.com/YueLiao/CDN"}],"metrics_order":"[\"AP(S1)\", \"AP(S2)\", \"Time Per Frame(ms)\", \"MAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":49850,"task":"Human-Object Interaction Detection","parent_task":null,"dataset":"V-COCO","model_name":"HOICLIP","metrics":{"AP(S1)":"63.50","AP(S2)":"64.81"},"paper_url":"https://arxiv.org/abs/2303.15786v3","paper_title":"HOICLIP: Efficient Knowledge Transfer for HOI Detection with Vision-Language Models","paper_date":"2023-03-28","code_links":[{"title":"artanic30/hoiclip","url":"https://github.com/artanic30/hoiclip"}],"metrics_order":"[\"AP(S1)\", \"AP(S2)\", \"Time Per Frame(ms)\", \"MAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":49851,"task":"Human-Object Interaction Detection","parent_task":null,"dataset":"V-COCO","model_name":"Body Part Interactiveness","metrics":{"AP(S1)":"63.0","AP(S2)":"65.1"},"paper_url":"https://arxiv.org/abs/2207.14192v2","paper_title":"Mining Cross-Person Cues for Body-Part Interactiveness Learning in HOI Detection","paper_date":"2022-07-28","code_links":[{"title":"enlighten0707/body-part-map-for-interactiveness","url":"https://github.com/enlighten0707/body-part-map-for-interactiveness"}],"metrics_order":"[\"AP(S1)\", \"AP(S2)\", \"Time Per Frame(ms)\", \"MAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":49852,"task":"Human-Object Interaction Detection","parent_task":null,"dataset":"V-COCO","model_name":"UPT-R101-DC5","metrics":{"AP(S1)":"61.3","AP(S2)":"67.1","Time Per Frame(ms)":"131"},"paper_url":"https://arxiv.org/abs/2112.01838v2","paper_title":"Efficient Two-Stage Detection of Human-Object Interactions with a Novel Unary-Pairwise Transformer","paper_date":"2021-12-03","code_links":[{"title":"fredzzhang/upt","url":"https://github.com/fredzzhang/upt"}],"metrics_order":"[\"AP(S1)\", \"AP(S2)\", \"Time Per Frame(ms)\", \"MAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":49853,"task":"Human-Object Interaction Detection","parent_task":null,"dataset":"V-COCO","model_name":"UPT-R101","metrics":{"AP(S1)":"60.7","AP(S2)":"66.2","Time Per Frame(ms)":"64"},"paper_url":"https://arxiv.org/abs/2112.01838v2","paper_title":"Efficient Two-Stage Detection of Human-Object Interactions with a Novel Unary-Pairwise Transformer","paper_date":"2021-12-03","code_links":[{"title":"fredzzhang/upt","url":"https://github.com/fredzzhang/upt"}],"metrics_order":"[\"AP(S1)\", \"AP(S2)\", \"Time Per Frame(ms)\", \"MAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":49854,"task":"Human-Object Interaction Detection","parent_task":null,"dataset":"V-COCO","model_name":"UPT-R50","metrics":{"AP(S1)":"59.0","AP(S2)":"64.5","Time Per Frame(ms)":"43"},"paper_url":"https://arxiv.org/abs/2112.01838v2","paper_title":"Efficient Two-Stage Detection of Human-Object Interactions with a Novel Unary-Pairwise Transformer","paper_date":"2021-12-03","code_links":[{"title":"fredzzhang/upt","url":"https://github.com/fredzzhang/upt"}],"metrics_order":"[\"AP(S1)\", \"AP(S2)\", \"Time Per Frame(ms)\", \"MAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":49855,"task":"Human-Object Interaction Detection","parent_task":null,"dataset":"V-COCO","model_name":"QPIC (ResNet50)","metrics":{"AP(S1)":"58.8","AP(S2)":"61.0","Time Per