{"url":"/sota/visual-object-tracking-on-lasot","task":{"name":"Visual Object Tracking","url":"/task/visual-object-tracking","note":null},"dataset":{"name":"LaSOT","url":"/dataset/lasot"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"**Visual Object Tracking** is an important research topic in computer vision, image understanding and pattern recognition. Given the initial state (centre location and scale) of a target in the first frame of a video sequence, the aim of Visual Object Tracking is to automatically obtain the states of the object in the subsequent video frames.\n\n\n<span class=\"description-source\">Source: [Learning Adaptive Discriminative Correlation Filters via Temporal Consistency Preserving Spatial Feature Selection for Robust Visual Object Tracking ](https://arxiv.org/abs/1807.11348)</span>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["AUC","Normalized Precision","Precision"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"AUC":"higher","Normalized Precision":"higher","Precision":"higher"}},"counts":{"rows":46,"rows_with_code":45,"rows_with_paper_page":45,"rows_dated":45,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"SPMTrack-G","metrics":{"AUC":"77.4","Normalized Precision":"86.6","Precision":"85"},"uses_additional_data":false,"paper_date":"2025-03-24","paper":"/paper/spmtrack-spatio-temporal-parameter-efficient","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","code":"https://github.com/wenruicai/spmtrack","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"SPMTrack-L","metrics":{"AUC":"76.8","Normalized Precision":"85.9","Precision":"84"},"uses_additional_data":false,"paper_date":"2025-03-24","paper":"/paper/spmtrack-spatio-temporal-parameter-efficient","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","code":"https://github.com/wenruicai/spmtrack","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"MCITrack-L384","metrics":{"AUC":"76.6","Normalized Precision":"86.1","Precision":"85.0"},"uses_additional_data":false,"paper_date":"2024-12-15","paper":"/paper/exploring-enhanced-contextual-information-for-1","paper_url":"https://arxiv.org/abs/2412.11023v1","paper_title":"Exploring Enhanced Contextual Information for Video-Level Object Tracking","code":"https://github.com/kangben258/MCITrack","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"LoRAT-g-378","metrics":{"AUC":"76.2","Normalized Precision":"85.3","Precision":"83.5"},"uses_additional_data":false,"paper_date":"2024-03-08","paper":"/paper/tracking-meets-lora-faster-training-larger","paper_url":"https://arxiv.org/abs/2403.05231v2","paper_title":"Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performance","code":"https://github.com/litinglin/lorat","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":2,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"MCITrack-B224","metrics":{"AUC":"75.3","Normalized Precision":"85.6","Precision":"83.3"},"uses_additional_data":false,"paper_date":"2024-12-15","paper":"/paper/exploring-enhanced-contextual-information-for-1","paper_url":"https://arxiv.org/abs/2412.11023v1","paper_title":"Exploring Enhanced Contextual Information for Video-Level Object Tracking","code":"https://github.com/kangben258/MCITrack","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"LoRAT-L-378","metrics":{"AUC":"75.1","Normalized Precision":"84.1","Precision":"82.0"},"uses_additional_data":false,"paper_date":"2024-03-08","paper":"/paper/tracking-meets-lora-faster-training-larger","paper_url":"https://arxiv.org/abs/2403.05231v2","paper_title":"Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performance","code":"https://github.com/litinglin/lorat","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":2,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"DAM4SAM","metrics":{"AUC":"75.1"},"uses_additional_data":false,"paper_date":"2024-11-26","paper":"/paper/a-distractor-aware-memory-for-visual-object","paper_url":"https://arxiv.org/abs/2411.17576v2","paper_title":"A Distractor-Aware Memory for Visual Object Tracking with