{"task":"Visual Object Tracking","dataset":"GOT-10k","metric_names":["Average Overlap","Success Rate 0.5","Success Rate 0.75"],"rows":[{"id":48196,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"GOT-10k","model_name":"SAMURAI-L","metrics":{"Average Overlap":"81.7","Success Rate 0.5":"92.2","Success Rate 0.75":"76.9"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48197,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"GOT-10k","model_name":"DAM4SAM","metrics":{"Average Overlap":"81.1"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48198,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"GOT-10k","model_name":"SPMTrack-G","metrics":{"Average Overlap":"81","Success Rate 0.5":"89.2","Success Rate 0.75":"82.3"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48199,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"GOT-10k","model_name":"MITS","metrics":{"Average Overlap":"80.4","Success Rate 0.5":"89.8","Success Rate 0.75":"75.8"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48200,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"GOT-10k","model_name":"SPMTrack-L","metrics":{"Average Overlap":"80","Success Rate 0.5":"89.4","Success Rate 0.75":"79.9"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48201,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"GOT-10k","model_name":"MCITrack-L384","metrics":{"Average Overlap":"80.0","Success Rate 0.5":"88.5","Success Rate 0.75":"80.2"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48202,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"GOT-10k","model_name":"ARTrackV2-L","metrics":{"Average Overlap":"79.5","Success Rate 0.5":"87.8","Success Rate 0.75":"79.6"},"paper_url":"https://arxiv.org/abs/2312.17133v3","paper_title":"ARTrackV2: Prompting Autoregressive Tracker Where to Look and How to Describe","paper_date":"2023-12-28","code_links":[{"title":"miv-xjtu/artrack","url":"https://github.com/miv-xjtu/artrack"}],"metrics_order":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48203,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"GOT-10k","model_name":"LoRAT-g-378","metrics":{"Average Overlap":"78.9","Success Rate 0.5":"87.8","Success Rate 0.75":"80.7"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48204,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"GOT-10k","model_name":"ARTrack-L","metrics":{"Average Overlap":"78.5","Success Rate 0.5":"87.4","Success Rate 0.75":"77.8"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48205,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"GOT-10k","model_name":"ODTrack-L","metrics":{"Average Overlap":"78.2"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48206,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"GOT-10k","model_name":"MCITrack-B224","metrics":{"Average Overlap":"77.9","Success Rate 0.5":"88.2","Success Rate 0.75":"76.8"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48207,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"GOT-10k","model_name":"RTracker-L","metrics":{"Average Overlap":"77.9","Success Rate 0.5":"87","Success Rate 0.75":"76.9"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48208,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"GOT-10k","model_name":"LoRAT-L-378","metrics":{"Average Overlap":"77.5","Success Rate 0.5":"86.2","Success Rate 0.75":"78.1"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48209,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"GOT-10k","model_name":"HIPTrack","metrics":{"Average Overlap":"77.4","Success Rate 0.5":"88.0","Success Rate 0.75":"74.5"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48210,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"GOT-10k","model_name":"ODTrack-B","metrics":{"Average Overlap":"77.0"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48211,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"GOT-10k","model_name":"TATrack-L-GOT","metrics":{"Average Overlap":"76.6","Success Rate 0.5":"85.7","Success Rate 0.75":"73.4"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48212,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"GOT-10k","model_name":"SPMTrack-B","metrics":{"Average Overlap":"76.5","Success Rate 0.5":"85.9","Success Rate 0.75":"76.3"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48213,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"GOT-10k","model_name":"DropMAE","metrics":{"Average Overlap":"75.9","Success Rate 0.5":"86.8","Success Rate 0.75":"72"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48214,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"GOT-10k","model_name":"NeighborTrack-OSTrack","metrics":{"Average