{"task":"Visual Object Tracking","dataset":"LaSOT","metric_names":["AUC","Normalized Precision","Precision"],"rows":[{"id":48121,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"LaSOT","model_name":"SPMTrack-G","metrics":{"AUC":"77.4","Normalized Precision":"86.6","Precision":"85"},"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\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48122,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"LaSOT","model_name":"SPMTrack-L","metrics":{"AUC":"76.8","Normalized Precision":"85.9","Precision":"84"},"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\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48123,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"LaSOT","model_name":"MCITrack-L384","metrics":{"AUC":"76.6","Normalized Precision":"86.1","Precision":"85.0"},"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\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48124,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"LaSOT","model_name":"LoRAT-g-378","metrics":{"AUC":"76.2","Normalized Precision":"85.3","Precision":"83.5"},"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\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48125,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"LaSOT","model_name":"MCITrack-B224","metrics":{"AUC":"75.3","Normalized Precision":"85.6","Precision":"83.3"},"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\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48126,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"LaSOT","model_name":"LoRAT-L-378","metrics":{"AUC":"75.1","Normalized Precision":"84.1","Precision":"82.0"},"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\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48127,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"LaSOT","model_name":"DAM4SAM","metrics":{"AUC":"75.1"},"paper_url":"https://arxiv.org/abs/2411.17576v2","paper_title":"A Distractor-Aware Memory for Visual Object Tracking with SAM2","paper_date":"2024-11-26","code_links":[{"title":"jovanavidenovic/dam4sam","url":"https://github.com/jovanavidenovic/dam4sam"}],"metrics_order":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48128,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"LaSOT","model_name":"SPMTrack-B","metrics":{"AUC":"74.9","Normalized Precision":"84","Precision":"81.7"},"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\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48129,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"LaSOT","model_name":"RTracker-L","metrics":{"AUC":"74.7","Normalized Precision":"84.5"},"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\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48130,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"LaSOT","model_name":"SAMURAI-L","metrics":{"AUC":"74.2","Normalized Precision":"82.7","Precision":"80.2"},"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":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48131,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"LaSOT","model_name":"ODTrack-L","metrics":{"AUC":"74.0"},"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\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48132,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"LaSOT","model_name":"ARTrackV2-L","metrics":{"AUC":"73.6","Normalized Precision":"82.8","Precision":"81.1"},"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\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48133,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"LaSOT","model_name":"PiVOT-L","metrics":{"AUC":"73.4","Normalized Precision":"84.7","Precision":"82.1"},"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":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48134,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"LaSOT","model_name":"MixViT-L(ConvMAE)","metrics":{"AUC":"73.3","Normalized Precision":"82.8","Precision":"80.3"},"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":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48135,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"LaSOT","model_name":"ODTrack-B","metrics":{"AUC":"73.2"},"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\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48136,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"LaSOT","model_name":"ARTrack-L","metrics":{"AUC":"73.1","Normalized Precision":"82.2","Precision":"80.3"},"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\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48137,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"LaSOT","model_name":"HIPTrack","metrics":{"AUC":"72.7","Normalized Precision":"82.9","Precision":"79.5"},"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":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48138,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"LaSOT","model_name":"SeqTrack-L384","metrics":{"AUC":"72.5","Normalized Precision":"81.5","Precision":"79.3"},"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\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48139,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"LaSOT","model_name":"UNINEXT-L","metrics":{"AUC":"72.4","Normalized Precision":"80.7","Precision":"78.9"},"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":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48140,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"LaSOT","model_name":"NeighborTrack-OSTrack","metrics":{"AUC":"72.2","Normalized