{"task":"Visual Object Tracking","dataset":"TrackingNet","metric_names":["Accuracy","Normalized Precision","Precision","Success Rate","AUC"],"rows":[{"id":48281,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TrackingNet","model_name":"MCITrack-L384","metrics":{"Accuracy":"87.9","Normalized Precision":"92.1","Precision":"89.2"},"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":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48282,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TrackingNet","model_name":"SPMTrack-G","metrics":{"Accuracy":"87.3","Normalized Precision":"91.4","Precision":"88.1"},"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":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48283,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TrackingNet","model_name":"SPMTrack-L","metrics":{"Accuracy":"86.9","Normalized Precision":"91","Precision":"87.2"},"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":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48284,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TrackingNet","model_name":"MCITrack-B224","metrics":{"Accuracy":"86.3","Normalized Precision":"90.9","Precision":"86.1"},"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":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48285,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TrackingNet","model_name":"ARTrackV2-L","metrics":{"Accuracy":"86.1","Normalized Precision":"90.4","Precision":"86.2"},"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":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48286,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TrackingNet","model_name":"MixViT-L(ConvMAE)","metrics":{"Accuracy":"86.1","Normalized Precision":"90.3","Precision":"86.0"},"paper_url":"https://arxiv.org/abs/2302.02814v2","paper_title":"MixFormer: End-to-End Tracking with Iterative Mixed Attention","paper_date":"2023-02-06","code_links":[{"title":"MCG-NJU/MixFormer","url":"https://github.com/MCG-NJU/MixFormer"}],"metrics_order":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48287,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TrackingNet","model_name":"SPMTrack-B","metrics":{"Accuracy":"86.1","Normalized Precision":"90.2","Precision":"85.6"},"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":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48288,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TrackingNet","model_name":"ODTrack-L","metrics":{"Accuracy":"86.1"},"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":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48289,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TrackingNet","model_name":"LoRAT-g-378","metrics":{"Accuracy":"86.0","Normalized Precision":"90.2","Precision":"86.1"},"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":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48290,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TrackingNet","model_name":"LoRAT-L-378","metrics":{"Accuracy":"85.6","Normalized Precision":"89.7","Precision":"85.4"},"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":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48291,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TrackingNet","model_name":"ARTrack-L","metrics":{"Accuracy":"85.6","Normalized Precision":"89.6","Precision":"86.0"},"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":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48292,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TrackingNet","model_name":"SeqTrack-L384","metrics":{"Accuracy":"85.5","Normalized Precision":"89.8","Precision":"85.8"},"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":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48293,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TrackingNet","model_name":"UNINEXT-H","metrics":{"Accuracy":"85.4","Normalized Precision":"89.0","Precision":"86.4"},"paper_url":"https://arxiv.org/abs/2303.06674v2","paper_title":"Universal Instance Perception as Object Discovery and Retrieval","paper_date":"2023-03-12","code_links":[{"title":"MasterBin-IIAU/UNINEXT","url":"https://github.com/MasterBin-IIAU/UNINEXT"}],"metrics_order":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48294,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TrackingNet","model_name":"SAMURAI-L","metrics":{"Accuracy":"85.3"},"paper_url":"https://arxiv.org/abs/2411.11922v2","paper_title":"SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory","paper_date":"2024-11-18","code_links":[{"title":"yangchris11/samurai","url":"https://github.com/yangchris11/samurai"}],"metrics_order":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48295,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TrackingNet","model_name":"ODTrack-B","metrics":{"Accuracy":"85.1"},"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":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48296,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TrackingNet","model_name":"TATrack-L","metrics":{"Accuracy":"85.0","Normalized