{"task":"Visual Object Tracking","dataset":"TNL2K","metric_names":["AUC","precision","Normalized Precision"],"rows":[{"id":48062,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TNL2K","model_name":"MCITrack-L384","metrics":{"AUC":"65.3"},"paper_url":"https://arxiv.org/abs/2412.11023v1","paper_title":"Exploring Enhanced Contextual Information for Video-Level Object Tracking","paper_date":"2024-12-15","code_links":[{"title":"kangben258/MCITrack","url":"https://github.com/kangben258/MCITrack"}],"metrics_order":"[\"AUC\", \"precision\", \"Normalized Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48063,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TNL2K","model_name":"SPMTrack-G","metrics":{"AUC":"64.7","Normalized Precision":"82.6","precision":"70.6"},"paper_url":"https://arxiv.org/abs/2503.18338v1","paper_title":"SPMTrack: Spatio-Temporal Parameter-Efficient Fine-Tuning with Mixture of Experts for Scalable Visual Tracking","paper_date":"2025-03-24","code_links":[{"title":"wenruicai/spmtrack","url":"https://github.com/wenruicai/spmtrack"}],"metrics_order":"[\"AUC\", \"precision\", \"Normalized Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48064,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TNL2K","model_name":"SPMTrack-L","metrics":{"AUC":"63.7","Normalized Precision":"81.5","precision":"69.2"},"paper_url":"https://arxiv.org/abs/2503.18338v1","paper_title":"SPMTrack: Spatio-Temporal Parameter-Efficient Fine-Tuning with Mixture of Experts for Scalable Visual Tracking","paper_date":"2025-03-24","code_links":[{"title":"wenruicai/spmtrack","url":"https://github.com/wenruicai/spmtrack"}],"metrics_order":"[\"AUC\", \"precision\", \"Normalized Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48065,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TNL2K","model_name":"MCITrack-B224","metrics":{"AUC":"62.9"},"paper_url":"https://arxiv.org/abs/2412.11023v1","paper_title":"Exploring Enhanced Contextual Information for Video-Level Object Tracking","paper_date":"2024-12-15","code_links":[{"title":"kangben258/MCITrack","url":"https://github.com/kangben258/MCITrack"}],"metrics_order":"[\"AUC\", \"precision\", \"Normalized Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48066,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TNL2K","model_name":"LoRAT-g-378","metrics":{"AUC":"62.7","precision":"67.8"},"paper_url":"https://arxiv.org/abs/2403.05231v2","paper_title":"Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performance","paper_date":"2024-03-08","code_links":[{"title":"litinglin/lorat","url":"https://github.com/litinglin/lorat"}],"metrics_order":"[\"AUC\", \"precision\", \"Normalized Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48067,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TNL2K","model_name":"LoRAT-L-378","metrics":{"AUC":"62.3","precision":"67.0"},"paper_url":"https://arxiv.org/abs/2403.05231v2","paper_title":"Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performance","paper_date":"2024-03-08","code_links":[{"title":"litinglin/lorat","url":"https://github.com/litinglin/lorat"}],"metrics_order":"[\"AUC\", \"precision\", \"Normalized Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48068,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TNL2K","model_name":"SPMTrack-B","metrics":{"AUC":"62.0","Normalized Precision":"79.7","precision":"66.7"},"paper_url":"https://arxiv.org/abs/2503.18338v1","paper_title":"SPMTrack: Spatio-Temporal Parameter-Efficient Fine-Tuning with Mixture of Experts for Scalable Visual Tracking","paper_date":"2025-03-24","code_links":[{"title":"wenruicai/spmtrack","url":"https://github.com/wenruicai/spmtrack"}],"metrics_order":"[\"AUC\", \"precision\", \"Normalized Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48069,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TNL2K","model_name":"ODTrack-L","metrics":{"AUC":"61.7"},"paper_url":"https://arxiv.org/abs/2401.01686v1","paper_title":"ODTrack: Online Dense Temporal Token Learning for Visual