{"task":"Temporal Action Localization","dataset":"MultiTHUMOS","metric_names":["Average mAP","mAP IOU@0.1","mAP IOU@0.2","mAP IOU@0.3","mAP IOU@0.4","mAP IOU@0.5","mAP IOU@0.6","mAP IOU@0.7"],"rows":[{"id":15559,"task":"Temporal Action Localization","parent_task":"Video","dataset":"MultiTHUMOS","model_name":"TriDet (VideoMAEv2)","metrics":{"Average mAP":"37.5","mAP IOU@0.2":"57.7","mAP IOU@0.5":"42.7","mAP IOU@0.7":"24.3"},"paper_url":"https://arxiv.org/abs/2309.05590v1","paper_title":"Temporal Action Localization with Enhanced Instant Discriminability","paper_date":"2023-09-11","code_links":[{"title":"dingfengshi/tridet","url":"https://github.com/dingfengshi/tridet"},{"title":"sssste/tridet","url":"https://github.com/sssste/tridet"},{"title":"dingfengshi/tridetplus","url":"https://github.com/dingfengshi/tridetplus"}],"metrics_order":"[\"Average mAP\", \"mAP IOU@0.1\", \"mAP IOU@0.2\", \"mAP IOU@0.3\", \"mAP IOU@0.4\", \"mAP IOU@0.5\", \"mAP IOU@0.6\", \"mAP IOU@0.7\", \"mAP IOU@0.8\", \"mAP IOU@0.9\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":15560,"task":"Temporal Action Localization","parent_task":"Video","dataset":"MultiTHUMOS","model_name":"DualDETR (I3D-rgb)","metrics":{"Average mAP":"32.64","mAP IOU@0.1":"53.42","mAP IOU@0.3":"47.41","mAP IOU@0.5":"35.18","mAP IOU@0.7":"20.18","mAP IOU@0.9":"4.02"},"paper_url":"https://arxiv.org/abs/2404.00653v1","paper_title":"Dual DETRs for Multi-Label Temporal Action Detection","paper_date":"2024-03-31","code_links":[],"metrics_order":"[\"Average mAP\", \"mAP IOU@0.1\", \"mAP IOU@0.2\", \"mAP IOU@0.3\", \"mAP IOU@0.4\", \"mAP IOU@0.5\", \"mAP IOU@0.6\", \"mAP IOU@0.7\", \"mAP IOU@0.8\", \"mAP IOU@0.9\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":15561,"task":"Temporal Action Localization","parent_task":"Video","dataset":"MultiTHUMOS","model_name":"TriDet (I3D-rgb)","metrics":{"Average mAP":"30.7","mAP IOU@0.2":"49.1","mAP IOU@0.5":"34.3","mAP IOU@0.7":"17.8"},"paper_url":"https://arxiv.org/abs/2309.05590v1","paper_title":"Temporal Action Localization with Enhanced Instant Discriminability","paper_date":"2023-09-11","code_links":[{"title":"dingfengshi/tridet","url":"https://github.com/dingfengshi/tridet"},{"title":"sssste/tridet","url":"https://github.com/sssste/tridet"},{"title":"dingfengshi/tridetplus","url":"https://github.com/dingfengshi/tridetplus"}],"metrics_order":"[\"Average mAP\", \"mAP IOU@0.1\", \"mAP IOU@0.2\", \"mAP IOU@0.3\", \"mAP IOU@0.4\", \"mAP IOU@0.5\", \"mAP IOU@0.6\", \"mAP IOU@0.7\", \"mAP IOU@0.8\", \"mAP IOU@0.9\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":15562,"task":"Temporal Action Localization","parent_task":"Video","dataset":"MultiTHUMOS","model_name":"TemporalMaxer","metrics":{"Average mAP":"29.9","mAP IOU@0.1":"49.1","mAP IOU@0.2":"47.5","mAP IOU@0.3":"44.3","mAP IOU@0.4":"39.4","mAP IOU@0.5":"33.4","mAP IOU@0.6":"26.5","mAP IOU@0.7":"17.4","mAP IOU@0.8":"9.1","mAP IOU@0.9":"2.24"},"paper_url":"https://arxiv.org/abs/2303.09055v1","paper_title":"TemporalMaxer: Maximize Temporal Context with only Max Pooling for Temporal