Precision":"81.8","Precision":"78.0"},"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":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48141,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"LaSOT","model_name":"UNINEXT-H","metrics":{"AUC":"72.2","Normalized Precision":"80.8","Precision":"79.4"},"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":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48142,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"LaSOT","model_name":"MITS","metrics":{"AUC":"72.0","Normalized Precision":"80.1","Precision":"78.5"},"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":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48143,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"LaSOT","model_name":"DropTrack","metrics":{"AUC":"71.8","Normalized Precision":"81.8","Precision":"78.1"},"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\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48144,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"LaSOT","model_name":"OSTrack-384","metrics":{"AUC":"71.1","Normalized Precision":"81.1","Precision":"77.6"},"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":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48145,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"LaSOT","model_name":"TATrack-L","metrics":{"AUC":"71.1","Normalized Precision":"79.1","Precision":"76.1"},"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":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48146,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"LaSOT","model_name":"SwinV2-L 1K-MIM","metrics":{"AUC":"70.7"},"paper_url":"https://arxiv.org/abs/2205.13543v2","paper_title":"Revealing the Dark Secrets of Masked Image Modeling","paper_date":"2022-05-26","code_links":[{"title":"SwinTransformer/MIM-Depth-Estimation","url":"https://github.com/SwinTransformer/MIM-Depth-Estimation"}],"metrics_order":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48147,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"LaSOT","model_name":"MixFormerV2-B","metrics":{"AUC":"70.6","Normalized Precision":"80.8","Precision":"76.2"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48148,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"LaSOT","model_name":"LoReTrack","metrics":{"AUC":"70.3","Precision":"76.2"},"paper_url":"https://arxiv.org/abs/2405.17660v1","paper_title":"LoReTrack: Efficient and Accurate Low-Resolution Transformer Tracking","paper_date":"2024-05-27","code_links":[{"title":"ShaohuaDong2021/LoReTrack","url":"https://github.com/ShaohuaDong2021/LoReTrack"}],"metrics_order":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48149,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"LaSOT","model_name":"SwinTrack-B-384","metrics":{"AUC":"70.2","Normalized Precision":"78.4","Precision":"75.3"},"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":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48150,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"LaSOT","model_name":"MixFormer-L","metrics":{"AUC":"70.1","Normalized Precision":"79.9","Precision":"76.3"},"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":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48151,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"LaSOT","model_name":"SwinV2-B 1K-MIM","metrics":{"AUC":"70"},"paper_url":"https://arxiv.org/abs/2205.13543v2","paper_title":"Revealing the Dark Secrets of Masked Image Modeling","paper_date":"2022-05-26","code_links":[{"title":"SwinTransformer/MIM-Depth-Estimation","url":"https://github.com/SwinTransformer/MIM-Depth-Estimation"}],"metrics_order":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48152,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"LaSOT","model_name":"AiATrack","metrics":{"AUC":"69.0","Normalized Precision":"79.4","Precision":"73.8"},"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":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48153,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"LaSOT","model_name":"Unicorn","metrics":{"AUC":"68.5","Normalized Precision":"76.6","Precision":"74.1"},"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":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48154,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"LaSOT","model_name":"KeepTrack","metrics":{"AUC":"67.1","Normalized Precision":"77.2","Precision":"70.2"},"paper_url":"https://arxiv.org/abs/2103.16556v2","paper_title":"Learning Target Candidate Association to Keep Track of What Not to Track","paper_date":"2021-03-30","code_links":[{"title":"visionml/pytracking","url":"https://github.com/visionml/pytracking"}],"metrics_order":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48155,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"LaSOT","model_name":"STARK","metrics":{"AUC":"67.1","Normalized Precision":"77.0"},"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":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48156,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"LaSOT","model_name":"SLT-TransT","metrics":{"AUC":"66.8","Normalized Precision":"75.5"},"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":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48157,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"LaSOT","model_name":"TransT","metrics":{"AUC":"64.9","Normalized Precision":"73.8","Precision":"69.0"},"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":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48158,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"LaSOT","model_name":"Siam