Frame(ms)":"46"},"paper_url":"https://arxiv.org/abs/2103.05399v1","paper_title":"QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information","paper_date":"2021-03-09","code_links":[{"title":"hitachi-rd-cv/qpic","url":"https://github.com/hitachi-rd-cv/qpic"}],"metrics_order":"[\"AP(S1)\", \"AP(S2)\", \"Time Per Frame(ms)\", \"MAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":49856,"task":"Human-Object Interaction Detection","parent_task":null,"dataset":"V-COCO","model_name":"QPIC (ResNet101)","metrics":{"AP(S1)":"58.3","AP(S2)":"60.7","Time Per Frame(ms)":"63"},"paper_url":"https://arxiv.org/abs/2103.05399v1","paper_title":"QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information","paper_date":"2021-03-09","code_links":[{"title":"hitachi-rd-cv/qpic","url":"https://github.com/hitachi-rd-cv/qpic"}],"metrics_order":"[\"AP(S1)\", \"AP(S2)\", \"Time Per Frame(ms)\", \"MAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":49857,"task":"Human-Object Interaction Detection","parent_task":null,"dataset":"V-COCO","model_name":"DIRV","metrics":{"AP(S1)":"56.1","Time Per Frame(ms)":"68"},"paper_url":"https://arxiv.org/abs/2010.01005v2","paper_title":"DIRV: Dense Interaction Region Voting for End-to-End Human-Object Interaction Detection","paper_date":"2020-10-02","code_links":[{"title":"MVIG-SJTU/DIRV","url":"https://github.com/MVIG-SJTU/DIRV"}],"metrics_order":"[\"AP(S1)\", \"AP(S2)\", \"Time Per Frame(ms)\", \"MAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":49858,"task":"Human-Object Interaction Detection","parent_task":null,"dataset":"V-COCO","model_name":"HOTR","metrics":{"AP(S1)":"55.2","AP(S2)":"64.4"},"paper_url":"https://arxiv.org/abs/2104.13682v1","paper_title":"HOTR: End-to-End Human-Object Interaction Detection with Transformers","paper_date":"2021-04-28","code_links":[{"title":"kakaobrain/HOTR","url":"https://github.com/kakaobrain/HOTR"}],"metrics_order":"[\"AP(S1)\", \"AP(S2)\", \"Time Per Frame(ms)\", \"MAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":49859,"task":"Human-Object Interaction Detection","parent_task":null,"dataset":"V-COCO","model_name":"GGNet","metrics":{"AP(S1)":"54.7"},"paper_url":"https://arxiv.org/abs/2104.05269v1","paper_title":"Glance and Gaze: Inferring Action-aware Points for One-Stage Human-Object Interaction Detection","paper_date":"2021-04-12","code_links":[{"title":"SherlockHolmes221/GGNet","url":"https://github.com/SherlockHolmes221/GGNet"}],"metrics_order":"[\"AP(S1)\", \"AP(S2)\", \"Time Per Frame(ms)\", \"MAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":49860,"task":"Human-Object Interaction Detection","parent_task":null,"dataset":"V-COCO","model_name":"SCG","metrics":{"AP(S1)":"54.2","AP(S2)":"60.9","Time Per Frame(ms)":"500"},"paper_url":"https://arxiv.org/abs/2012.06060v3","paper_title":"Spatially Conditioned Graphs for Detecting Human-Object Interactions","paper_date":"2020-12-11","code_links":[{"title":"fredzzhang/spatially-conditioned-graphs","url":"https://github.com/fredzzhang/spatially-conditioned-graphs"},{"title":"fredzzhang/hicodet","url":"https://github.com/fredzzhang/hicodet"}],"metrics_order":"[\"AP(S1)\", \"AP(S2)\", \"Time Per Frame(ms)\", \"MAP\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":49861,"task":"Human-Object Interaction