Precision":"89.3","Precision":"84.5"},"paper_url":"https://arxiv.org/abs/2302.13840v1","paper_title":"Target-Aware Tracking with Long-term Context Attention","paper_date":"2023-02-27","code_links":[{"title":"hekaijie123/TATrack","url":"https://github.com/hekaijie123/TATrack"}],"metrics_order":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48297,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TrackingNet","model_name":"HIPTrack","metrics":{"Accuracy":"84.5","Normalized Precision":"89.1","Precision":"83.8"},"paper_url":"https://arxiv.org/abs/2311.02072v2","paper_title":"HIPTrack: Visual Tracking with Historical Prompts","paper_date":"2023-11-03","code_links":[{"title":"wenruicai/hiptrack","url":"https://github.com/wenruicai/hiptrack"}],"metrics_order":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48298,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TrackingNet","model_name":"SwinTrack-B-384","metrics":{"Accuracy":"84","Normalized Precision":"88.2","Precision":"83.2"},"paper_url":"https://arxiv.org/abs/2112.00995v3","paper_title":"SwinTrack: A Simple and Strong Baseline for Transformer Tracking","paper_date":"2021-12-02","code_links":[{"title":"litinglin/swintrack","url":"https://github.com/litinglin/swintrack"}],"metrics_order":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48299,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TrackingNet","model_name":"MixFormer-L","metrics":{"Accuracy":"83.9","Normalized Precision":"88.9","Precision":"83.1"},"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":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48300,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TrackingNet","model_name":"OSTrack-384","metrics":{"Accuracy":"83.9","Normalized Precision":"88.5","Precision":"83.2"},"paper_url":"https://arxiv.org/abs/2203.11991v4","paper_title":"Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework","paper_date":"2022-03-22","code_links":[{"title":"botaoye/ostrack","url":"https://github.com/botaoye/ostrack"}],"metrics_order":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48301,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TrackingNet","model_name":"NeighborTrack-OSTrack","metrics":{"Accuracy":"83.79","Normalized Precision":"88.30"},"paper_url":"https://arxiv.org/abs/2211.06663v3","paper_title":"NeighborTrack: Improving Single Object Tracking by Bipartite Matching with Neighbor Tracklets","paper_date":"2022-11-12","code_links":[{"title":"franktpmvu/NeighborTrack","url":"https://github.com/franktpmvu/NeighborTrack"}],"metrics_order":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48302,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TrackingNet","model_name":"MITS","metrics":{"Accuracy":"83.4","Normalized Precision":"88.9","Precision":"84.6"},"paper_url":"https://arxiv.org/abs/2308.13266v3","paper_title":"Integrating Boxes and Masks: A Multi-Object Framework for Unified Visual Tracking and Segmentation","paper_date":"2023-08-25","code_links":[{"title":"yoxu515/mits","url":"https://github.com/yoxu515/mits"}],"metrics_order":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48303,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TrackingNet","model_name":"MixFormerV2-B","metrics":{"Accuracy":"83.4","Normalized Precision":"88.1","Precision":"81.6"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48304,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TrackingNet","model_name":"Unicorn","metrics":{"Accuracy":"83","Normalized Precision":"86.4","Precision":"82.2"},"paper_url":"https://arxiv.org/abs/2207.07078v4","paper_title":"Towards Grand Unification of Object Tracking","paper_date":"2022-07-14","code_links":[{"title":"masterbin-iiau/unicorn","url":"https://github.com/masterbin-iiau/unicorn"}],"metrics_order":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48305,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TrackingNet","model_name":"SLT-TransT","metrics":{"Accuracy":"82.8","Normalized Precision":"87.5","Precision":"81.4"},"paper_url":"https://arxiv.org/abs/2208.05810v3","paper_title":"Towards Sequence-Level Training for Visual Tracking","paper_date":"2022-08-11","code_links":[{"title":"byminji/SLTtrack","url":"https://github.com/byminji/SLTtrack"},{"title":"wangxiao5791509/Tracking-with-Deep-Reinforcement-Learning","url":"https://github.com/wangxiao5791509/Tracking-with-Deep-Reinforcement-Learning"}],"metrics_order":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48306,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TrackingNet","model_name":"AiATrack","metrics":{"Accuracy":"82.7","Normalized