{"task":"Visual Object Tracking","dataset":"AVisT","metric_names":["Success Rate"],"rows":[{"id":48245,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"AVisT","model_name":"PiVOT-L","metrics":{"Success Rate":"62.2"},"paper_url":"https://arxiv.org/abs/2409.18901v1","paper_title":"Improving Visual Object Tracking through Visual Prompting","paper_date":"2024-09-27","code_links":[{"title":"chenshihfang/GOT","url":"https://github.com/chenshihfang/GOT"}],"metrics_order":"[\"Success Rate\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48246,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"AVisT","model_name":"UVLTrack-L","metrics":{"Success Rate":"57.8"},"paper_url":"https://arxiv.org/abs/2401.11228v1","paper_title":"Unifying Visual and Vision-Language Tracking via Contrastive Learning","paper_date":"2024-01-20","code_links":[{"title":"openspaceai/uvltrack","url":"https://github.com/openspaceai/uvltrack"}],"metrics_order":"[\"Success Rate\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48247,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"AVisT","model_name":"MixFormerL-22k","metrics":{"Success Rate":"56.0"},"paper_url":"https://arxiv.org/abs/2203.11082v2","paper_title":"MixFormer: End-to-End Tracking with Iterative Mixed Attention","paper_date":"2022-03-21","code_links":[{"title":"MCG-NJU/MixFormer","url":"https://github.com/MCG-NJU/MixFormer"}],"metrics_order":"[\"Success Rate\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48248,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"AVisT","model_name":"GRM","metrics":{"Success Rate":"54.5"},"paper_url":"https://arxiv.org/abs/2303.16580v3","paper_title":"Generalized Relation Modeling for Transformer Tracking","paper_date":"2023-03-29","code_links":[{"title":"little-podi/grm","url":"https://github.com/little-podi/grm"}],"metrics_order":"[\"Success Rate\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48249,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"AVisT","model_name":"ToMP","metrics":{"Success Rate":"52.5"},"paper_url":"https://arxiv.org/abs/2203.11192v1","paper_title":"Transforming Model Prediction for Tracking","paper_date":"2022-03-21","code_links":[{"title":"visionml/pytracking","url":"https://github.com/visionml/pytracking"}],"metrics_order":"[\"Success Rate\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48250,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"AVisT","model_name":"STARK-ST-101","metrics":{"Success Rate":"50.50"},"paper_url":"https://arxiv.org/abs/2103.17154v1","paper_title":"Learning Spatio-Temporal Transformer for Visual Tracking","paper_date":"2021-03-31","code_links":[{"title":"researchmm/Stark","url":"https://github.com/researchmm/Stark"}],"metrics_order":"[\"Success Rate\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48251,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"AVisT","model_name":"TransT","metrics":{"Success Rate":"49.03"},"paper_url":"https://arxiv.org/abs/2103.15436v1","paper_title":"Transformer Tracking","paper_date":"2021-03-29","code_links":[{"title":"chenxin-dlut/TransT","url":"https://github.com/chenxin-dlut/TransT"}],"metrics_order":"[\"Success Rate\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143674,"task":"Visual Object Tracking","parent_task":null,"dataset":"AVisT","model_name":"PiVOT-L","metrics":{"Success Rate":"62.2"},"paper_url":"https://arxiv.org/abs/2409.18901v1","paper_title":"Improving Visual Object Tracking through Visual Prompting","paper_date":"2024-09-27","code_links":[{"title":"chenshihfang/GOT","url":"https://github.com/chenshihfang/GOT"}],"metrics_order":"[\"Success Rate\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143675,"task":"Visual Object Tracking","parent_task":null,"dataset":"AVisT","model_name":"UVLTrack-L","metrics":{"Success Rate":"57.8"},"paper_url":"https://arxiv.org/abs/2401.11228v1","paper_title":"Unifying Visual and Vision-Language Tracking via Contrastive Learning","paper_date":"2024-01-20","code_links":[{"title":"openspaceai/uvltrack","url":"https://github.com/openspaceai/uvltrack"}],"metrics_order":"[\"Success Rate\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143676,"task":"Visual Object Tracking","parent_task":null,"dataset":"AVisT","model_name":"MixFormerL-22k","metrics":{"Success Rate":"56.0"},"paper_url":"https://arxiv.org/abs/2203.11082v2","paper_title":"MixFormer: End-to-End Tracking with Iterative Mixed Attention","paper_date":"2022-03-21","code_links":[{"title":"MCG-NJU/MixFormer","url":"https://github.com/MCG-NJU/MixFormer"}],"metrics_order":"[\"Success Rate\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143677,"task":"Visual Object Tracking","parent_task":null,"dataset":"AVisT","model_name":"GRM","metrics":{"Success Rate":"54.5"},"paper_url":"https://arxiv.org/abs/2303.16580v3","paper_title":"Generalized Relation Modeling for Transformer Tracking","paper_date":"2023-03-29","code_links":[{"title":"little-podi/grm","url":"https://github.com/little-podi/grm"}],"metrics_order":"[\"Success Rate\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143678,"task":"Visual Object Tracking","parent_task":null,"dataset":"AVisT","model_name":"ToMP","metrics":{"Success Rate":"52.5"},"paper_url":"https://arxiv.org/abs/2203.11192v1","paper_title":"Transforming Model Prediction for Tracking","paper_date":"2022-03-21","code_links":[{"title":"visionml/pytracking","url":"https://github.com/visionml/pytracking"}],"metrics_order":"[\"Success Rate\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143679,"task":"Visual Object Tracking","parent_task":null,"dataset":"AVisT","model_name":"STARK-ST-101","metrics":{"Success Rate":"50.50"},"paper_url":"https://arxiv.org/abs/2103.17154v1","paper_title":"Learning Spatio-Temporal Transformer for Visual Tracking","paper_date":"2021-03-31","code_links":[{"title":"researchmm/Stark","url":"https://github.com/researchmm/Stark"}],"metrics_order":"[\"Success Rate\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143680,"task":"Visual Object Tracking","parent_task":null,"dataset":"AVisT","model_name":"TransT","metrics":{"Success Rate":"49.03"},"paper_url":"https://arxiv.org/abs/2103.15436v1","paper_title":"Transformer Tracking","paper_date":"2021-03-29","code_links":[{"title":"chenxin-dlut/TransT","url":"https://github.com/chenxin-dlut/TransT"}],"metrics_order":"[\"Success Rate\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]}]}