{"task":"Multi-Object Tracking","dataset":"BDD100K","metric_names":["TETA","AssocA","ClsA","LocA"],"rows":[{"id":27280,"task":"Multi-Object Tracking","parent_task":null,"dataset":"BDD100K","model_name":"CO-MOT","metrics":{"AssocA":"56.2","ClsA":"63.6","LocA":"38.7","TETA":"52.8"},"paper_url":"https://arxiv.org/abs/2305.12724v1","paper_title":"Bridging the Gap Between End-to-end and Non-End-to-end Multi-Object Tracking","paper_date":"2023-05-22","code_links":[{"title":"bingfengyan/visam","url":"https://github.com/bingfengyan/visam"},{"title":"BingfengYan/CO-MOT","url":"https://github.com/BingfengYan/CO-MOT"}],"metrics_order":"[\"TETA\", \"AssocA\", \"ClsA\", \"LocA\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":47700,"task":"Multi-Object Tracking","parent_task":"Object Tracking","dataset":"BDD100K","model_name":"CO-MOT","metrics":{"AssocA":"56.2","ClsA":"63.6","LocA":"38.7","TETA":"52.8"},"paper_url":"https://arxiv.org/abs/2305.12724v1","paper_title":"Bridging the Gap Between End-to-end and Non-End-to-end Multi-Object Tracking","paper_date":"2023-05-22","code_links":[{"title":"bingfengyan/visam","url":"https://github.com/bingfengyan/visam"},{"title":"BingfengYan/CO-MOT","url":"https://github.com/BingfengYan/CO-MOT"}],"metrics_order":"[\"TETA\", \"AssocA\", \"ClsA\", \"LocA\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":758977,"task":"Multi-Object Tracking","parent_task":null,"dataset":"BDD100K","model_name":"COVTrack++","metrics":{"AssocA":"30.5"},"paper_url":"https://paperswithcode.com/paper/covtrack-learning-open-vocabulary-multi-object-tracking-from-continuous-videos-via-a-synergistic-paradigm","paper_title":"COVTrack++: Learning Open-Vocabulary Multi-Object Tracking from Continuous Videos via a Synergistic Paradigm","paper_date":"2026-03-25","code_links":[],"metrics_order":null,"area":null,"uses_additional_data":null,"source":"auto","tags":[]}]}