Precision":"87.8","Precision":"80.4"},"paper_url":"https://arxiv.org/abs/2207.09603v2","paper_title":"AiATrack: Attention in Attention for Transformer Visual Tracking","paper_date":"2022-07-20","code_links":[{"title":"Little-Podi/AiATrack","url":"https://github.com/Little-Podi/AiATrack"}],"metrics_order":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48307,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TrackingNet","model_name":"STARK","metrics":{"Accuracy":"82.0","Normalized Precision":"86.9","Precision":"79.1"},"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":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48308,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TrackingNet","model_name":"Siam R-CNN","metrics":{"Accuracy":"81.2","Normalized Precision":"85.4","Precision":"80.0"},"paper_url":"https://arxiv.org/abs/1911.12836v2","paper_title":"Siam R-CNN: Visual Tracking by Re-Detection","paper_date":"2019-11-28","code_links":[{"title":"VisualComputingInstitute/SiamR-CNN","url":"https://github.com/VisualComputingInstitute/SiamR-CNN"}],"metrics_order":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48309,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TrackingNet","model_name":"TREG","metrics":{"Accuracy":"78.5","Normalized Precision":"83.8","Precision":"75"},"paper_url":"https://arxiv.org/abs/2104.00403v1","paper_title":"Target Transformed Regression for Accurate Tracking","paper_date":"2021-04-01","code_links":[{"title":"MCG-NJU/TREG","url":"https://github.com/MCG-NJU/TREG"}],"metrics_order":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48310,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TrackingNet","model_name":"SiamBAN-ACM","metrics":{"Accuracy":"75.3","Normalized Precision":"81.0","Precision":"71.2"},"paper_url":"https://arxiv.org/abs/2012.02776v2","paper_title":"Learning to Fuse Asymmetric Feature Maps in Siamese Trackers","paper_date":"2020-12-04","code_links":[{"title":"wencheng256/SiamBAN-ACM","url":"https://github.com/wencheng256/SiamBAN-ACM"}],"metrics_order":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48311,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TrackingNet","model_name":"SiamFC++","metrics":{"Accuracy":"74.5","Normalized Precision":"79.8","Precision":"68.5"},"paper_url":"https://arxiv.org/abs/1911.06188v4","paper_title":"SiamFC++: Towards Robust and Accurate Visual Tracking with Target Estimation Guidelines","paper_date":"2019-11-14","code_links":[{"title":"MegviiDetection/video_analyst","url":"https://github.com/MegviiDetection/video_analyst"},{"title":"ZekuiQin/SiamKPN","url":"https://github.com/ZekuiQin/SiamKPN"},{"title":"mingyuw/tracker_209as","url":"https://github.com/mingyuw/tracker_209as"},{"title":"code-implementation1/Code8","url":"https://github.com/code-implementation1/Code8/tree/main/SiamFC"},{"title":"2023-MindSpore-4/Code11","url":"https://github.com/2023-MindSpore-4/Code11/tree/main/SiamFC"},{"title":"2023-MindSpore-1/ms-code-216","url":"https://github.com/2023-MindSpore-1/ms-code-216/tree/main/SiamFC"}],"metrics_order":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48312,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TrackingNet","model_name":"DiMP-50","metrics":{"Accuracy":"74.0","Normalized Precision":"80.1"},"paper_url":"https://arxiv.org/abs/1904.07220v2","paper_title":"Learning Discriminative Model Prediction for Tracking","paper_date":"2019-04-15","code_links":[{"title":"visionml/pytracking","url":"https://github.com/visionml/pytracking"},{"title":"martin-danelljan/ECO","url":"https://github.com/martin-danelljan/ECO"}],"metrics_order":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48313,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TrackingNet","model_name":"ATOM","metrics":{"Accuracy":"70.34","Normalized Precision":"77.11","Precision":"64.84"},"paper_url":"http://arxiv.org/abs/1811.07628v2","paper_title":"ATOM: Accurate Tracking by Overlap Maximization","paper_date":"2018-11-19","code_links":[{"title":"visionml/pytracking","url":"https://github.com/visionml/pytracking"},{"title":"martin-danelljan/ECO","url":"https://github.com/martin-danelljan/ECO"},{"title":"martin-danelljan/Continuous-ConvOp","url":"https://github.com/martin-danelljan/Continuous-ConvOp"},{"title":"xuefeng-zhu5/cdaat","url":"https://github.com/xuefeng-zhu5/cdaat"}],"metrics_order":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48314,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TrackingNet","model_name":"SiamRPN++","metrics":{"Accuracy":"70","Normalized