Action Localization","paper_date":"2023-03-16","code_links":[{"title":"tuantng/temporalmaxer","url":"https://github.com/tuantng/temporalmaxer"}],"metrics_order":"[\"Average mAP\", \"mAP IOU@0.1\", \"mAP IOU@0.2\", \"mAP IOU@0.3\", \"mAP IOU@0.4\", \"mAP IOU@0.5\", \"mAP IOU@0.6\", \"mAP IOU@0.7\", \"mAP IOU@0.8\", \"mAP IOU@0.9\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":15563,"task":"Temporal Action Localization","parent_task":"Video","dataset":"MultiTHUMOS","model_name":"PointTAD","metrics":{"Average mAP":"23.5","mAP IOU@0.1":"42.3","mAP IOU@0.2":"39.7 ","mAP IOU@0.3":"35.8","mAP IOU@0.4":"30.9","mAP IOU@0.5":"24.9","mAP IOU@0.6":"18.5","mAP IOU@0.7":"12.0","mAP IOU@0.8":"5.6","mAP IOU@0.9":"1.4"},"paper_url":"https://arxiv.org/abs/2210.11035v3","paper_title":"PointTAD: Multi-Label Temporal Action Detection with Learnable Query Points","paper_date":"2022-10-20","code_links":[{"title":"mcg-nju/pointtad","url":"https://github.com/mcg-nju/pointtad"}],"metrics_order":"[\"Average mAP\", \"mAP IOU@0.1\", \"mAP IOU@0.2\", \"mAP IOU@0.3\", \"mAP IOU@0.4\", \"mAP IOU@0.5\", \"mAP IOU@0.6\", \"mAP IOU@0.7\", \"mAP IOU@0.8\", \"mAP IOU@0.9\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":15564,"task":"Temporal Action Localization","parent_task":"Video","dataset":"MultiTHUMOS","model_name":"PDAN","metrics":{"Average mAP":"17.3"},"paper_url":"https://openaccess.thecvf.com/content/WACV2021/html/Dai_PDAN_Pyramid_Dilated_Attention_Network_for_Action_Detection_WACV_2021_paper.html","paper_title":"PDAN: Pyramid Dilated Attention Network for Action Detection","paper_date":"2021-01-05","code_links":[{"title":"dairui01/PDAN","url":"https://github.com/dairui01/PDAN"}],"metrics_order":"[\"Average mAP\", \"mAP IOU@0.1\", \"mAP IOU@0.2\", \"mAP IOU@0.3\", \"mAP IOU@0.4\", \"mAP IOU@0.5\", \"mAP IOU@0.6\", \"mAP IOU@0.7\", \"mAP IOU@0.8\", \"mAP IOU@0.9\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":15565,"task":"Temporal Action Localization","parent_task":"Video","dataset":"MultiTHUMOS","model_name":"MS-TCT","metrics":{"Average mAP":"16.2"},"paper_url":"https://arxiv.org/abs/2112.03902v2","paper_title":"MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detection","paper_date":"2021-12-07","code_links":[{"title":"dairui01/MS-TCT","url":"https://github.com/dairui01/MS-TCT"}],"metrics_order":"[\"Average mAP\", \"mAP IOU@0.1\", \"mAP IOU@0.2\", \"mAP IOU@0.3\", \"mAP IOU@0.4\", \"mAP IOU@0.5\", \"mAP IOU@0.6\", \"mAP IOU@0.7\", \"mAP IOU@0.8\", \"mAP IOU@0.9\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":15566,"task":"Temporal Action Localization","parent_task":"Video","dataset":"MultiTHUMOS","model_name":"MLAD","metrics":{"Average mAP":"14.2"},"paper_url":"https://arxiv.org/abs/2103.03027v3","paper_title":"Modeling Multi-Label Action Dependencies for Temporal Action Localization","paper_date":"2021-03-04","code_links":[{"title":"ptirupat/MLAD","url":"https://github.com/ptirupat/MLAD"}],"metrics_order":"[\"Average mAP\", \"mAP IOU@0.1\", \"mAP IOU@0.2\", \"mAP IOU@0.3\", \"mAP IOU@0.4\", \"mAP IOU@0.5\", \"mAP