R-CNN","metrics":{"AUC":"64.8","Normalized Precision":"72.2"},"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":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48159,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"LaSOT","model_name":"TrDiMP","metrics":{"AUC":"63.7","Precision":"61.4"},"paper_url":"https://arxiv.org/abs/2103.11681v2","paper_title":"Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking","paper_date":"2021-03-22","code_links":[{"title":"594422814/TransformerTrack","url":"https://github.com/594422814/TransformerTrack"}],"metrics_order":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48160,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"LaSOT","model_name":"DiMP-NCE+","metrics":{"AUC":"63.7"},"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":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48161,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"LaSOT","model_name":"TRASFUST","metrics":{"AUC":"57.6"},"paper_url":"https://arxiv.org/abs/2007.04108v2","paper_title":"Tracking-by-Trackers with a Distilled and Reinforced Model","paper_date":"2020-07-08","code_links":[{"title":"dontfollowmeimcrazy/vot-kd-rl","url":"https://github.com/dontfollowmeimcrazy/vot-kd-rl"}],"metrics_order":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48162,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"LaSOT","model_name":"SiamBAN-ACM","metrics":{"AUC":"57.2","Normalized Precision":"65.3","Precision":"58.7"},"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":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48163,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"LaSOT","model_name":"DiMP","metrics":{"AUC":"56.8","Normalized Precision":"65.0","Precision":"56.7"},"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":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48164,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"LaSOT","model_name":"ATOM","metrics":{"AUC":"51.4","Normalized Precision":"57.6","Precision":"50.5"},"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":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48165,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"LaSOT","model_name":"DiMP-50","metrics":{"Precision":"68.7"},"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":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48166,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"LaSOT","model_name":"ToMP","metrics":{"Precision":"67.1"},"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":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143550,"task":"Visual Object Tracking","parent_task":null,"dataset":"LaSOT","model_name":"SPMTrack-G","metrics":{"AUC":"77.4","Normalized Precision":"86.6","Precision":"85"},"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\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143551,"task":"Visual Object Tracking","parent_task":null,"dataset":"LaSOT","model_name":"SPMTrack-L","metrics":{"AUC":"76.8","Normalized Precision":"85.9","Precision":"84"},"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\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143552,"task":"Visual Object Tracking","parent_task":null,"dataset":"LaSOT","model_name":"MCITrack-L384","metrics":{"AUC":"76.6","Normalized Precision":"86.1","Precision":"85.0"},"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\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143553,"task":"Visual Object Tracking","parent_task":null,"dataset":"LaSOT","model_name":"LoRAT-g-378","metrics":{"AUC":"76.2","Normalized Precision":"85.3","Precision":"83.5"},"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\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143554,"task":"Visual Object Tracking","parent_task":null,"dataset":"LaSOT","model_name":"MCITrack-B224","metrics":{"AUC":"75.3","Normalized Precision":"85.6","Precision":"83.3"},"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\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143555,"task":"Visual Object Tracking","parent_task":null,"dataset":"LaSOT","model_name":"LoRAT-L-378","metrics":{"AUC":"75.1","Normalized Precision":"84.1","Precision":"82.0"},"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\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143556,"task":"Visual Object Tracking","parent_task":null,"dataset":"LaSOT","model_name":"DAM4SAM","metrics":{"AUC":"75.1"},"paper_url":"https://arxiv.org/abs/2411.17576v2","paper_title":"A Distractor-Aware Memory for Visual Object Tracking with SAM2","paper_date":"2024-11-26","code_links":[{"title":"jovanavidenovic/dam4sam","url":"https://github.com/jovanavidenovic/dam4sam"}],"metrics_order":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143557,"task":"Visual Object Tracking","parent_task":null,"dataset":"LaSOT","model_name":"SPMTrack-B","metrics":{"AUC":"74.9","Normalized Precision":"84","Precision":"81.7"},"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\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143558,"task":"Visual Object Tracking","parent_task":null,"dataset":"LaSOT","model_name":"RTracker-L","metrics":{"AUC":"74.7","Normalized Precision":"84.5"},"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\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143559,"task":"Visual Object Tracking","parent_task":null,"dataset":"LaSOT","model_name":"SAMURAI-L","metrics":{"AUC":"74.2","Normalized Precision":"82.7","Precision":"80.2"},"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":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143560,"task":"Visual