Precision":"79.98","Precision":"69.38"},"paper_url":"http://arxiv.org/abs/1812.11703v1","paper_title":"SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks","paper_date":"2018-12-31","code_links":[{"title":"STVIR/pysot","url":"https://github.com/STVIR/pysot"},{"title":"open-mmlab/mmtracking","url":"https://github.com/open-mmlab/mmtracking"},{"title":"pengboxiangshang/siamrpn","url":"https://github.com/pengboxiangshang/siamrpn"},{"title":"zllrunning/SiameseX.PyTorch","url":"https://github.com/zllrunning/SiameseX.PyTorch"},{"title":"shallowtoil/DROL","url":"https://github.com/shallowtoil/DROL"},{"title":"xingpingdong/CLNet-tracking","url":"https://github.com/xingpingdong/CLNet-tracking"},{"title":"lql-team/TSDM","url":"https://github.com/lql-team/TSDM"},{"title":"logiklesuraj/siamfcex","url":"https://github.com/logiklesuraj/siamfcex"},{"title":"2023-MindSpore-4/Code14","url":"https://github.com/2023-MindSpore-4/Code14/tree/main/siamRPN"},{"title":"2023-MindSpore-1/ms-code-216","url":"https://github.com/2023-MindSpore-1/ms-code-216/tree/main/siamRPN"},{"title":"2023-MindSpore-4/Code14","url":"https://github.com/2023-MindSpore-4/Code14/tree/main/SiamFC"},{"title":"logiklesuraj/SiamFC","url":"https://github.com/logiklesuraj/SiamFC"},{"title":"2023-MindSpore-4/Code11","url":"https://github.com/2023-MindSpore-4/Code11/tree/main/siamRPN"}],"metrics_order":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48315,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TrackingNet","model_name":"GFS-DCF","metrics":{"Accuracy":"60.9","Normalized Precision":"71.79","Precision":"56.57"},"paper_url":"https://arxiv.org/abs/1907.13242v2","paper_title":"Joint Group Feature Selection and Discriminative Filter Learning for Robust Visual Object Tracking","paper_date":"2019-07-30","code_links":[{"title":"XU-TIANYANG/GFS-DCF","url":"https://github.com/XU-TIANYANG/GFS-DCF"}],"metrics_order":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48316,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TrackingNet","model_name":"ECO","metrics":{"Accuracy":"56.13","Normalized Precision":"62.14","Precision":"48.86"},"paper_url":"http://arxiv.org/abs/1611.09224v2","paper_title":"ECO: Efficient Convolution Operators for Tracking","paper_date":"2016-11-28","code_links":[{"title":"martin-danelljan/ECO","url":"https://github.com/martin-danelljan/ECO"},{"title":"fengyang95/pyCFTrackers","url":"https://github.com/fengyang95/pyCFTrackers"},{"title":"MindSpore-MS-Code2/code0","url":"https://github.com/MindSpore-MS-Code2/code0/tree/main/ecolite"},{"title":"2023-MindSpore-1/ms-code-212","url":"https://github.com/2023-MindSpore-1/ms-code-212/tree/main/ecolite"},{"title":"2023-MindSpore-4/Code3","url":"https://github.com/2023-MindSpore-4/Code3/tree/main/ecolite"}],"metrics_order":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48317,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TrackingNet","model_name":"STAPLE_CA","metrics":{"Accuracy":"53.59","Normalized Precision":"60.84","Precision":"46.72"},"paper_url":"http://arxiv.org/abs/1512.01355v2","paper_title":"Staple: Complementary Learners for Real-Time Tracking","paper_date":"2015-12-04","code_links":[{"title":"fengyang95/pyCFTrackers","url":"https://github.com/fengyang95/pyCFTrackers"},{"title":"xuduo35/STAPLE","url":"https://github.com/xuduo35/STAPLE"},{"title":"Superlee506/Correlation_Filtering_Tracking_Lib","url":"https://github.com/Superlee506/Correlation_Filtering_Tracking_Lib"}],"metrics_order":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48318,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TrackingNet","model_name":"DropTrack","metrics":{"AUC":"0.841","Normalized Precision":"88.9"},"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":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48319,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TrackingNet","model_name":"DiMP-NCE+","metrics":{"AUC":"0.787","Normalized Precision":"83.7","Precision":"73.7","Success Rate":"0.787"},"paper_url":"https://arxiv.org/abs/2005.01698v2","paper_title":"How to Train Your Energy-Based Model for Regression","paper_date":"2020-05-04","code_links":[{"title":"fregu856/ebms_regression","url":"https://github.com/fregu856/ebms_regression"},{"title":"soran-ghaderi/torchebm","url":"https://github.com/soran-ghaderi/torchebm"}],"metrics_order":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48320,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"TrackingNet","model_name":"ATOM(Resnet18)+EnergyRegression","metrics":{"Normalized Precision":"80.1","Precision":"69.7","Success Rate":"74.5"},"paper_url":"https://arxiv.org/abs/1909.12297v4","paper_title":"Energy-Based Models for Deep Probabilistic Regression","paper_date":"2019-09-26","code_links":[{"title":"fregu856/ebms_regression","url":"https://github.com/fregu856/ebms_regression"},{"title":"soran-ghaderi/torchebm","url":"https://github.com/soran-ghaderi/torchebm"}],"metrics_order":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143710,"task":"Visual Object Tracking","parent_task":null,"dataset":"TrackingNet","model_name":"MCITrack-L384","metrics":{"Accuracy":"87.9","Normalized