SAM2","code":"https://github.com/jovanavidenovic/dam4sam","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":8,"n_samples":11,"n_pointer_only_licence":11}},{"rank_in_archive_order":8,"model":"SPMTrack-B","metrics":{"AUC":"74.9","Normalized Precision":"84","Precision":"81.7"},"uses_additional_data":false,"paper_date":"2025-03-24","paper":"/paper/spmtrack-spatio-temporal-parameter-efficient","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","code":"https://github.com/wenruicai/spmtrack","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":9,"model":"RTracker-L","metrics":{"AUC":"74.7","Normalized Precision":"84.5"},"uses_additional_data":false,"paper_date":"2024-03-28","paper":"/paper/rtracker-recoverable-tracking-via-pn-tree","paper_url":"https://arxiv.org/abs/2403.19242v1","paper_title":"RTracker: Recoverable Tracking via PN Tree Structured Memory","code":"https://github.com/norahgreen/rtracker","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"SAMURAI-L","metrics":{"AUC":"74.2","Normalized Precision":"82.7","Precision":"80.2"},"uses_additional_data":false,"paper_date":"2024-11-18","paper":"/paper/samurai-adapting-segment-anything-model-for-1","paper_url":"https://arxiv.org/abs/2411.11922v2","paper_title":"SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory","code":"https://github.com/yangchris11/samurai","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":11,"model":"ODTrack-L","metrics":{"AUC":"74.0"},"uses_additional_data":false,"paper_date":"2024-01-03","paper":"/paper/odtrack-online-dense-temporal-token-learning","paper_url":"https://arxiv.org/abs/2401.01686v1","paper_title":"ODTrack: Online Dense Temporal Token Learning for Visual Tracking","code":"https://github.com/gxnu-zhonglab/odtrack","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":12,"model":"ARTrackV2-L","metrics":{"AUC":"73.6","Normalized Precision":"82.8","Precision":"81.1"},"uses_additional_data":false,"paper_date":"2023-12-28","paper":"/paper/artrackv2-prompting-autoregressive-tracker","paper_url":"https://arxiv.org/abs/2312.17133v3","paper_title":"ARTrackV2: Prompting Autoregressive Tracker Where to Look and How to Describe","code":"https://github.com/miv-xjtu/artrack","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"PiVOT-L","metrics":{"AUC":"73.4","Normalized Precision":"84.7","Precision":"82.1"},"uses_additional_data":false,"paper_date":"2024-09-27","paper":"/paper/improving-visual-object-tracking-through","paper_url":"https://arxiv.org/abs/2409.18901v1","paper_title":"Improving Visual Object Tracking through Visual Prompting","code":"https://github.com/chenshihfang/GOT","n_code_links":1,"syntology":null},{"rank_in_archive_order":14,"model":"MixViT-L(ConvMAE)","metrics":{"AUC":"73.3","Normalized Precision":"82.8","Precision":"80.3"},"uses_additional_data":false,"paper_date":"2023-02-06","paper":"/paper/mixformer-end-to-end-tracking-with-iterative-2","paper_url":"https://arxiv.org/abs/2302.02814v2","paper_title":"MixFormer: End-to-End Tracking with Iterative Mixed Attention","code":"https://github.com/MCG-NJU/MixFormer","n_code_links":1,"syntology":null},{"rank_in_archive_order":15,"model":"ODTrack-B","metrics":{"AUC":"73.2"},"uses_additional_data":false,"paper_date":"2024-01-03","paper":"/paper/odtrack-online-dense-temporal-token-learning","paper_url":"https://arxiv.org/abs/2401.01686v1","paper_title":"ODTrack: Online Dense Temporal Token Learning for Visual Tracking","code":"https://github.com/gxnu-zhonglab/odtrack","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":16,"model":"ARTrack-L","metrics":{"AUC":"73.1","Normalized Precision":"82.2","Precision":"80.3"},"uses_additional_data":false,"paper_date":"2023-01-01","paper":"/paper/autoregressive-visual-tracking","paper_url":"http://openaccess.thecvf.com//content/CVPR2023/html/Wei_Autoregressive_Visual_Tracking_CVPR_2023_paper.html","paper_title":"Autoregressive Visual Tracking","code":"https://github.com/miv-xjtu/artrack","n_code_links":1,"syntology":null},{"rank_in_archive_order":17,"model":"HIPTrack","metrics":{"AUC":"72.7","Normalized Precision":"82.9","Precision":"79.5"},"uses_additional_data":false,"paper_date":"2023-11-03","paper":"/paper/learning-historical-status-prompt-for","paper_url":"https://arxiv.org/abs/2311.02072v2","paper_title":"HIPTrack: Visual Tracking with Historical Prompts","code":"https://github.com/wenruicai/hiptrack","n_code_links":1,"syntology":null},{"rank_in_archive_order":18,"model":"SeqTrack-L384","metrics":{"AUC":"72.5","Normalized Precision":"81.5","Precision":"79.3"},"uses_additional_data":false,"paper_date":"2023-04-27","paper":"/paper/seqtrack-sequence-to-sequence-learning-for","paper_url":"https://arxiv.org/abs/2304.14394v3","paper_title":"Unified Sequence-to-Sequence Learning for Single- and Multi-Modal Visual Object Tracking","code":"https://github.com/chenxin-dlut/seqtrackv2","n_code_links":1,"syntology":null},{"rank_in_archive_order":19,"model":"UNINEXT-L","metrics":{"AUC":"72.4","Normalized Precision":"80.7","Precision":"78.9"},"uses_additional_data":false,"paper_date":"2023-03-12","paper":"/paper/universal-instance-perception-as-object","paper_url":"https://arxiv.org/abs/2303.06674v2","paper_title":"Universal Instance Perception as Object Discovery and Retrieval","code":"https://github.com/MasterBin-IIAU/UNINEXT","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":20,"model":"NeighborTrack-OSTrack","metrics":{"AUC":"72.2","Normalized Precision":"81.8","Precision":"78.0"},"uses_additional_data":false,"paper_date":"2022-11-12","paper":"/paper/neighbortrack-improving-single-object","paper_url":"https://arxiv.org/abs/2211.06663v3","paper_title":"NeighborTrack: Improving Single Object Tracking by Bipartite Matching with Neighbor Tracklets","code":"https://github.com/franktpmvu/NeighborTrack","n_code_links":1,"syntology":null},{"rank_in_archive_order":21,"model":"UNINEXT-H","metrics":{"AUC":"72.2","Normalized Precision":"80.8","Precision":"79.4"},"uses_additional_data":false,"paper_date":"2023-03-12","paper":"/paper/universal-instance-perception-as-object","paper_url":"https://arxiv.org/abs/2303.06674v2","paper_title":"Universal Instance Perception as Object Discovery and Retrieval","code":"https://github.com/MasterBin-IIAU/UNINEXT","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":22,"model":"MITS","metrics":{"AUC":"72.0","Normalized Precision":"80.1","Precision":"78.5"},"uses_additional_data":false,"paper_date":"2023-08-25","paper":"/paper/integrating-boxes-and-masks-a-multi-object","paper_url":"https://arxiv.org/abs/2308.13266v3","paper_title":"Integrating Boxes and Masks: A Multi-Object Framework for Unified Visual Tracking and Segmentation","code":"https://github.com/yoxu515/mits","n_code_links":1,"syntology":null},{"rank_in_archive_order":23,"model":"DropTrack","metrics":{"AUC":"71.8","Normalized Precision":"81.8","Precision":"78.1"},"uses_additional_data":false,"paper_date":"2023-04-02","paper":"/paper/dropmae-masked-autoencoders-with-spatial","paper_url":"https://arxiv.org/abs/2304.00571v2","paper_title":"DropMAE: Masked Autoencoders with Spatial-Attention Dropout for Tracking Tasks","code":"https://github.com/jimmy-dq/dropmae","n_code_links":1,"syntology":null},{"rank_in_archive_order":24,"model":"OSTrack-384","metrics":{"AUC":"71.1","Normalized Precision":"81.1","Precision":"77.6"},"uses_additional_data":false,"paper_date":"2022-03-22","paper":"/paper/joint-feature-learning-and-relation-modeling","paper_url":"https://arxiv.org/abs/2203.11991v4","paper_title":"Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework","code":"https://github.com/botaoye/ostrack","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":25,"model":"TATrack-L","metrics":{"AUC":"71.1","Normalized Precision":"79.1","Precision":"76.1"},"uses_additional_data":false,"paper_date":"2023-02-27","paper":"/paper/target-aware-tracking-with-long-term-context","paper_url":"https://arxiv.org/abs/2302.13840v1","paper_title":"Target-Aware Tracking with Long-term Context Attention","code":"https://github.com/hekaijie123/TATrack","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":26,"model":"SwinV2-L 1K-MIM","metrics":{"AUC":"70.7"},"uses_additional_data":false,"paper_date":"2022-05-26","paper":"/paper/revealing-the-dark-secrets-of-masked-image","paper_url":"https://arxiv.org/abs/2205.13543v2","paper_title":"Revealing