IOU@0.6\", \"mAP IOU@0.7\", \"mAP IOU@0.8\", \"mAP IOU@0.9\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":18903,"task":"Temporal Action Localization","parent_task":null,"dataset":"MultiTHUMOS","model_name":"TriDet (VideoMAEv2)","metrics":{"Average mAP":"37.5","mAP IOU@0.2":"57.7","mAP IOU@0.5":"42.7","mAP IOU@0.7":"24.3"},"paper_url":"https://arxiv.org/abs/2309.05590v1","paper_title":"Temporal Action Localization with Enhanced Instant Discriminability","paper_date":"2023-09-11","code_links":[{"title":"dingfengshi/tridet","url":"https://github.com/dingfengshi/tridet"},{"title":"sssste/tridet","url":"https://github.com/sssste/tridet"},{"title":"dingfengshi/tridetplus","url":"https://github.com/dingfengshi/tridetplus"}],"metrics_order":"[\"Average mAP\", \"mAP IOU@0.1\", \"mAP IOU@0.2\", \"mAP IOU@0.3\", \"mAP IOU@0.4\", \"mAP IOU@0.5\", \"mAP IOU@0.6\", \"mAP IOU@0.7\", \"mAP IOU@0.8\", \"mAP IOU@0.9\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":18904,"task":"Temporal Action Localization","parent_task":null,"dataset":"MultiTHUMOS","model_name":"DualDETR (I3D-rgb)","metrics":{"Average mAP":"32.64","mAP IOU@0.1":"53.42","mAP IOU@0.3":"47.41","mAP IOU@0.5":"35.18","mAP IOU@0.7":"20.18","mAP IOU@0.9":"4.02"},"paper_url":"https://arxiv.org/abs/2404.00653v1","paper_title":"Dual DETRs for Multi-Label Temporal Action Detection","paper_date":"2024-03-31","code_links":[],"metrics_order":"[\"Average mAP\", \"mAP IOU@0.1\", \"mAP IOU@0.2\", \"mAP IOU@0.3\", \"mAP IOU@0.4\", \"mAP IOU@0.5\", \"mAP IOU@0.6\", \"mAP IOU@0.7\", \"mAP IOU@0.8\", \"mAP IOU@0.9\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":18905,"task":"Temporal Action Localization","parent_task":null,"dataset":"MultiTHUMOS","model_name":"TriDet (I3D-rgb)","metrics":{"Average mAP":"30.7","mAP IOU@0.2":"49.1","mAP IOU@0.5":"34.3","mAP IOU@0.7":"17.8"},"paper_url":"https://arxiv.org/abs/2309.05590v1","paper_title":"Temporal Action Localization with Enhanced Instant Discriminability","paper_date":"2023-09-11","code_links":[{"title":"dingfengshi/tridet","url":"https://github.com/dingfengshi/tridet"},{"title":"sssste/tridet","url":"https://github.com/sssste/tridet"},{"title":"dingfengshi/tridetplus","url":"https://github.com/dingfengshi/tridetplus"}],"metrics_order":"[\"Average mAP\", \"mAP IOU@0.1\", \"mAP IOU@0.2\", \"mAP IOU@0.3\", \"mAP IOU@0.4\", \"mAP IOU@0.5\", \"mAP IOU@0.6\", \"mAP IOU@0.7\", \"mAP IOU@0.8\", \"mAP IOU@0.9\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":18906,"task":"Temporal Action Localization","parent_task":null,"dataset":"MultiTHUMOS","model_name":"TemporalMaxer","metrics":{"Average mAP":"29.9","mAP IOU@0.1":"49.1","mAP IOU@0.2":"47.5","mAP IOU@0.3":"44.3","mAP IOU@0.4":"39.4","mAP IOU@0.5":"33.4","mAP IOU@0.6":"26.5","mAP IOU@0.7":"17.4","mAP IOU@0.8":"9.1","mAP IOU@0.9":"2.24"},"paper_url":"https://arxiv.org/abs/2303.09055v1","paper_title":"TemporalMaxer: Maximize Temporal Context with only Max Pooling for Temporal Action Localization","paper_date":"2023-03-16","code_links":[{"title":"tuantng/temporalmaxer","url":"https://github.com/tuantng/temporalmaxer"}],"metrics_order":"[\"Average