Overlap":"75.7","Success Rate 0.5":"85.72","Success Rate 0.75":"73.3"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48215,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"GOT-10k","model_name":"MixViT-L(ConvMAE)","metrics":{"Average Overlap":"75.7","Success Rate 0.5":"85.3","Success Rate 0.75":"75.1"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48216,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"GOT-10k","model_name":"MixFormer-L","metrics":{"Average Overlap":"75.6","Success Rate 0.5":"85.73","Success Rate 0.75":"72.8"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48217,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"GOT-10k","model_name":"SeqTrack-L384","metrics":{"Average Overlap":"74.8","Success Rate 0.5":"81.9","Success Rate 0.75":"72.2"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48218,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"GOT-10k","model_name":"OSTrack-384","metrics":{"Average Overlap":"73.7","Success Rate 0.5":"83.2","Success Rate 0.75":"70.8"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48219,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"GOT-10k","model_name":"SwinV2-L 1K-MIM","metrics":{"Average Overlap":"72.9"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48220,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"GOT-10k","model_name":"MixFormer-1k","metrics":{"Average Overlap":"71.2","Success Rate 0.5":"79.9","Success Rate 0.75":"65.8"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48221,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"GOT-10k","model_name":"SwinV2-B 1K-MIM","metrics":{"Average Overlap":"70.8"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48222,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"GOT-10k","model_name":"MixFormer","metrics":{"Average Overlap":"70.7","Success Rate 0.5":"80.0","Success Rate 0.75":"67.8"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48223,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"GOT-10k","model_name":"AiATrack","metrics":{"Average Overlap":"69.6","Success Rate 0.5":"80.0","Success Rate 0.75":"63.2"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48224,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"GOT-10k","model_name":"SwinTrack-B","metrics":{"Average Overlap":"69.4","Success Rate 0.5":"78","Success Rate 0.75":"64.3"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48225,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"GOT-10k","model_name":"STARK","metrics":{"Average Overlap":"68.8","Success Rate 0.5":"78.1"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48226,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"GOT-10k","model_name":"SLT-TransT","metrics":{"Average Overlap":"67.5","Success Rate 0.5":"76.8","Success Rate 0.75":"60.3"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48227,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"GOT-10k","model_name":"TREG","metrics":{"Average Overlap":"66.8","Success Rate 0.5":"77.8","Success Rate 0.75":"57.2"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48228,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"GOT-10k","model_name":"Siam R-CNN","metrics":{"Average Overlap":"64.9","Success Rate 0.5":"72.8"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48229,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"GOT-10k","model_name":"FEAR-L","metrics":{"Average Overlap":"64.5"},"paper_url":"https://arxiv.org/abs/2112.07957v2","paper_title":"FEAR: Fast, Efficient, Accurate and Robust Visual Tracker","paper_date":"2021-12-15","code_links":[{"title":"pinatafarms/feartracker","url":"https://github.com/pinatafarms/feartracker"}],"metrics_order":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48230,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"GOT-10k","model_name":"STMTrack","metrics":{"Average Overlap":"64.2","Success Rate 0.5":"73.7","Success Rate 0.75":"57.5"},"paper_url":"https://arxiv.org/abs/2104.00324v2","paper_title":"STMTrack: Template-free Visual Tracking with Space-time Memory Networks","paper_date":"2021-04-01","code_links":[{"title":"fzh0917/STMTrack","url":"https://github.com/fzh0917/STMTrack"}],"metrics_order":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48231,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"GOT-10k","model_name":"FEAR-M","metrics":{"Average Overlap":"62.3"},"paper_url":"https://arxiv.org/abs/2112.07957v2","paper_title":"FEAR: Fast, Efficient, Accurate and Robust Visual