Tracking","paper_date":"2024-01-03","code_links":[{"title":"gxnu-zhonglab/odtrack","url":"https://github.com/gxnu-zhonglab/odtrack"}],"metrics_order":"[\"AUC\", \"precision\", \"Normalized Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48070,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TNL2K","model_name":"ARTrackV2-L","metrics":{"AUC":"61.6"},"paper_url":"https://arxiv.org/abs/2312.17133v3","paper_title":"ARTrackV2: Prompting Autoregressive Tracker Where to Look and How to Describe","paper_date":"2023-12-28","code_links":[{"title":"miv-xjtu/artrack","url":"https://github.com/miv-xjtu/artrack"}],"metrics_order":"[\"AUC\", \"precision\", \"Normalized Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48071,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TNL2K","model_name":"ODTrack-B","metrics":{"AUC":"60.9"},"paper_url":"https://arxiv.org/abs/2401.01686v1","paper_title":"ODTrack: Online Dense Temporal Token Learning for Visual Tracking","paper_date":"2024-01-03","code_links":[{"title":"gxnu-zhonglab/odtrack","url":"https://github.com/gxnu-zhonglab/odtrack"}],"metrics_order":"[\"AUC\", \"precision\", \"Normalized Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48072,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TNL2K","model_name":"RTracker-L","metrics":{"AUC":"60.6","precision":"63.7"},"paper_url":"https://arxiv.org/abs/2403.19242v1","paper_title":"RTracker: Recoverable Tracking via PN Tree Structured Memory","paper_date":"2024-03-28","code_links":[{"title":"norahgreen/rtracker","url":"https://github.com/norahgreen/rtracker"}],"metrics_order":"[\"AUC\", \"precision\", \"Normalized Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48073,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TNL2K","model_name":"ARTrack-L","metrics":{"AUC":"60.3"},"paper_url":"http://openaccess.thecvf.com//content/CVPR2023/html/Wei_Autoregressive_Visual_Tracking_CVPR_2023_paper.html","paper_title":"Autoregressive Visual Tracking","paper_date":"2023-01-01","code_links":[{"title":"miv-xjtu/artrack","url":"https://github.com/miv-xjtu/artrack"}],"metrics_order":"[\"AUC\", \"precision\", \"Normalized Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48074,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TNL2K","model_name":"SeqTrack-L384","metrics":{"AUC":"57.8"},"paper_url":"https://arxiv.org/abs/2304.14394v3","paper_title":"Unified Sequence-to-Sequence Learning for Single- and Multi-Modal Visual Object Tracking","paper_date":"2023-04-27","code_links":[{"title":"chenxin-dlut/seqtrackv2","url":"https://github.com/chenxin-dlut/seqtrackv2"}],"metrics_order":"[\"AUC\", \"precision\", \"Normalized Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48075,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TNL2K","model_name":"MixFormerV2-B","metrics":{"AUC":"57.4","precision":"58.4"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"AUC\", \"precision\", \"Normalized Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48076,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TNL2K","model_name":"DropTrack","metrics":{"AUC":"56.9","precision":"57.9"},"paper_url":"https://arxiv.org/abs/2304.00571v2","paper_title":"DropMAE: Masked Autoencoders with Spatial-Attention Dropout for Tracking Tasks","paper_date":"2023-04-02","code_links":[{"title":"jimmy-dq/dropmae","url":"https://github.com/jimmy-dq/dropmae"}],"metrics_order":"[\"AUC\", \"precision\", \"Normalized Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48077,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TNL2K","model_name":"AdaSwitcher","metrics":{"precision":"0.42|0.50|0.42"},"paper_url":"https://arxiv.org/abs/2103.16746v1","paper_title":"Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark","paper_date":"2021-03-31","code_links":[{"title":"wangxiao5791509/Single_Object_Tracking_Paper_List","url":"https://github.com/wangxiao5791509/Single_Object_Tracking_Paper_List"},{"title":"wangxiao5791509/TNL2K_evaluation_toolkit","url":"https://github.com/wangxiao5791509/TNL2K_evaluation_toolkit"}],"metrics_order":"[\"AUC\", \"precision\", \"Normalized Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143491,"task":"Visual