mAP\", \"mAP IOU@0.1\", \"mAP IOU@0.2\", \"mAP IOU@0.3\", \"mAP IOU@0.4\", \"mAP IOU@0.5\", \"mAP IOU@0.6\", \"mAP IOU@0.7\", \"mAP IOU@0.8\", \"mAP IOU@0.9\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":18907,"task":"Temporal Action Localization","parent_task":null,"dataset":"MultiTHUMOS","model_name":"PointTAD","metrics":{"Average mAP":"23.5","mAP IOU@0.1":"42.3","mAP IOU@0.2":"39.7 ","mAP IOU@0.3":"35.8","mAP IOU@0.4":"30.9","mAP IOU@0.5":"24.9","mAP IOU@0.6":"18.5","mAP IOU@0.7":"12.0","mAP IOU@0.8":"5.6","mAP IOU@0.9":"1.4"},"paper_url":"https://arxiv.org/abs/2210.11035v3","paper_title":"PointTAD: Multi-Label Temporal Action Detection with Learnable Query Points","paper_date":"2022-10-20","code_links":[{"title":"mcg-nju/pointtad","url":"https://github.com/mcg-nju/pointtad"}],"metrics_order":"[\"Average mAP\", \"mAP IOU@0.1\", \"mAP IOU@0.2\", \"mAP IOU@0.3\", \"mAP IOU@0.4\", \"mAP IOU@0.5\", \"mAP IOU@0.6\", \"mAP IOU@0.7\", \"mAP IOU@0.8\", \"mAP IOU@0.9\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":18908,"task":"Temporal Action Localization","parent_task":null,"dataset":"MultiTHUMOS","model_name":"PDAN","metrics":{"Average mAP":"17.3"},"paper_url":"https://openaccess.thecvf.com/content/WACV2021/html/Dai_PDAN_Pyramid_Dilated_Attention_Network_for_Action_Detection_WACV_2021_paper.html","paper_title":"PDAN: Pyramid Dilated Attention Network for Action Detection","paper_date":"2021-01-05","code_links":[{"title":"dairui01/PDAN","url":"https://github.com/dairui01/PDAN"}],"metrics_order":"[\"Average mAP\", \"mAP IOU@0.1\", \"mAP IOU@0.2\", \"mAP IOU@0.3\", \"mAP IOU@0.4\", \"mAP IOU@0.5\", \"mAP IOU@0.6\", \"mAP IOU@0.7\", \"mAP IOU@0.8\", \"mAP IOU@0.9\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":18909,"task":"Temporal Action Localization","parent_task":null,"dataset":"MultiTHUMOS","model_name":"MS-TCT","metrics":{"Average mAP":"16.2"},"paper_url":"https://arxiv.org/abs/2112.03902v2","paper_title":"MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detection","paper_date":"2021-12-07","code_links":[{"title":"dairui01/MS-TCT","url":"https://github.com/dairui01/MS-TCT"}],"metrics_order":"[\"Average mAP\", \"mAP IOU@0.1\", \"mAP IOU@0.2\", \"mAP IOU@0.3\", \"mAP IOU@0.4\", \"mAP IOU@0.5\", \"mAP IOU@0.6\", \"mAP IOU@0.7\", \"mAP IOU@0.8\", \"mAP IOU@0.9\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":18910,"task":"Temporal Action Localization","parent_task":null,"dataset":"MultiTHUMOS","model_name":"MLAD","metrics":{"Average mAP":"14.2"},"paper_url":"https://arxiv.org/abs/2103.03027v3","paper_title":"Modeling Multi-Label Action Dependencies for Temporal Action Localization","paper_date":"2021-03-04","code_links":[{"title":"ptirupat/MLAD","url":"https://github.com/ptirupat/MLAD"}],"metrics_order":"[\"Average mAP\", \"mAP IOU@0.1\", \"mAP IOU@0.2\", \"mAP IOU@0.3\", \"mAP IOU@0.4\", \"mAP IOU@0.5\", \"mAP IOU@0.6\", \"mAP IOU@0.7\", \"mAP IOU@0.8\", \"mAP IOU@0.9\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":21825,"task":"Temporal