Object Tracking","parent_task":null,"dataset":"LaSOT","model_name":"ODTrack-L","metrics":{"AUC":"74.0"},"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\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143561,"task":"Visual Object Tracking","parent_task":null,"dataset":"LaSOT","model_name":"ARTrackV2-L","metrics":{"AUC":"73.6","Normalized Precision":"82.8","Precision":"81.1"},"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\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143562,"task":"Visual Object Tracking","parent_task":null,"dataset":"LaSOT","model_name":"PiVOT-L","metrics":{"AUC":"73.4","Normalized Precision":"84.7","Precision":"82.1"},"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":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143563,"task":"Visual Object Tracking","parent_task":null,"dataset":"LaSOT","model_name":"MixViT-L(ConvMAE)","metrics":{"AUC":"73.3","Normalized Precision":"82.8","Precision":"80.3"},"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":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143564,"task":"Visual Object Tracking","parent_task":null,"dataset":"LaSOT","model_name":"ODTrack-B","metrics":{"AUC":"73.2"},"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\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143565,"task":"Visual Object Tracking","parent_task":null,"dataset":"LaSOT","model_name":"ARTrack-L","metrics":{"AUC":"73.1","Normalized Precision":"82.2","Precision":"80.3"},"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\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143566,"task":"Visual Object Tracking","parent_task":null,"dataset":"LaSOT","model_name":"HIPTrack","metrics":{"AUC":"72.7","Normalized Precision":"82.9","Precision":"79.5"},"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":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143567,"task":"Visual Object Tracking","parent_task":null,"dataset":"LaSOT","model_name":"SeqTrack-L384","metrics":{"AUC":"72.5","Normalized Precision":"81.5","Precision":"79.3"},"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\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143568,"task":"Visual Object Tracking","parent_task":null,"dataset":"LaSOT","model_name":"UNINEXT-L","metrics":{"AUC":"72.4","Normalized Precision":"80.7","Precision":"78.9"},"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":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143569,"task":"Visual Object Tracking","parent_task":null,"dataset":"LaSOT","model_name":"NeighborTrack-OSTrack","metrics":{"AUC":"72.2","Normalized Precision":"81.8","Precision":"78.0"},"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":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143570,"task":"Visual Object Tracking","parent_task":null,"dataset":"LaSOT","model_name":"UNINEXT-H","metrics":{"AUC":"72.2","Normalized Precision":"80.8","Precision":"79.4"},"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":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143571,"task":"Visual Object Tracking","parent_task":null,"dataset":"LaSOT","model_name":"MITS","metrics":{"AUC":"72.0","Normalized Precision":"80.1","Precision":"78.5"},"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":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143572,"task":"Visual Object Tracking","parent_task":null,"dataset":"LaSOT","model_name":"DropTrack","metrics":{"AUC":"71.8","Normalized Precision":"81.8","Precision":"78.1"},"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\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143573,"task":"Visual Object Tracking","parent_task":null,"dataset":"LaSOT","model_name":"OSTrack-384","metrics":{"AUC":"71.1","Normalized Precision":"81.1","Precision":"77.6"},"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":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143574,"task":"Visual Object Tracking","parent_task":null,"dataset":"LaSOT","model_name":"TATrack-L","metrics":{"AUC":"71.1","Normalized Precision":"79.1","Precision":"76.1"},"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":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143575,"task":"Visual Object Tracking","parent_task":null,"dataset":"LaSOT","model_name":"SwinV2-L 1K-MIM","metrics":{"AUC":"70.7"},"paper_url":"https://arxiv.org/abs/2205.13543v2","paper_title":"Revealing the Dark Secrets of Masked Image Modeling","paper_date":"2022-05-26","code_links":[{"title":"SwinTransformer/MIM-Depth-Estimation","url":"https://github.com/SwinTransformer/MIM-Depth-Estimation"}],"metrics_order":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143576,"task":"Visual Object Tracking","parent_task":null,"dataset":"LaSOT","model_name":"MixFormerV2-B","metrics":{"AUC":"70.6","Normalized Precision":"80.8","Precision":"76.2"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143577,"task":"Visual Object Tracking","parent_task":null,"dataset":"LaSOT","model_name":"LoReTrack","metrics":{"AUC":"70.3","Precision":"76.2"},"paper_url":"https://arxiv.org/abs/2405.17660v1","paper_title":"LoReTrack: Efficient and Accurate Low-Resolution Transformer Tracking","paper_date":"2024-05-27","code_links":[{"title":"ShaohuaDong2021/LoReTrack","url":"https://github.com/ShaohuaDong2021/LoReTrack"}],"metrics_order":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143578,"task":"Visual Object Tracking","parent_task":null,"dataset":"LaSOT","model_name":"SwinTrack-B-384","metrics":{"AUC":"70.2","Normalized