Tracker","paper_date":"2021-12-15","code_links":[{"title":"pinatafarms/feartracker","url":"https://github.com/pinatafarms/feartracker"}],"metrics_order":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48232,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"GOT-10k","model_name":"FEAR-XS","metrics":{"Average Overlap":"61.9"},"paper_url":"https://arxiv.org/abs/2112.07957v2","paper_title":"FEAR: Fast, Efficient, Accurate and Robust Visual Tracker","paper_date":"2021-12-15","code_links":[{"title":"pinatafarms/feartracker","url":"https://github.com/pinatafarms/feartracker"}],"metrics_order":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48233,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"GOT-10k","model_name":"TRASFUST","metrics":{"Average Overlap":"61.7","Success Rate 0.5":"72.9"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48234,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"GOT-10k","model_name":"Ocean","metrics":{"Average Overlap":"61.1","Success Rate 0.5":"72.1"},"paper_url":"https://arxiv.org/abs/2006.10721v2","paper_title":"Ocean: Object-aware Anchor-free Tracking","paper_date":"2020-06-18","code_links":[{"title":"researchmm/SiamDW","url":"https://github.com/researchmm/SiamDW"},{"title":"researchmm/TracKit","url":"https://github.com/researchmm/TracKit"},{"title":"code-implementation1/Code9","url":"https://github.com/code-implementation1/Code9/tree/main/ocean_model"},{"title":"2023-MindSpore-1/ms-code-218","url":"https://github.com/2023-MindSpore-1/ms-code-218/tree/main/ocean_model"}],"metrics_order":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48235,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"GOT-10k","model_name":"DiMP","metrics":{"Average Overlap":"61.1","Success Rate 0.5":"71.7"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48236,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"GOT-10k","model_name":"ATOM","metrics":{"Average Overlap":"61.0","Success Rate 0.5":"74.2"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48237,"task":"Visual Object Tracking","parent_task":"Object Tracking","dataset":"GOT-10k","model_name":"SiamFC++","metrics":{"Average Overlap":"61.0","Success Rate 0.5":"74.2"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143625,"task":"Visual Object Tracking","parent_task":null,"dataset":"GOT-10k","model_name":"SAMURAI-L","metrics":{"Average Overlap":"81.7","Success Rate 0.5":"92.2","Success Rate 0.75":"76.9"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143626,"task":"Visual Object Tracking","parent_task":null,"dataset":"GOT-10k","model_name":"DAM4SAM","metrics":{"Average Overlap":"81.1"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143627,"task":"Visual Object Tracking","parent_task":null,"dataset":"GOT-10k","model_name":"SPMTrack-G","metrics":{"Average Overlap":"81","Success Rate 0.5":"89.2","Success Rate 0.75":"82.3"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143628,"task":"Visual Object Tracking","parent_task":null,"dataset":"GOT-10k","model_name":"MITS","metrics":{"Average Overlap":"80.4","Success Rate 0.5":"89.8","Success Rate 0.75":"75.8"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143629,"task":"Visual Object Tracking","parent_task":null,"dataset":"GOT-10k","model_name":"SPMTrack-L","metrics":{"Average Overlap":"80","Success Rate 0.5":"89.4","Success Rate 0.75":"79.9"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143630,"task":"Visual Object Tracking","parent_task":null,"dataset":"GOT-10k","model_name":"MCITrack-L384","metrics":{"Average Overlap":"80.0","Success Rate 0.5":"88.5","Success Rate 0.75":"80.2"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143631,"task":"Visual Object Tracking","parent_task":null,"dataset":"GOT-10k","model_name":"ARTrackV2-L","metrics":{"Average Overlap":"79.5","Success Rate 0.5":"87.8","Success Rate 0.75":"79.6"},"paper_url":"https://arxiv.org/abs/2312.17133v3","paper_title":"ARTrackV2: Prompting Autoregressive Tracker Where to Look and How to Describe","paper_date":"2023-12-28","code_links":[{"title":"miv-xjtu/artrack","url":"https://github.com/miv-xjtu/artrack"}],"metrics_order":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143632,"task":"Visual Object Tracking","parent_task":null,"dataset":"GOT-10k","model_name":"LoRAT-g-378","metrics":{"Average Overlap":"78.9","Success Rate 0.5":"87.8","Success Rate 0.75":"80.7"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143633,"task":"Visual Object Tracking","parent_task":null,"dataset":"GOT-10k","model_name":"ARTrack-L","metrics":{"Average Overlap":"78.5","Success Rate 0.5":"87.4","Success Rate 0.75":"77.8"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143634,"task":"Visual Object