Action Localization","parent_task":"Zero-Shot Learning","dataset":"MultiTHUMOS","model_name":"TriDet (VideoMAEv2)","metrics":{"Average mAP":"37.5","mAP IOU@0.2":"57.7","mAP IOU@0.5":"42.7","mAP IOU@0.7":"24.3"},"paper_url":"https://arxiv.org/abs/2309.05590v1","paper_title":"Temporal Action Localization with Enhanced Instant Discriminability","paper_date":"2023-09-11","code_links":[{"title":"dingfengshi/tridet","url":"https://github.com/dingfengshi/tridet"},{"title":"sssste/tridet","url":"https://github.com/sssste/tridet"},{"title":"dingfengshi/tridetplus","url":"https://github.com/dingfengshi/tridetplus"}],"metrics_order":"[\"Average mAP\", \"mAP IOU@0.1\", \"mAP IOU@0.2\", \"mAP IOU@0.3\", \"mAP IOU@0.4\", \"mAP IOU@0.5\", \"mAP IOU@0.6\", \"mAP IOU@0.7\", \"mAP IOU@0.8\", \"mAP IOU@0.9\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":21826,"task":"Temporal Action Localization","parent_task":"Zero-Shot Learning","dataset":"MultiTHUMOS","model_name":"DualDETR (I3D-rgb)","metrics":{"Average mAP":"32.64","mAP IOU@0.1":"53.42","mAP IOU@0.3":"47.41","mAP IOU@0.5":"35.18","mAP IOU@0.7":"20.18","mAP IOU@0.9":"4.02"},"paper_url":"https://arxiv.org/abs/2404.00653v1","paper_title":"Dual DETRs for Multi-Label Temporal Action Detection","paper_date":"2024-03-31","code_links":[],"metrics_order":"[\"Average mAP\", \"mAP IOU@0.1\", \"mAP IOU@0.2\", \"mAP IOU@0.3\", \"mAP IOU@0.4\", \"mAP IOU@0.5\", \"mAP IOU@0.6\", \"mAP IOU@0.7\", \"mAP IOU@0.8\", \"mAP IOU@0.9\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":21827,"task":"Temporal Action Localization","parent_task":"Zero-Shot Learning","dataset":"MultiTHUMOS","model_name":"TriDet (I3D-rgb)","metrics":{"Average mAP":"30.7","mAP IOU@0.2":"49.1","mAP IOU@0.5":"34.3","mAP IOU@0.7":"17.8"},"paper_url":"https://arxiv.org/abs/2309.05590v1","paper_title":"Temporal Action Localization with Enhanced Instant Discriminability","paper_date":"2023-09-11","code_links":[{"title":"dingfengshi/tridet","url":"https://github.com/dingfengshi/tridet"},{"title":"sssste/tridet","url":"https://github.com/sssste/tridet"},{"title":"dingfengshi/tridetplus","url":"https://github.com/dingfengshi/tridetplus"}],"metrics_order":"[\"Average mAP\", \"mAP IOU@0.1\", \"mAP IOU@0.2\", \"mAP IOU@0.3\", \"mAP IOU@0.4\", \"mAP IOU@0.5\", \"mAP IOU@0.6\", \"mAP IOU@0.7\", \"mAP IOU@0.8\", \"mAP IOU@0.9\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":21828,"task":"Temporal Action Localization","parent_task":"Zero-Shot Learning","dataset":"MultiTHUMOS","model_name":"TemporalMaxer","metrics":{"Average mAP":"29.9","mAP IOU@0.1":"49.1","mAP IOU@0.2":"47.5","mAP IOU@0.3":"44.3","mAP IOU@0.4":"39.4","mAP IOU@0.5":"33.4","mAP IOU@0.6":"26.5","mAP IOU@0.7":"17.4","mAP IOU@0.8":"9.1","mAP IOU@0.9":"2.24"},"paper_url":"https://arxiv.org/abs/2303.09055v1","paper_title":"TemporalMaxer: Maximize Temporal Context with only Max Pooling for Temporal Action Localization","paper_date":"2023-03-16","code_links":[{"title":"tuantng/temporalmaxer","url":"https://github.com/tuantng/temporalmaxer"}],"metrics_order":"[\"Average