Precision":"92.1","Precision":"89.2"},"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":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143711,"task":"Visual Object Tracking","parent_task":null,"dataset":"TrackingNet","model_name":"SPMTrack-G","metrics":{"Accuracy":"87.3","Normalized Precision":"91.4","Precision":"88.1"},"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":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143712,"task":"Visual Object Tracking","parent_task":null,"dataset":"TrackingNet","model_name":"SPMTrack-L","metrics":{"Accuracy":"86.9","Normalized Precision":"91","Precision":"87.2"},"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":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143713,"task":"Visual Object Tracking","parent_task":null,"dataset":"TrackingNet","model_name":"MCITrack-B224","metrics":{"Accuracy":"86.3","Normalized Precision":"90.9","Precision":"86.1"},"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":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143714,"task":"Visual Object Tracking","parent_task":null,"dataset":"TrackingNet","model_name":"ARTrackV2-L","metrics":{"Accuracy":"86.1","Normalized Precision":"90.4","Precision":"86.2"},"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":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143715,"task":"Visual Object Tracking","parent_task":null,"dataset":"TrackingNet","model_name":"MixViT-L(ConvMAE)","metrics":{"Accuracy":"86.1","Normalized Precision":"90.3","Precision":"86.0"},"paper_url":"https://arxiv.org/abs/2302.02814v2","paper_title":"MixFormer: End-to-End Tracking with Iterative Mixed Attention","paper_date":"2023-02-06","code_links":[{"title":"MCG-NJU/MixFormer","url":"https://github.com/MCG-NJU/MixFormer"}],"metrics_order":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143716,"task":"Visual Object Tracking","parent_task":null,"dataset":"TrackingNet","model_name":"SPMTrack-B","metrics":{"Accuracy":"86.1","Normalized Precision":"90.2","Precision":"85.6"},"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":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143717,"task":"Visual Object Tracking","parent_task":null,"dataset":"TrackingNet","model_name":"ODTrack-L","metrics":{"Accuracy":"86.1"},"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":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143718,"task":"Visual Object Tracking","parent_task":null,"dataset":"TrackingNet","model_name":"LoRAT-g-378","metrics":{"Accuracy":"86.0","Normalized Precision":"90.2","Precision":"86.1"},"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":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143719,"task":"Visual Object Tracking","parent_task":null,"dataset":"TrackingNet","model_name":"LoRAT-L-378","metrics":{"Accuracy":"85.6","Normalized Precision":"89.7","Precision":"85.4"},"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":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143720,"task":"Visual Object Tracking","parent_task":null,"dataset":"TrackingNet","model_name":"ARTrack-L","metrics":{"Accuracy":"85.6","Normalized Precision":"89.6","Precision":"86.0"},"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":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143721,"task":"Visual Object Tracking","parent_task":null,"dataset":"TrackingNet","model_name":"SeqTrack-L384","metrics":{"Accuracy":"85.5","Normalized Precision":"89.8","Precision":"85.8"},"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":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143722,"task":"Visual Object Tracking","parent_task":null,"dataset":"TrackingNet","model_name":"UNINEXT-H","metrics":{"Accuracy":"85.4","Normalized Precision":"89.0","Precision":"86.4"},"paper_url":"https://arxiv.org/abs/2303.06674v2","paper_title":"Universal Instance Perception as Object Discovery and Retrieval","paper_date":"2023-03-12","code_links":[{"title":"MasterBin-IIAU/UNINEXT","url":"https://github.com/MasterBin-IIAU/UNINEXT"}],"metrics_order":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143723,"task":"Visual Object Tracking","parent_task":null,"dataset":"TrackingNet","model_name":"SAMURAI-L","metrics":{"Accuracy":"85.3"},"paper_url":"https://arxiv.org/abs/2411.11922v2","paper_title":"SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory","paper_date":"2024-11-18","code_links":[{"title":"yangchris11/samurai","url":"https://github.com/yangchris11/samurai"}],"metrics_order":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143724,"task":"Visual Object Tracking","parent_task":null,"dataset":"TrackingNet","model_name":"ODTrack-B","metrics":{"Accuracy":"85.1"},"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":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143725,"task":"Visual Object