Detection","parent_task":null,"dataset":"V-COCO","model_name":"PD-Net","metrics":{"AP(S1)":"53.34"},"paper_url":"https://arxiv.org/abs/2008.02918v3","paper_title":"Polysemy Deciphering Network for Robust Human-Object Interaction Detection","paper_date":"2020-08-07","code_links":[{"title":"MuchHair/PD-Net","url":"https://github.com/MuchHair/PD-Net"},{"title":"MuchHair/PD-Net-Extended-Version","url":"https://github.com/MuchHair/PD-Net-Extended-Version"}],"metrics_order":"[\"AP(S1)\", \"AP(S2)\", \"Time Per Frame(ms)\", \"MAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":49862,"task":"Human-Object Interaction Detection","parent_task":null,"dataset":"V-COCO","model_name":"IDN","metrics":{"AP(S1)":"53.3","AP(S2)":"60.3"},"paper_url":"https://arxiv.org/abs/2010.16219v2","paper_title":"HOI Analysis: Integrating and Decomposing Human-Object Interaction","paper_date":"2020-10-30","code_links":[{"title":"DirtyHarryLYL/HAKE-Action-Torch","url":"https://github.com/DirtyHarryLYL/HAKE-Action-Torch"},{"title":"UCSB-VRL/GTNet","url":"https://github.com/UCSB-VRL/GTNet"}],"metrics_order":"[\"AP(S1)\", \"AP(S2)\", \"Time Per Frame(ms)\", \"MAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":49863,"task":"Human-Object Interaction Detection","parent_task":null,"dataset":"V-COCO","model_name":"ACP","metrics":{"AP(S1)":"53.23"},"paper_url":"https://www.ecva.net/papers/eccv_2020/papers_ECCV/html/3850_ECCV_2020_paper.php","paper_title":"Detecting Human-Object Interactions with Action Co-occurrence Priors","paper_date":null,"code_links":[{"title":"Dong-JinKim/ActionCooccurrencePriors","url":"https://github.com/Dong-JinKim/ActionCooccurrencePriors"}],"metrics_order":"[\"AP(S1)\", \"AP(S2)\", \"Time Per Frame(ms)\", \"MAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":49864,"task":"Human-Object Interaction Detection","parent_task":null,"dataset":"V-COCO","model_name":"SGCN4HOI","metrics":{"AP(S1)":"53.1","AP(S2)":"57.9"},"paper_url":"https://arxiv.org/abs/2207.05733v1","paper_title":"A Skeleton-aware Graph Convolutional Network for Human-Object Interaction Detection","paper_date":"2022-07-11","code_links":[{"title":"zhumanli/sgcn4hoi","url":"https://github.com/zhumanli/sgcn4hoi"}],"metrics_order":"[\"AP(S1)\", \"AP(S2)\", \"Time Per Frame(ms)\", \"MAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":49865,"task":"Human-Object Interaction Detection","parent_task":null,"dataset":"V-COCO","model_name":"PMN","metrics":{"AP(S1)":"51.8"},"paper_url":"https://arxiv.org/abs/2008.02042v1","paper_title":"Pose-based Modular Network for Human-Object Interaction Detection","paper_date":"2020-08-05","code_links":[{"title":"birlrobotics/PMN","url":"https://github.com/birlrobotics/PMN"}],"metrics_order":"[\"AP(S1)\", \"AP(S2)\", \"Time Per Frame(ms)\", \"MAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":49866,"task":"Human-Object Interaction Detection","parent_task":null,"dataset":"V-COCO","model_name":"VSGNet","metrics":{"AP(S1)":"51.76","AP(S2)":"57.0","Time Per Frame(ms)":"312"},"paper_url":"https://arxiv.org/abs/2003.05541v1","paper_title":"VSGNet: Spatial Attention Network for Detecting Human Object Interactions Using Graph