mAP\", \"mAP IOU@0.1\", \"mAP IOU@0.2\", \"mAP IOU@0.3\", \"mAP IOU@0.4\", \"mAP IOU@0.5\", \"mAP IOU@0.6\", \"mAP IOU@0.7\", \"mAP IOU@0.8\", \"mAP IOU@0.9\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":21829,"task":"Temporal Action Localization","parent_task":"Zero-Shot Learning","dataset":"MultiTHUMOS","model_name":"PointTAD","metrics":{"Average mAP":"23.5","mAP IOU@0.1":"42.3","mAP IOU@0.2":"39.7 ","mAP IOU@0.3":"35.8","mAP IOU@0.4":"30.9","mAP IOU@0.5":"24.9","mAP IOU@0.6":"18.5","mAP IOU@0.7":"12.0","mAP IOU@0.8":"5.6","mAP IOU@0.9":"1.4"},"paper_url":"https://arxiv.org/abs/2210.11035v3","paper_title":"PointTAD: Multi-Label Temporal Action Detection with Learnable Query Points","paper_date":"2022-10-20","code_links":[{"title":"mcg-nju/pointtad","url":"https://github.com/mcg-nju/pointtad"}],"metrics_order":"[\"Average mAP\", \"mAP IOU@0.1\", \"mAP IOU@0.2\", \"mAP IOU@0.3\", \"mAP IOU@0.4\", \"mAP IOU@0.5\", \"mAP IOU@0.6\", \"mAP IOU@0.7\", \"mAP IOU@0.8\", \"mAP IOU@0.9\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":21830,"task":"Temporal Action Localization","parent_task":"Zero-Shot Learning","dataset":"MultiTHUMOS","model_name":"PDAN","metrics":{"Average mAP":"17.3"},"paper_url":"https://openaccess.thecvf.com/content/WACV2021/html/Dai_PDAN_Pyramid_Dilated_Attention_Network_for_Action_Detection_WACV_2021_paper.html","paper_title":"PDAN: Pyramid Dilated Attention Network for Action Detection","paper_date":"2021-01-05","code_links":[{"title":"dairui01/PDAN","url":"https://github.com/dairui01/PDAN"}],"metrics_order":"[\"Average mAP\", \"mAP IOU@0.1\", \"mAP IOU@0.2\", \"mAP IOU@0.3\", \"mAP IOU@0.4\", \"mAP IOU@0.5\", \"mAP IOU@0.6\", \"mAP IOU@0.7\", \"mAP IOU@0.8\", \"mAP IOU@0.9\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":21831,"task":"Temporal Action Localization","parent_task":"Zero-Shot Learning","dataset":"MultiTHUMOS","model_name":"MS-TCT","metrics":{"Average mAP":"16.2"},"paper_url":"https://arxiv.org/abs/2112.03902v2","paper_title":"MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detection","paper_date":"2021-12-07","code_links":[{"title":"dairui01/MS-TCT","url":"https://github.com/dairui01/MS-TCT"}],"metrics_order":"[\"Average mAP\", \"mAP IOU@0.1\", \"mAP IOU@0.2\", \"mAP IOU@0.3\", \"mAP IOU@0.4\", \"mAP IOU@0.5\", \"mAP IOU@0.6\", \"mAP IOU@0.7\", \"mAP IOU@0.8\", \"mAP IOU@0.9\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":21832,"task":"Temporal Action Localization","parent_task":"Zero-Shot Learning","dataset":"MultiTHUMOS","model_name":"MLAD","metrics":{"Average mAP":"14.2"},"paper_url":"https://arxiv.org/abs/2103.03027v3","paper_title":"Modeling Multi-Label Action Dependencies for Temporal Action Localization","paper_date":"2021-03-04","code_links":[{"title":"ptirupat/MLAD","url":"https://github.com/ptirupat/MLAD"}],"metrics_order":"[\"Average mAP\", \"mAP IOU@0.1\", \"mAP IOU@0.2\", \"mAP IOU@0.3\", \"mAP IOU@0.4\", \"mAP IOU@0.5\", \"mAP IOU@0.6\", \"mAP IOU@0.7\", \"mAP IOU@0.8\", \"mAP IOU@0.9\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":39125,"task":"Temporal