Object Tracking","parent_task":null,"dataset":"TNL2K","model_name":"MCITrack-L384","metrics":{"AUC":"65.3"},"paper_url":"https://arxiv.org/abs/2412.11023v1","paper_title":"Exploring Enhanced Contextual Information for Video-Level Object Tracking","paper_date":"2024-12-15","code_links":[{"title":"kangben258/MCITrack","url":"https://github.com/kangben258/MCITrack"}],"metrics_order":"[\"AUC\", \"precision\", \"Normalized Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143492,"task":"Visual Object Tracking","parent_task":null,"dataset":"TNL2K","model_name":"SPMTrack-G","metrics":{"AUC":"64.7","Normalized Precision":"82.6","precision":"70.6"},"paper_url":"https://arxiv.org/abs/2503.18338v1","paper_title":"SPMTrack: Spatio-Temporal Parameter-Efficient Fine-Tuning with Mixture of Experts for Scalable Visual Tracking","paper_date":"2025-03-24","code_links":[{"title":"wenruicai/spmtrack","url":"https://github.com/wenruicai/spmtrack"}],"metrics_order":"[\"AUC\", \"precision\", \"Normalized Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143493,"task":"Visual Object Tracking","parent_task":null,"dataset":"TNL2K","model_name":"SPMTrack-L","metrics":{"AUC":"63.7","Normalized Precision":"81.5","precision":"69.2"},"paper_url":"https://arxiv.org/abs/2503.18338v1","paper_title":"SPMTrack: Spatio-Temporal Parameter-Efficient Fine-Tuning with Mixture of Experts for Scalable Visual Tracking","paper_date":"2025-03-24","code_links":[{"title":"wenruicai/spmtrack","url":"https://github.com/wenruicai/spmtrack"}],"metrics_order":"[\"AUC\", \"precision\", \"Normalized Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143494,"task":"Visual Object Tracking","parent_task":null,"dataset":"TNL2K","model_name":"MCITrack-B224","metrics":{"AUC":"62.9"},"paper_url":"https://arxiv.org/abs/2412.11023v1","paper_title":"Exploring Enhanced Contextual Information for Video-Level Object Tracking","paper_date":"2024-12-15","code_links":[{"title":"kangben258/MCITrack","url":"https://github.com/kangben258/MCITrack"}],"metrics_order":"[\"AUC\", \"precision\", \"Normalized Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143495,"task":"Visual Object Tracking","parent_task":null,"dataset":"TNL2K","model_name":"LoRAT-g-378","metrics":{"AUC":"62.7","precision":"67.8"},"paper_url":"https://arxiv.org/abs/2403.05231v2","paper_title":"Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performance","paper_date":"2024-03-08","code_links":[{"title":"litinglin/lorat","url":"https://github.com/litinglin/lorat"}],"metrics_order":"[\"AUC\", \"precision\", \"Normalized Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143496,"task":"Visual Object Tracking","parent_task":null,"dataset":"TNL2K","model_name":"LoRAT-L-378","metrics":{"AUC":"62.3","precision":"67.0"},"paper_url":"https://arxiv.org/abs/2403.05231v2","paper_title":"Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performance","paper_date":"2024-03-08","code_links":[{"title":"litinglin/lorat","url":"https://github.com/litinglin/lorat"}],"metrics_order":"[\"AUC\", \"precision\", \"Normalized Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143497,"task":"Visual Object Tracking","parent_task":null,"dataset":"TNL2K","model_name":"SPMTrack-B","metrics":{"AUC":"62.0","Normalized Precision":"79.7","precision":"66.7"},"paper_url":"https://arxiv.org/abs/2503.18338v1","paper_title":"SPMTrack: Spatio-Temporal Parameter-Efficient Fine-Tuning with Mixture of Experts for Scalable Visual Tracking","paper_date":"2025-03-24","code_links":[{"title":"wenruicai/spmtrack","url":"https://github.com/wenruicai/spmtrack"}],"metrics_order":"[\"AUC\", \"precision\", \"Normalized Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143498,"task":"Visual Object Tracking","parent_task":null,"dataset":"TNL2K","model_name":"ODTrack-L","metrics":{"AUC":"61.7"},"paper_url":"https://arxiv.org/abs/2401.01686v1","paper_title":"ODTrack: Online Dense Temporal Token Learning for Visual Tracking","paper_date":"2024-01-03","code_links":[{"title":"gxnu-zhonglab/odtrack","url":"https://github.com/gxnu-zhonglab/odtrack"}],"metrics_order":"[\"AUC\", \"precision\", \"Normalized Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143499,"task":"Visual