Tracking","parent_task":null,"dataset":"GOT-10k","model_name":"ODTrack-L","metrics":{"Average Overlap":"78.2"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143635,"task":"Visual Object Tracking","parent_task":null,"dataset":"GOT-10k","model_name":"MCITrack-B224","metrics":{"Average Overlap":"77.9","Success Rate 0.5":"88.2","Success Rate 0.75":"76.8"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143636,"task":"Visual Object Tracking","parent_task":null,"dataset":"GOT-10k","model_name":"RTracker-L","metrics":{"Average Overlap":"77.9","Success Rate 0.5":"87","Success Rate 0.75":"76.9"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143637,"task":"Visual Object Tracking","parent_task":null,"dataset":"GOT-10k","model_name":"LoRAT-L-378","metrics":{"Average Overlap":"77.5","Success Rate 0.5":"86.2","Success Rate 0.75":"78.1"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143638,"task":"Visual Object Tracking","parent_task":null,"dataset":"GOT-10k","model_name":"HIPTrack","metrics":{"Average Overlap":"77.4","Success Rate 0.5":"88.0","Success Rate 0.75":"74.5"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143639,"task":"Visual Object Tracking","parent_task":null,"dataset":"GOT-10k","model_name":"ODTrack-B","metrics":{"Average Overlap":"77.0"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143640,"task":"Visual Object Tracking","parent_task":null,"dataset":"GOT-10k","model_name":"TATrack-L-GOT","metrics":{"Average Overlap":"76.6","Success Rate 0.5":"85.7","Success Rate 0.75":"73.4"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143641,"task":"Visual Object Tracking","parent_task":null,"dataset":"GOT-10k","model_name":"SPMTrack-B","metrics":{"Average Overlap":"76.5","Success Rate 0.5":"85.9","Success Rate 0.75":"76.3"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143642,"task":"Visual Object Tracking","parent_task":null,"dataset":"GOT-10k","model_name":"DropMAE","metrics":{"Average Overlap":"75.9","Success Rate 0.5":"86.8","Success Rate 0.75":"72"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143643,"task":"Visual Object Tracking","parent_task":null,"dataset":"GOT-10k","model_name":"NeighborTrack-OSTrack","metrics":{"Average Overlap":"75.7","Success Rate 0.5":"85.72","Success Rate 0.75":"73.3"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143644,"task":"Visual Object Tracking","parent_task":null,"dataset":"GOT-10k","model_name":"MixViT-L(ConvMAE)","metrics":{"Average Overlap":"75.7","Success Rate 0.5":"85.3","Success Rate 0.75":"75.1"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143645,"task":"Visual Object Tracking","parent_task":null,"dataset":"GOT-10k","model_name":"MixFormer-L","metrics":{"Average Overlap":"75.6","Success Rate 0.5":"85.73","Success Rate 0.75":"72.8"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143646,"task":"Visual Object Tracking","parent_task":null,"dataset":"GOT-10k","model_name":"SeqTrack-L384","metrics":{"Average Overlap":"74.8","Success Rate 0.5":"81.9","Success Rate 0.75":"72.2"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143647,"task":"Visual Object Tracking","parent_task":null,"dataset":"GOT-10k","model_name":"OSTrack-384","metrics":{"Average Overlap":"73.7","Success Rate 0.5":"83.2","Success Rate 0.75":"70.8"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143648,"task":"Visual Object Tracking","parent_task":null,"dataset":"GOT-10k","model_name":"SwinV2-L 1K-MIM","metrics":{"Average Overlap":"72.9"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143649,"task":"Visual Object Tracking","parent_task":null,"dataset":"GOT-10k","model_name":"MixFormer-1k","metrics":{"Average Overlap":"71.2","Success Rate 0.5":"79.9","Success Rate 0.75":"65.8"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143650,"task":"Visual Object Tracking","parent_task":null,"dataset":"GOT-10k","model_name":"SwinV2-B 1K-MIM","metrics":{"Average Overlap":"70.8"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143651,"task":"Visual Object Tracking","parent_task":null,"dataset":"GOT-10k","model_name":"MixFormer","metrics":{"Average Overlap":"70.7","Success Rate 0.5":"80.0","Success Rate 0.75":"67.8"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143652,"task":"Visual Object Tracking","parent_task":null,"dataset":"GOT-10k","model_name":"AiATrack","metrics":{"Average Overlap":"69.6","Success Rate 0.5":"80.0","Success Rate 0.75":"63.2"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143653,"task":"Visual Object Tracking","parent_task":null,"dataset":"GOT-10k","model_name":"SwinTrack-B","metrics":{"Average Overlap":"69.4","Success Rate 0.5":"78","Success Rate 