Action Localization","parent_task":"Action Localization","dataset":"MultiTHUMOS","model_name":"TriDet (VideoMAEv2)","metrics":{"Average mAP":"37.5","mAP IOU@0.2":"57.7","mAP IOU@0.5":"42.7","mAP IOU@0.7":"24.3"},"paper_url":"https://arxiv.org/abs/2309.05590v1","paper_title":"Temporal Action Localization with Enhanced Instant Discriminability","paper_date":"2023-09-11","code_links":[{"title":"dingfengshi/tridet","url":"https://github.com/dingfengshi/tridet"},{"title":"sssste/tridet","url":"https://github.com/sssste/tridet"},{"title":"dingfengshi/tridetplus","url":"https://github.com/dingfengshi/tridetplus"}],"metrics_order":"[\"Average mAP\", \"mAP IOU@0.1\", \"mAP IOU@0.2\", \"mAP IOU@0.3\", \"mAP IOU@0.4\", \"mAP IOU@0.5\", \"mAP IOU@0.6\", \"mAP IOU@0.7\", \"mAP IOU@0.8\", \"mAP IOU@0.9\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":39126,"task":"Temporal Action Localization","parent_task":"Action Localization","dataset":"MultiTHUMOS","model_name":"DualDETR (I3D-rgb)","metrics":{"Average mAP":"32.64","mAP IOU@0.1":"53.42","mAP IOU@0.3":"47.41","mAP IOU@0.5":"35.18","mAP IOU@0.7":"20.18","mAP IOU@0.9":"4.02"},"paper_url":"https://arxiv.org/abs/2404.00653v1","paper_title":"Dual DETRs for Multi-Label Temporal Action Detection","paper_date":"2024-03-31","code_links":[],"metrics_order":"[\"Average mAP\", \"mAP IOU@0.1\", \"mAP IOU@0.2\", \"mAP IOU@0.3\", \"mAP IOU@0.4\", \"mAP IOU@0.5\", \"mAP IOU@0.6\", \"mAP IOU@0.7\", \"mAP IOU@0.8\", \"mAP IOU@0.9\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":39127,"task":"Temporal Action Localization","parent_task":"Action Localization","dataset":"MultiTHUMOS","model_name":"TriDet (I3D-rgb)","metrics":{"Average mAP":"30.7","mAP IOU@0.2":"49.1","mAP IOU@0.5":"34.3","mAP IOU@0.7":"17.8"},"paper_url":"https://arxiv.org/abs/2309.05590v1","paper_title":"Temporal Action Localization with Enhanced Instant Discriminability","paper_date":"2023-09-11","code_links":[{"title":"dingfengshi/tridet","url":"https://github.com/dingfengshi/tridet"},{"title":"sssste/tridet","url":"https://github.com/sssste/tridet"},{"title":"dingfengshi/tridetplus","url":"https://github.com/dingfengshi/tridetplus"}],"metrics_order":"[\"Average mAP\", \"mAP IOU@0.1\", \"mAP IOU@0.2\", \"mAP IOU@0.3\", \"mAP IOU@0.4\", \"mAP IOU@0.5\", \"mAP IOU@0.6\", \"mAP IOU@0.7\", \"mAP IOU@0.8\", \"mAP IOU@0.9\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":39128,"task":"Temporal Action Localization","parent_task":"Action Localization","dataset":"MultiTHUMOS","model_name":"TemporalMaxer","metrics":{"Average mAP":"29.9","mAP IOU@0.1":"49.1","mAP IOU@0.2":"47.5","mAP IOU@0.3":"44.3","mAP IOU@0.4":"39.4","mAP IOU@0.5":"33.4","mAP IOU@0.6":"26.5","mAP IOU@0.7":"17.4","mAP IOU@0.8":"9.1","mAP IOU@0.9":"2.24"},"paper_url":"https://arxiv.org/abs/2303.09055v1","paper_title":"TemporalMaxer: Maximize Temporal Context with only Max Pooling for Temporal Action Localization","paper_date":"2023-03-16","code_links":[{"title":"tuantng/temporalmaxer","url":"https://github.com/tuantng/temporalmaxer"}],"metrics_order":"[\"Average