Tracking","parent_task":null,"dataset":"TrackingNet","model_name":"TATrack-L","metrics":{"Accuracy":"85.0","Normalized Precision":"89.3","Precision":"84.5"},"paper_url":"https://arxiv.org/abs/2302.13840v1","paper_title":"Target-Aware Tracking with Long-term Context Attention","paper_date":"2023-02-27","code_links":[{"title":"hekaijie123/TATrack","url":"https://github.com/hekaijie123/TATrack"}],"metrics_order":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143726,"task":"Visual Object Tracking","parent_task":null,"dataset":"TrackingNet","model_name":"HIPTrack","metrics":{"Accuracy":"84.5","Normalized Precision":"89.1","Precision":"83.8"},"paper_url":"https://arxiv.org/abs/2311.02072v2","paper_title":"HIPTrack: Visual Tracking with Historical Prompts","paper_date":"2023-11-03","code_links":[{"title":"wenruicai/hiptrack","url":"https://github.com/wenruicai/hiptrack"}],"metrics_order":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143727,"task":"Visual Object Tracking","parent_task":null,"dataset":"TrackingNet","model_name":"SwinTrack-B-384","metrics":{"Accuracy":"84","Normalized Precision":"88.2","Precision":"83.2"},"paper_url":"https://arxiv.org/abs/2112.00995v3","paper_title":"SwinTrack: A Simple and Strong Baseline for Transformer Tracking","paper_date":"2021-12-02","code_links":[{"title":"litinglin/swintrack","url":"https://github.com/litinglin/swintrack"}],"metrics_order":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143728,"task":"Visual Object Tracking","parent_task":null,"dataset":"TrackingNet","model_name":"MixFormer-L","metrics":{"Accuracy":"83.9","Normalized Precision":"88.9","Precision":"83.1"},"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":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143729,"task":"Visual Object Tracking","parent_task":null,"dataset":"TrackingNet","model_name":"OSTrack-384","metrics":{"Accuracy":"83.9","Normalized Precision":"88.5","Precision":"83.2"},"paper_url":"https://arxiv.org/abs/2203.11991v4","paper_title":"Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework","paper_date":"2022-03-22","code_links":[{"title":"botaoye/ostrack","url":"https://github.com/botaoye/ostrack"}],"metrics_order":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143730,"task":"Visual Object Tracking","parent_task":null,"dataset":"TrackingNet","model_name":"NeighborTrack-OSTrack","metrics":{"Accuracy":"83.79","Normalized Precision":"88.30"},"paper_url":"https://arxiv.org/abs/2211.06663v3","paper_title":"NeighborTrack: Improving Single Object Tracking by Bipartite Matching with Neighbor Tracklets","paper_date":"2022-11-12","code_links":[{"title":"franktpmvu/NeighborTrack","url":"https://github.com/franktpmvu/NeighborTrack"}],"metrics_order":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143731,"task":"Visual Object Tracking","parent_task":null,"dataset":"TrackingNet","model_name":"MITS","metrics":{"Accuracy":"83.4","Normalized Precision":"88.9","Precision":"84.6"},"paper_url":"https://arxiv.org/abs/2308.13266v3","paper_title":"Integrating Boxes and Masks: A Multi-Object Framework for Unified Visual Tracking and Segmentation","paper_date":"2023-08-25","code_links":[{"title":"yoxu515/mits","url":"https://github.com/yoxu515/mits"}],"metrics_order":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143732,"task":"Visual Object Tracking","parent_task":null,"dataset":"TrackingNet","model_name":"MixFormerV2-B","metrics":{"Accuracy":"83.4","Normalized Precision":"88.1","Precision":"81.6"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143733,"task":"Visual Object Tracking","parent_task":null,"dataset":"TrackingNet","model_name":"Unicorn","metrics":{"Accuracy":"83","Normalized Precision":"86.4","Precision":"82.2"},"paper_url":"https://arxiv.org/abs/2207.07078v4","paper_title":"Towards Grand Unification of Object Tracking","paper_date":"2022-07-14","code_links":[{"title":"masterbin-iiau/unicorn","url":"https://github.com/masterbin-iiau/unicorn"}],"metrics_order":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143734,"task":"Visual Object Tracking","parent_task":null,"dataset":"TrackingNet","model_name":"SLT-TransT","metrics":{"Accuracy":"82.8","Normalized Precision":"87.5","Precision":"81.4"},"paper_url":"https://arxiv.org/abs/2208.05810v3","paper_title":"Towards Sequence-Level Training for Visual Tracking","paper_date":"2022-08-11","code_links":[{"title":"byminji/SLTtrack","url":"https://github.com/byminji/SLTtrack"},{"title":"wangxiao5791509/Tracking-with-Deep-Reinforcement-Learning","url":"https://github.com/wangxiao5791509/Tracking-with-Deep-Reinforcement-Learning"}],"metrics_order":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143735,"task":"Visual Object Tracking","parent_task":null,"dataset":"TrackingNet","model_name":"AiATrack","metrics":{"Accuracy":"82.7","Normalized Precision":"87.8","Precision":"80.4"},"paper_url":"https://arxiv.org/abs/2207.09603v2","paper_title":"AiATrack: Attention in Attention for Transformer Visual Tracking","paper_date":"2022-07-20","code_links":[{"title":"Little-Podi/AiATrack","url":"https://github.com/Little-Podi/AiATrack"}],"metrics_order":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143736,"task":"Visual Object Tracking","parent_task":null,"dataset":"TrackingNet","model_name":"STARK","metrics":{"Accuracy":"82.0","Normalized Precision":"86.9","Precision":"79.1"},"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":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143737,"task":"Visual Object Tracking","parent_task":null,"dataset":"TrackingNet","model_name":"Siam R-CNN","metrics":{"Accuracy":"81.2","Normalized Precision":"85.4","Precision":"80.0"},"paper_url":"https://arxiv.org/abs/1911.12836v2","paper_title":"Siam R-CNN: Visual Tracking by Re-Detection","paper_date":"2019-11-28","code_links":[{"title":"VisualComputingInstitute/SiamR-CNN","url":"https://github.com/VisualComputingInstitute/SiamR-CNN"}],"metrics_order":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143738,"task":"Visual Object Tracking","parent_task":null,"dataset":"TrackingNet","model_name":"TREG","metrics":{"Accuracy":"78.5","Normalized Precision":"83.8","Precision":"75"},"paper_url":"https://arxiv.org/abs/2104.00403v1","paper_title":"Target Transformed Regression for Accurate Tracking","paper_date":"2021-04-01","code_links":[{"title":"MCG-NJU/TREG","url":"https://github.com/MCG-NJU/TREG"}],"metrics_order":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143739,"task":"Visual Object Tracking","parent_task":null,"dataset":"TrackingNet","model_name":"SiamBAN-ACM","metrics":{"Accuracy":"75.3","Normalized Precision":"81.0","Precision":"71.2"},"paper_url":"https://arxiv.org/abs/2012.02776v2","paper_title":"Learning to Fuse Asymmetric Feature Maps in Siamese Trackers","paper_date":"2020-12-04","code_links":[{"title":"wencheng256/SiamBAN-ACM","url":"https://github.com/wencheng256/SiamBAN-ACM"}],"metrics_order":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143740,"task":"Visual Object Tracking","parent_task":null,"dataset":"TrackingNet","model_name":"SiamFC++","metrics":{"Accuracy":"74.5","Normalized Precision":"79.8","Precision":"68.5"},"paper_url":"https://arxiv.org/abs/1911.06188v4","paper_title":"SiamFC++: Towards Robust and Accurate Visual Tracking with Target Estimation Guidelines","paper_date":"2019-11-14","code_links":[{"title":"MegviiDetection/video_analyst","url":"https://github.com/MegviiDetection/video_analyst"},{"title":"ZekuiQin/SiamKPN","url":"https://github.com/ZekuiQin/SiamKPN"},{"title":"mingyuw/tracker_209as","url":"https://github.com/mingyuw/tracker_209as"},{"title":"code-implementation1/Code8","url":"https://github.com/code-implementation1/Code8/tree/main/SiamFC"},{"title":"2023-MindSpore-4/Code11","url":"https://github.com/2023-MindSpore-4/Code11/tree/main/SiamFC"},{"title":"2023-MindSpore-1/ms-code-216","url":"https://github.com/2023-MindSpore-1/ms-code-216/tree/main/SiamFC"}],"metrics_order":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143741,"task":"Visual Object Tracking","parent_task":null,"dataset":"TrackingNet","model_name":"DiMP-50","metrics":{"Accuracy":"74.0","Normalized Precision":"80.1"},"paper_url":"https://arxiv.org/abs/1904.07220v2","paper_title":"Learning Discriminative Model Prediction for Tracking","paper_date":"2019-04-15","code_links":[{"title":"visionml/pytracking","url":"https://github.com/visionml/pytracking"},{"title":"martin-danelljan/ECO","url":"https://github.com/martin-danelljan/ECO"}],"metrics_order":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143742,"task":"Visual Object Tracking","parent_task":null,"dataset":"TrackingNet","model_name":"ATOM","metrics":{"Accuracy":"70.34","Normalized Precision":"77.11","Precision":"64.84"},"paper_url":"http://arxiv.org/abs/1811.07628v2","paper_title":"ATOM: Accurate Tracking by Overlap Maximization","paper_date":"2018-11-19","code_links":[{"title":"visionml/pytracking","url":"https://github.com/visionml/pytracking"},{"title":"martin-danelljan/ECO","url":"https://github.com/martin-danelljan/ECO"},{"title":"martin-danelljan/Continuous-ConvOp","url":"https://github.com/martin-danelljan/Continuous-ConvOp"},{"title":"xuefeng-zhu5/cdaat","url":"https://github.com/xuefeng-zhu5/cdaat"}],"metrics_order":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143743,"task":"Visual Object Tracking","parent_task":null,"dataset":"TrackingNet","model_name":"SiamRPN++","metrics":{"Accuracy":"70","Normalized