Convolutions","paper_date":"2020-03-11","code_links":[{"title":"ASMIftekhar/VSGNet","url":"https://github.com/ASMIftekhar/VSGNet"},{"title":"UCSB-VRL/GTNet","url":"https://github.com/UCSB-VRL/GTNet"}],"metrics_order":"[\"AP(S1)\", \"AP(S2)\", \"Time Per Frame(ms)\", \"MAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":49867,"task":"Human-Object Interaction Detection","parent_task":null,"dataset":"V-COCO","model_name":"PPDM","metrics":{"AP(S1)":"51.1","Time Per Frame(ms)":"71"},"paper_url":"https://arxiv.org/abs/1912.12898v3","paper_title":"PPDM: Parallel Point Detection and Matching for Real-time Human-Object Interaction Detection","paper_date":"2019-12-30","code_links":[{"title":"YueLiao/PPDM","url":"https://github.com/YueLiao/PPDM"}],"metrics_order":"[\"AP(S1)\", \"AP(S2)\", \"Time Per Frame(ms)\", \"MAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":49868,"task":"Human-Object Interaction Detection","parent_task":null,"dataset":"V-COCO","model_name":"PaStaNet","metrics":{"AP(S1)":"51.0","AP(S2)":"57.5"},"paper_url":"https://arxiv.org/abs/2004.00945v2","paper_title":"PaStaNet: Toward Human Activity Knowledge Engine","paper_date":"2020-04-02","code_links":[{"title":"DirtyHarryLYL/HAKE-Action-Torch","url":"https://github.com/DirtyHarryLYL/HAKE-Action-Torch"},{"title":"DirtyHarryLYL/HAKE","url":"https://github.com/DirtyHarryLYL/HAKE"}],"metrics_order":"[\"AP(S1)\", \"AP(S2)\", \"Time Per Frame(ms)\", \"MAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":49869,"task":"Human-Object Interaction Detection","parent_task":null,"dataset":"V-COCO","model_name":"DRG","metrics":{"AP(S1)":"51.0"},"paper_url":"https://arxiv.org/abs/2008.11714v1","paper_title":"DRG: Dual Relation Graph for Human-Object Interaction Detection","paper_date":"2020-08-26","code_links":[{"title":"vt-vl-lab/DRG","url":"https://github.com/vt-vl-lab/DRG"}],"metrics_order":"[\"AP(S1)\", \"AP(S2)\", \"Time Per Frame(ms)\", \"MAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":49870,"task":"Human-Object Interaction Detection","parent_task":null,"dataset":"V-COCO","model_name":"TIN (TIPAMI)","metrics":{"AP(S1)":"49.1"},"paper_url":"https://arxiv.org/abs/2101.10292v3","paper_title":"Transferable Interactiveness Knowledge for Human-Object Interaction Detection","paper_date":"2021-01-25","code_links":[{"title":"DirtyHarryLYL/Transferable-Interactiveness-Network","url":"https://github.com/DirtyHarryLYL/Transferable-Interactiveness-Network"}],"metrics_order":"[\"AP(S1)\", \"AP(S2)\", \"Time Per Frame(ms)\", \"MAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":49871,"task":"Human-Object Interaction Detection","parent_task":null,"dataset":"V-COCO","model_name":"TIN (Interactiveness)","metrics":{"AP(S1)":"49.0","Time Per Frame(ms)":"513"},"paper_url":"https://arxiv.org/abs/1811.08264v4","paper_title":"Transferable Interactiveness Knowledge for Human-Object Interaction Detection","paper_date":"2018-11-20","code_links":[{"title":"DirtyHarryLYL/Transferable-Interactiveness-Network","url":"https://github.com/DirtyHarryLYL/Transferable-Interactiveness-Network"},{"title":"zhihou7/FCL","url":"https://github.com/zhihou7/FCL"},{"title":"Imposingapple/Transferable_Interactiveness_Network_with_Partpair","url":"https://github.com/Imposingapple/Transferable_Interactiveness_Network_with_Partpair"}],"metrics_order":"[\"AP(S1)\", \"AP(S2)\", \"Time