mAP\", \"mAP IOU@0.1\", \"mAP IOU@0.2\", \"mAP IOU@0.3\", \"mAP IOU@0.4\", \"mAP IOU@0.5\", \"mAP IOU@0.6\", \"mAP IOU@0.7\", \"mAP IOU@0.8\", \"mAP IOU@0.9\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":39129,"task":"Temporal Action Localization","parent_task":"Action Localization","dataset":"MultiTHUMOS","model_name":"PointTAD","metrics":{"Average mAP":"23.5","mAP IOU@0.1":"42.3","mAP IOU@0.2":"39.7 ","mAP IOU@0.3":"35.8","mAP IOU@0.4":"30.9","mAP IOU@0.5":"24.9","mAP IOU@0.6":"18.5","mAP IOU@0.7":"12.0","mAP IOU@0.8":"5.6","mAP IOU@0.9":"1.4"},"paper_url":"https://arxiv.org/abs/2210.11035v3","paper_title":"PointTAD: Multi-Label Temporal Action Detection with Learnable Query Points","paper_date":"2022-10-20","code_links":[{"title":"mcg-nju/pointtad","url":"https://github.com/mcg-nju/pointtad"}],"metrics_order":"[\"Average mAP\", \"mAP IOU@0.1\", \"mAP IOU@0.2\", \"mAP IOU@0.3\", \"mAP IOU@0.4\", \"mAP IOU@0.5\", \"mAP IOU@0.6\", \"mAP IOU@0.7\", \"mAP IOU@0.8\", \"mAP IOU@0.9\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":39130,"task":"Temporal Action Localization","parent_task":"Action Localization","dataset":"MultiTHUMOS","model_name":"PDAN","metrics":{"Average mAP":"17.3"},"paper_url":"https://openaccess.thecvf.com/content/WACV2021/html/Dai_PDAN_Pyramid_Dilated_Attention_Network_for_Action_Detection_WACV_2021_paper.html","paper_title":"PDAN: Pyramid Dilated Attention Network for Action Detection","paper_date":"2021-01-05","code_links":[{"title":"dairui01/PDAN","url":"https://github.com/dairui01/PDAN"}],"metrics_order":"[\"Average mAP\", \"mAP IOU@0.1\", \"mAP IOU@0.2\", \"mAP IOU@0.3\", \"mAP IOU@0.4\", \"mAP IOU@0.5\", \"mAP IOU@0.6\", \"mAP IOU@0.7\", \"mAP IOU@0.8\", \"mAP IOU@0.9\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":39131,"task":"Temporal Action Localization","parent_task":"Action Localization","dataset":"MultiTHUMOS","model_name":"MS-TCT","metrics":{"Average mAP":"16.2"},"paper_url":"https://arxiv.org/abs/2112.03902v2","paper_title":"MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detection","paper_date":"2021-12-07","code_links":[{"title":"dairui01/MS-TCT","url":"https://github.com/dairui01/MS-TCT"}],"metrics_order":"[\"Average mAP\", \"mAP IOU@0.1\", \"mAP IOU@0.2\", \"mAP IOU@0.3\", \"mAP IOU@0.4\", \"mAP IOU@0.5\", \"mAP IOU@0.6\", \"mAP IOU@0.7\", \"mAP IOU@0.8\", \"mAP IOU@0.9\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":39132,"task":"Temporal Action Localization","parent_task":"Action Localization","dataset":"MultiTHUMOS","model_name":"MLAD","metrics":{"Average mAP":"14.2"},"paper_url":"https://arxiv.org/abs/2103.03027v3","paper_title":"Modeling Multi-Label Action Dependencies for Temporal Action Localization","paper_date":"2021-03-04","code_links":[{"title":"ptirupat/MLAD","url":"https://github.com/ptirupat/MLAD"}],"metrics_order":"[\"Average mAP\", \"mAP IOU@0.1\", \"mAP IOU@0.2\", \"mAP IOU@0.3\", \"mAP IOU@0.4\", \"mAP IOU@0.5\", \"mAP IOU@0.6\", \"mAP IOU@0.7\", \"mAP IOU@0.8\", \"mAP IOU@0.9\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]}]}