Precision":"79.98","Precision":"69.38"},"paper_url":"http://arxiv.org/abs/1812.11703v1","paper_title":"SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks","paper_date":"2018-12-31","code_links":[{"title":"STVIR/pysot","url":"https://github.com/STVIR/pysot"},{"title":"open-mmlab/mmtracking","url":"https://github.com/open-mmlab/mmtracking"},{"title":"pengboxiangshang/siamrpn","url":"https://github.com/pengboxiangshang/siamrpn"},{"title":"zllrunning/SiameseX.PyTorch","url":"https://github.com/zllrunning/SiameseX.PyTorch"},{"title":"shallowtoil/DROL","url":"https://github.com/shallowtoil/DROL"},{"title":"xingpingdong/CLNet-tracking","url":"https://github.com/xingpingdong/CLNet-tracking"},{"title":"lql-team/TSDM","url":"https://github.com/lql-team/TSDM"},{"title":"logiklesuraj/siamfcex","url":"https://github.com/logiklesuraj/siamfcex"},{"title":"2023-MindSpore-4/Code14","url":"https://github.com/2023-MindSpore-4/Code14/tree/main/siamRPN"},{"title":"2023-MindSpore-1/ms-code-216","url":"https://github.com/2023-MindSpore-1/ms-code-216/tree/main/siamRPN"},{"title":"2023-MindSpore-4/Code14","url":"https://github.com/2023-MindSpore-4/Code14/tree/main/SiamFC"},{"title":"logiklesuraj/SiamFC","url":"https://github.com/logiklesuraj/SiamFC"},{"title":"2023-MindSpore-4/Code11","url":"https://github.com/2023-MindSpore-4/Code11/tree/main/siamRPN"}],"metrics_order":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143744,"task":"Visual Object Tracking","parent_task":null,"dataset":"TrackingNet","model_name":"GFS-DCF","metrics":{"Accuracy":"60.9","Normalized Precision":"71.79","Precision":"56.57"},"paper_url":"https://arxiv.org/abs/1907.13242v2","paper_title":"Joint Group Feature Selection and Discriminative Filter Learning for Robust Visual Object Tracking","paper_date":"2019-07-30","code_links":[{"title":"XU-TIANYANG/GFS-DCF","url":"https://github.com/XU-TIANYANG/GFS-DCF"}],"metrics_order":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143745,"task":"Visual Object Tracking","parent_task":null,"dataset":"TrackingNet","model_name":"ECO","metrics":{"Accuracy":"56.13","Normalized Precision":"62.14","Precision":"48.86"},"paper_url":"http://arxiv.org/abs/1611.09224v2","paper_title":"ECO: Efficient Convolution Operators for Tracking","paper_date":"2016-11-28","code_links":[{"title":"martin-danelljan/ECO","url":"https://github.com/martin-danelljan/ECO"},{"title":"fengyang95/pyCFTrackers","url":"https://github.com/fengyang95/pyCFTrackers"},{"title":"MindSpore-MS-Code2/code0","url":"https://github.com/MindSpore-MS-Code2/code0/tree/main/ecolite"},{"title":"2023-MindSpore-1/ms-code-212","url":"https://github.com/2023-MindSpore-1/ms-code-212/tree/main/ecolite"},{"title":"2023-MindSpore-4/Code3","url":"https://github.com/2023-MindSpore-4/Code3/tree/main/ecolite"}],"metrics_order":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143746,"task":"Visual Object Tracking","parent_task":null,"dataset":"TrackingNet","model_name":"STAPLE_CA","metrics":{"Accuracy":"53.59","Normalized Precision":"60.84","Precision":"46.72"},"paper_url":"http://arxiv.org/abs/1512.01355v2","paper_title":"Staple: Complementary Learners for Real-Time Tracking","paper_date":"2015-12-04","code_links":[{"title":"fengyang95/pyCFTrackers","url":"https://github.com/fengyang95/pyCFTrackers"},{"title":"xuduo35/STAPLE","url":"https://github.com/xuduo35/STAPLE"},{"title":"Superlee506/Correlation_Filtering_Tracking_Lib","url":"https://github.com/Superlee506/Correlation_Filtering_Tracking_Lib"}],"metrics_order":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143747,"task":"Visual Object Tracking","parent_task":null,"dataset":"TrackingNet","model_name":"DropTrack","metrics":{"AUC":"0.841","Normalized Precision":"88.9"},"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":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143748,"task":"Visual Object Tracking","parent_task":null,"dataset":"TrackingNet","model_name":"DiMP-NCE+","metrics":{"AUC":"0.787","Normalized Precision":"83.7","Precision":"73.7","Success Rate":"0.787"},"paper_url":"https://arxiv.org/abs/2005.01698v2","paper_title":"How to Train Your Energy-Based Model for Regression","paper_date":"2020-05-04","code_links":[{"title":"fregu856/ebms_regression","url":"https://github.com/fregu856/ebms_regression"},{"title":"soran-ghaderi/torchebm","url":"https://github.com/soran-ghaderi/torchebm"}],"metrics_order":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143749,"task":"Visual Object Tracking","parent_task":null,"dataset":"TrackingNet","model_name":"ATOM(Resnet18)+EnergyRegression","metrics":{"Normalized Precision":"80.1","Precision":"69.7","Success Rate":"74.5"},"paper_url":"https://arxiv.org/abs/1909.12297v4","paper_title":"Energy-Based Models for Deep Probabilistic Regression","paper_date":"2019-09-26","code_links":[{"title":"fregu856/ebms_regression","url":"https://github.com/fregu856/ebms_regression"},{"title":"soran-ghaderi/torchebm","url":"https://github.com/soran-ghaderi/torchebm"}],"metrics_order":"[\"Accuracy\", \"Normalized Precision\", \"Precision\", \"Success Rate\", \"AUC\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]}]}