0.75":"64.3"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143654,"task":"Visual Object Tracking","parent_task":null,"dataset":"GOT-10k","model_name":"STARK","metrics":{"Average Overlap":"68.8","Success Rate 0.5":"78.1"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143655,"task":"Visual Object Tracking","parent_task":null,"dataset":"GOT-10k","model_name":"SLT-TransT","metrics":{"Average Overlap":"67.5","Success Rate 0.5":"76.8","Success Rate 0.75":"60.3"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143656,"task":"Visual Object Tracking","parent_task":null,"dataset":"GOT-10k","model_name":"TREG","metrics":{"Average Overlap":"66.8","Success Rate 0.5":"77.8","Success Rate 0.75":"57.2"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143657,"task":"Visual Object Tracking","parent_task":null,"dataset":"GOT-10k","model_name":"Siam R-CNN","metrics":{"Average Overlap":"64.9","Success Rate 0.5":"72.8"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143658,"task":"Visual Object Tracking","parent_task":null,"dataset":"GOT-10k","model_name":"FEAR-L","metrics":{"Average Overlap":"64.5"},"paper_url":"https://arxiv.org/abs/2112.07957v2","paper_title":"FEAR: Fast, Efficient, Accurate and Robust Visual Tracker","paper_date":"2021-12-15","code_links":[{"title":"pinatafarms/feartracker","url":"https://github.com/pinatafarms/feartracker"}],"metrics_order":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143659,"task":"Visual Object Tracking","parent_task":null,"dataset":"GOT-10k","model_name":"STMTrack","metrics":{"Average Overlap":"64.2","Success Rate 0.5":"73.7","Success Rate 0.75":"57.5"},"paper_url":"https://arxiv.org/abs/2104.00324v2","paper_title":"STMTrack: Template-free Visual Tracking with Space-time Memory Networks","paper_date":"2021-04-01","code_links":[{"title":"fzh0917/STMTrack","url":"https://github.com/fzh0917/STMTrack"}],"metrics_order":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143660,"task":"Visual Object Tracking","parent_task":null,"dataset":"GOT-10k","model_name":"FEAR-M","metrics":{"Average Overlap":"62.3"},"paper_url":"https://arxiv.org/abs/2112.07957v2","paper_title":"FEAR: Fast, Efficient, Accurate and Robust Visual Tracker","paper_date":"2021-12-15","code_links":[{"title":"pinatafarms/feartracker","url":"https://github.com/pinatafarms/feartracker"}],"metrics_order":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143661,"task":"Visual Object Tracking","parent_task":null,"dataset":"GOT-10k","model_name":"FEAR-XS","metrics":{"Average Overlap":"61.9"},"paper_url":"https://arxiv.org/abs/2112.07957v2","paper_title":"FEAR: Fast, Efficient, Accurate and Robust Visual Tracker","paper_date":"2021-12-15","code_links":[{"title":"pinatafarms/feartracker","url":"https://github.com/pinatafarms/feartracker"}],"metrics_order":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143662,"task":"Visual Object Tracking","parent_task":null,"dataset":"GOT-10k","model_name":"TRASFUST","metrics":{"Average Overlap":"61.7","Success Rate 0.5":"72.9"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143663,"task":"Visual Object Tracking","parent_task":null,"dataset":"GOT-10k","model_name":"Ocean","metrics":{"Average Overlap":"61.1","Success Rate 0.5":"72.1"},"paper_url":"https://arxiv.org/abs/2006.10721v2","paper_title":"Ocean: Object-aware Anchor-free Tracking","paper_date":"2020-06-18","code_links":[{"title":"researchmm/SiamDW","url":"https://github.com/researchmm/SiamDW"},{"title":"researchmm/TracKit","url":"https://github.com/researchmm/TracKit"},{"title":"code-implementation1/Code9","url":"https://github.com/code-implementation1/Code9/tree/main/ocean_model"},{"title":"2023-MindSpore-1/ms-code-218","url":"https://github.com/2023-MindSpore-1/ms-code-218/tree/main/ocean_model"}],"metrics_order":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143664,"task":"Visual Object Tracking","parent_task":null,"dataset":"GOT-10k","model_name":"DiMP","metrics":{"Average Overlap":"61.1","Success Rate 0.5":"71.7"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143665,"task":"Visual Object Tracking","parent_task":null,"dataset":"GOT-10k","model_name":"ATOM","metrics":{"Average Overlap":"61.0","Success Rate 0.5":"74.2"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":143666,"task":"Visual Object Tracking","parent_task":null,"dataset":"GOT-10k","model_name":"SiamFC++","metrics":{"Average Overlap":"61.0","Success Rate 0.5":"74.2"},"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":"[\"Average Overlap\", \"Success Rate 0.5\", \"Success Rate 0.75\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]}]}