Object Tracking","parent_task":null,"dataset":"TNL2K","model_name":"ARTrackV2-L","metrics":{"AUC":"61.6"},"paper_url":"https://arxiv.org/abs/2312.17133v3","paper_title":"ARTrackV2: Prompting Autoregressive Tracker Where to Look and How to Describe","paper_date":"2023-12-28","code_links":[{"title":"miv-xjtu/artrack","url":"https://github.com/miv-xjtu/artrack"}],"metrics_order":"[\"AUC\", \"precision\", \"Normalized Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143500,"task":"Visual Object Tracking","parent_task":null,"dataset":"TNL2K","model_name":"ODTrack-B","metrics":{"AUC":"60.9"},"paper_url":"https://arxiv.org/abs/2401.01686v1","paper_title":"ODTrack: Online Dense Temporal Token Learning for Visual Tracking","paper_date":"2024-01-03","code_links":[{"title":"gxnu-zhonglab/odtrack","url":"https://github.com/gxnu-zhonglab/odtrack"}],"metrics_order":"[\"AUC\", \"precision\", \"Normalized Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143501,"task":"Visual Object Tracking","parent_task":null,"dataset":"TNL2K","model_name":"RTracker-L","metrics":{"AUC":"60.6","precision":"63.7"},"paper_url":"https://arxiv.org/abs/2403.19242v1","paper_title":"RTracker: Recoverable Tracking via PN Tree Structured Memory","paper_date":"2024-03-28","code_links":[{"title":"norahgreen/rtracker","url":"https://github.com/norahgreen/rtracker"}],"metrics_order":"[\"AUC\", \"precision\", \"Normalized Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143502,"task":"Visual Object Tracking","parent_task":null,"dataset":"TNL2K","model_name":"ARTrack-L","metrics":{"AUC":"60.3"},"paper_url":"http://openaccess.thecvf.com//content/CVPR2023/html/Wei_Autoregressive_Visual_Tracking_CVPR_2023_paper.html","paper_title":"Autoregressive Visual Tracking","paper_date":"2023-01-01","code_links":[{"title":"miv-xjtu/artrack","url":"https://github.com/miv-xjtu/artrack"}],"metrics_order":"[\"AUC\", \"precision\", \"Normalized Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143503,"task":"Visual Object Tracking","parent_task":null,"dataset":"TNL2K","model_name":"SeqTrack-L384","metrics":{"AUC":"57.8"},"paper_url":"https://arxiv.org/abs/2304.14394v3","paper_title":"Unified Sequence-to-Sequence Learning for Single- and Multi-Modal Visual Object Tracking","paper_date":"2023-04-27","code_links":[{"title":"chenxin-dlut/seqtrackv2","url":"https://github.com/chenxin-dlut/seqtrackv2"}],"metrics_order":"[\"AUC\", \"precision\", \"Normalized Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143504,"task":"Visual Object Tracking","parent_task":null,"dataset":"TNL2K","model_name":"MixFormerV2-B","metrics":{"AUC":"57.4","precision":"58.4"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"AUC\", \"precision\", \"Normalized Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143505,"task":"Visual Object Tracking","parent_task":null,"dataset":"TNL2K","model_name":"DropTrack","metrics":{"AUC":"56.9","precision":"57.9"},"paper_url":"https://arxiv.org/abs/2304.00571v2","paper_title":"DropMAE: Masked Autoencoders with Spatial-Attention Dropout for Tracking Tasks","paper_date":"2023-04-02","code_links":[{"title":"jimmy-dq/dropmae","url":"https://github.com/jimmy-dq/dropmae"}],"metrics_order":"[\"AUC\", \"precision\", \"Normalized Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143506,"task":"Visual Object Tracking","parent_task":null,"dataset":"TNL2K","model_name":"AdaSwitcher","metrics":{"precision":"0.42|0.50|0.42"},"paper_url":"https://arxiv.org/abs/2103.16746v1","paper_title":"Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark","paper_date":"2021-03-31","code_links":[{"title":"wangxiao5791509/Single_Object_Tracking_Paper_List","url":"https://github.com/wangxiao5791509/Single_Object_Tracking_Paper_List"},{"title":"wangxiao5791509/TNL2K_evaluation_toolkit","url":"https://github.com/wangxiao5791509/TNL2K_evaluation_toolkit"}],"metrics_order":"[\"AUC\", \"precision\", \"Normalized Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]}]}