{"task":"Spatio-Temporal Action Localization","dataset":"AVA-Kinetics","metric_names":["val mAP","test mAP"],"rows":[{"id":40006,"task":"Spatio-Temporal Action Localization","parent_task":"Action Localization","dataset":"AVA-Kinetics","model_name":"VideoMAE V2-g","metrics":{"val mAP":"42.6"},"paper_url":"https://arxiv.org/abs/2303.16727v2","paper_title":"VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking","paper_date":"2023-03-29","code_links":[{"title":"OpenGVLab/VideoMAEv2","url":"https://github.com/OpenGVLab/VideoMAEv2"}],"metrics_order":"[\"val mAP\", \"test mAP\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":40007,"task":"Spatio-Temporal Action Localization","parent_task":"Action Localization","dataset":"AVA-Kinetics","model_name":"STAR/L","metrics":{"val mAP":"41.7"},"paper_url":"https://arxiv.org/abs/2304.12160v1","paper_title":"End-to-End Spatio-Temporal Action Localisation with Video Transformers","paper_date":"2023-04-24","code_links":[],"metrics_order":"[\"val mAP\", \"test mAP\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":40008,"task":"Spatio-Temporal Action Localization","parent_task":"Action Localization","dataset":"AVA-Kinetics","model_name":"InternVideo","metrics":{"val mAP":"41.01"},"paper_url":"https://arxiv.org/abs/2212.03191v2","paper_title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","paper_date":"2022-12-06","code_links":[{"title":"opengvlab/internvideo","url":"https://github.com/opengvlab/internvideo"},{"title":"yingsen1/unimd","url":"https://github.com/yingsen1/unimd"}],"metrics_order":"[\"val mAP\", \"test mAP\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":40009,"task":"Spatio-Temporal Action Localization","parent_task":"Action Localization","dataset":"AVA-Kinetics","model_name":"RM  (multi-scale, ensemble)","metrics":{"val mAP":"40.52"},"paper_url":"https://arxiv.org/abs/2106.08061v2","paper_title":"Relation Modeling in Spatio-Temporal Action Localization","paper_date":"2021-06-15","code_links":[],"metrics_order":"[\"val mAP\", \"test mAP\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":40010,"task":"Spatio-Temporal Action Localization","parent_task":"Action Localization","dataset":"AVA-Kinetics","model_name":"ACAR (multi-scale, ensemble)","metrics":{"test mAP":"39.62","val mAP":"40.49"},"paper_url":"https://arxiv.org/abs/2006.07976v3","paper_title":"Actor-Context-Actor Relation Network for Spatio-Temporal Action Localization","paper_date":"2020-06-14","code_links":[{"title":"towhee-io/towhee","url":"https://github.com/towhee-io/towhee"},{"title":"Siyu-C/ACAR-Net","url":"https://github.com/Siyu-C/ACAR-Net"},{"title":"salmank255/ROADSlowFast","url":"https://github.com/salmank255/ROADSlowFast"}],"metrics_order":"[\"val mAP\", \"test mAP\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":40011,"task":"Spatio-Temporal Action Localization","parent_task":"Action Localization","dataset":"AVA-Kinetics","model_name":"RM (multi-scale, ir-CSN-152)","metrics":{"val mAP":"37.95"},"paper_url":"https://arxiv.org/abs/2106.08061v2","paper_title":"Relation Modeling in Spatio-Temporal Action Localization","paper_date":"2021-06-15","code_links":[],"metrics_order":"[\"val mAP\", \"test mAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":40012,"task":"Spatio-Temporal Action Localization","parent_task":"Action Localization","dataset":"AVA-Kinetics","model_name":"ACAR (multi-scale,  R-101, 8 × 8)","metrics":{"val mAP":"36.36"},"paper_url":"https://arxiv.org/abs/2006.07976v3","paper_title":"Actor-Context-Actor Relation Network for Spatio-Temporal Action Localization","paper_date":"2020-06-14","code_links":[{"title":"towhee-io/towhee","url":"https://github.com/towhee-io/towhee"},{"title":"Siyu-C/ACAR-Net","url":"https://github.com/Siyu-C/ACAR-Net"},{"title":"salmank255/ROADSlowFast","url":"https://github.com/salmank255/ROADSlowFast"}],"metrics_order":"[\"val mAP\", \"test mAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]}]}