Per Frame(ms)\", \"MAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":49872,"task":"Human-Object Interaction Detection","parent_task":null,"dataset":"V-COCO","model_name":"TIN (CVPR)","metrics":{"AP(S1)":"48.7"},"paper_url":"https://arxiv.org/abs/1811.08264v4","paper_title":"Transferable Interactiveness Knowledge for Human-Object Interaction Detection","paper_date":"2018-11-20","code_links":[{"title":"DirtyHarryLYL/Transferable-Interactiveness-Network","url":"https://github.com/DirtyHarryLYL/Transferable-Interactiveness-Network"},{"title":"zhihou7/FCL","url":"https://github.com/zhihou7/FCL"},{"title":"Imposingapple/Transferable_Interactiveness_Network_with_Partpair","url":"https://github.com/Imposingapple/Transferable_Interactiveness_Network_with_Partpair"}],"metrics_order":"[\"AP(S1)\", \"AP(S2)\", \"Time Per Frame(ms)\", \"MAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":49873,"task":"Human-Object Interaction Detection","parent_task":null,"dataset":"V-COCO","model_name":"iCAN","metrics":{"AP(S1)":"44.7"},"paper_url":"http://arxiv.org/abs/1808.10437v1","paper_title":"iCAN: Instance-Centric Attention Network for Human-Object Interaction Detection","paper_date":"2018-08-30","code_links":[{"title":"vt-vl-lab/iCAN","url":"https://github.com/vt-vl-lab/iCAN"},{"title":"zhihou7/VCL","url":"https://github.com/zhihou7/VCL"},{"title":"zhihou7/FCL","url":"https://github.com/zhihou7/FCL"},{"title":"TaiwanRobert/iCAN_for_live_video","url":"https://github.com/TaiwanRobert/iCAN_for_live_video"}],"metrics_order":"[\"AP(S1)\", \"AP(S2)\", \"Time Per Frame(ms)\", \"MAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":49874,"task":"Human-Object Interaction Detection","parent_task":null,"dataset":"V-COCO","model_name":"GPNN","metrics":{"AP(S1)":"44.0"},"paper_url":"http://arxiv.org/abs/1808.07962v1","paper_title":"Learning Human-Object Interactions by Graph Parsing Neural Networks","paper_date":"2018-08-23","code_links":[{"title":"SiyuanQi/gpnn","url":"https://github.com/SiyuanQi/gpnn"}],"metrics_order":"[\"AP(S1)\", \"AP(S2)\", \"Time Per Frame(ms)\", \"MAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":49875,"task":"Human-Object Interaction Detection","parent_task":null,"dataset":"V-COCO","model_name":"QPIC + CPC","metrics":{"MAP":"63.1"},"paper_url":"https://arxiv.org/abs/2204.04836v1","paper_title":"Consistency Learning via Decoding Path Augmentation for Transformers in Human Object Interaction Detection","paper_date":"2022-04-11","code_links":[{"title":"mlvlab/cpchoi","url":"https://github.com/mlvlab/cpchoi"}],"metrics_order":"[\"AP(S1)\", \"AP(S2)\", \"Time Per Frame(ms)\", \"MAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":49876,"task":"Human-Object Interaction Detection","parent_task":null,"dataset":"V-COCO","model_name":"HOTR + CPC","metrics":{"MAP":"61.6"},"paper_url":"https://arxiv.org/abs/2204.04836v1","paper_title":"Consistency Learning via Decoding Path Augmentation for Transformers in Human Object Interaction Detection","paper_date":"2022-04-11","code_links":[{"title":"mlvlab/cpchoi","url":"https://github.com/mlvlab/cpchoi"}],"metrics_order":"[\"AP(S1)\", \"AP(S2)\", \"Time Per Frame(ms)\", \"MAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]}]}