Precision":"78.4","Precision":"75.3"},"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":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143579,"task":"Visual Object Tracking","parent_task":null,"dataset":"LaSOT","model_name":"MixFormer-L","metrics":{"AUC":"70.1","Normalized Precision":"79.9","Precision":"76.3"},"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":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143580,"task":"Visual Object Tracking","parent_task":null,"dataset":"LaSOT","model_name":"SwinV2-B 1K-MIM","metrics":{"AUC":"70"},"paper_url":"https://arxiv.org/abs/2205.13543v2","paper_title":"Revealing the Dark Secrets of Masked Image Modeling","paper_date":"2022-05-26","code_links":[{"title":"SwinTransformer/MIM-Depth-Estimation","url":"https://github.com/SwinTransformer/MIM-Depth-Estimation"}],"metrics_order":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143581,"task":"Visual Object Tracking","parent_task":null,"dataset":"LaSOT","model_name":"AiATrack","metrics":{"AUC":"69.0","Normalized Precision":"79.4","Precision":"73.8"},"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":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143582,"task":"Visual Object Tracking","parent_task":null,"dataset":"LaSOT","model_name":"Unicorn","metrics":{"AUC":"68.5","Normalized Precision":"76.6","Precision":"74.1"},"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":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143583,"task":"Visual Object Tracking","parent_task":null,"dataset":"LaSOT","model_name":"KeepTrack","metrics":{"AUC":"67.1","Normalized Precision":"77.2","Precision":"70.2"},"paper_url":"https://arxiv.org/abs/2103.16556v2","paper_title":"Learning Target Candidate Association to Keep Track of What Not to Track","paper_date":"2021-03-30","code_links":[{"title":"visionml/pytracking","url":"https://github.com/visionml/pytracking"}],"metrics_order":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143584,"task":"Visual Object Tracking","parent_task":null,"dataset":"LaSOT","model_name":"STARK","metrics":{"AUC":"67.1","Normalized Precision":"77.0"},"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":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143585,"task":"Visual Object Tracking","parent_task":null,"dataset":"LaSOT","model_name":"SLT-TransT","metrics":{"AUC":"66.8","Normalized Precision":"75.5"},"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":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143586,"task":"Visual Object Tracking","parent_task":null,"dataset":"LaSOT","model_name":"TransT","metrics":{"AUC":"64.9","Normalized Precision":"73.8","Precision":"69.0"},"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":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143587,"task":"Visual Object Tracking","parent_task":null,"dataset":"LaSOT","model_name":"Siam R-CNN","metrics":{"AUC":"64.8","Normalized Precision":"72.2"},"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":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143588,"task":"Visual Object Tracking","parent_task":null,"dataset":"LaSOT","model_name":"TrDiMP","metrics":{"AUC":"63.7","Precision":"61.4"},"paper_url":"https://arxiv.org/abs/2103.11681v2","paper_title":"Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking","paper_date":"2021-03-22","code_links":[{"title":"594422814/TransformerTrack","url":"https://github.com/594422814/TransformerTrack"}],"metrics_order":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143589,"task":"Visual Object Tracking","parent_task":null,"dataset":"LaSOT","model_name":"DiMP-NCE+","metrics":{"AUC":"63.7"},"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":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143590,"task":"Visual Object Tracking","parent_task":null,"dataset":"LaSOT","model_name":"TRASFUST","metrics":{"AUC":"57.6"},"paper_url":"https://arxiv.org/abs/2007.04108v2","paper_title":"Tracking-by-Trackers with a Distilled and Reinforced Model","paper_date":"2020-07-08","code_links":[{"title":"dontfollowmeimcrazy/vot-kd-rl","url":"https://github.com/dontfollowmeimcrazy/vot-kd-rl"}],"metrics_order":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143591,"task":"Visual Object Tracking","parent_task":null,"dataset":"LaSOT","model_name":"SiamBAN-ACM","metrics":{"AUC":"57.2","Normalized Precision":"65.3","Precision":"58.7"},"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":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143592,"task":"Visual Object Tracking","parent_task":null,"dataset":"LaSOT","model_name":"DiMP","metrics":{"AUC":"56.8","Normalized Precision":"65.0","Precision":"56.7"},"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":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143593,"task":"Visual Object Tracking","parent_task":null,"dataset":"LaSOT","model_name":"ATOM","metrics":{"AUC":"51.4","Normalized Precision":"57.6","Precision":"50.5"},"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":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143594,"task":"Visual Object Tracking","parent_task":null,"dataset":"LaSOT","model_name":"DiMP-50","metrics":{"Precision":"68.7"},"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":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143595,"task":"Visual Object Tracking","parent_task":null,"dataset":"LaSOT","model_name":"ToMP","metrics":{"Precision":"67.1"},"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":"[\"AUC\", \"Normalized Precision\", \"Precision\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]}]}