the Dark Secrets of Masked Image Modeling","code":"https://github.com/SwinTransformer/MIM-Depth-Estimation","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":27,"model":"MixFormerV2-B","metrics":{"AUC":"70.6","Normalized Precision":"80.8","Precision":"76.2"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":28,"model":"LoReTrack","metrics":{"AUC":"70.3","Precision":"76.2"},"uses_additional_data":false,"paper_date":"2024-05-27","paper":"/paper/loretrack-efficient-and-accurate-low","paper_url":"https://arxiv.org/abs/2405.17660v1","paper_title":"LoReTrack: Efficient and Accurate Low-Resolution Transformer Tracking","code":"https://github.com/ShaohuaDong2021/LoReTrack","n_code_links":1,"syntology":null},{"rank_in_archive_order":29,"model":"SwinTrack-B-384","metrics":{"AUC":"70.2","Normalized Precision":"78.4","Precision":"75.3"},"uses_additional_data":false,"paper_date":"2021-12-02","paper":"/paper/swintrack-a-simple-and-strong-baseline-for","paper_url":"https://arxiv.org/abs/2112.00995v3","paper_title":"SwinTrack: A Simple and Strong Baseline for Transformer Tracking","code":"https://github.com/litinglin/swintrack","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":30,"model":"MixFormer-L","metrics":{"AUC":"70.1","Normalized Precision":"79.9","Precision":"76.3"},"uses_additional_data":false,"paper_date":"2022-03-21","paper":"/paper/mixformer-end-to-end-tracking-with-iterative-1","paper_url":"https://arxiv.org/abs/2203.11082v2","paper_title":"MixFormer: End-to-End Tracking with Iterative Mixed Attention","code":"https://github.com/MCG-NJU/MixFormer","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":31,"model":"SwinV2-B 1K-MIM","metrics":{"AUC":"70"},"uses_additional_data":false,"paper_date":"2022-05-26","paper":"/paper/revealing-the-dark-secrets-of-masked-image","paper_url":"https://arxiv.org/abs/2205.13543v2","paper_title":"Revealing the Dark Secrets of Masked Image Modeling","code":"https://github.com/SwinTransformer/MIM-Depth-Estimation","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":32,"model":"AiATrack","metrics":{"AUC":"69.0","Normalized Precision":"79.4","Precision":"73.8"},"uses_additional_data":false,"paper_date":"2022-07-20","paper":"/paper/aiatrack-attention-in-attention-for","paper_url":"https://arxiv.org/abs/2207.09603v2","paper_title":"AiATrack: Attention in Attention for Transformer Visual Tracking","code":"https://github.com/Little-Podi/AiATrack","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":33,"model":"Unicorn","metrics":{"AUC":"68.5","Normalized Precision":"76.6","Precision":"74.1"},"uses_additional_data":false,"paper_date":"2022-07-14","paper":"/paper/towards-grand-unification-of-object-tracking","paper_url":"https://arxiv.org/abs/2207.07078v4","paper_title":"Towards Grand Unification of Object Tracking","code":"https://github.com/masterbin-iiau/unicorn","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":0,"n_samples":6,"n_pointer_only_licence":1}},{"rank_in_archive_order":34,"model":"KeepTrack","metrics":{"AUC":"67.1","Normalized Precision":"77.2","Precision":"70.2"},"uses_additional_data":false,"paper_date":"2021-03-30","paper":"/paper/learning-target-candidate-association-to-keep","paper_url":"https://arxiv.org/abs/2103.16556v2","paper_title":"Learning Target Candidate Association to Keep Track of What Not to Track","code":"https://github.com/visionml/pytracking","n_code_links":1,"syntology":null},{"rank_in_archive_order":35,"model":"STARK","metrics":{"AUC":"67.1","Normalized Precision":"77.0"},"uses_additional_data":false,"paper_date":"2021-03-31","paper":"/paper/learning-spatio-temporal-transformer-for","paper_url":"https://arxiv.org/abs/2103.17154v1","paper_title":"Learning Spatio-Temporal Transformer for Visual Tracking","code":"https://github.com/researchmm/Stark","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":36,"model":"SLT-TransT","metrics":{"AUC":"66.8","Normalized Precision":"75.5"},"uses_additional_data":false,"paper_date":"2022-08-11","paper":"/paper/towards-sequence-level-training-for-visual","paper_url":"https://arxiv.org/abs/2208.05810v3","paper_title":"Towards Sequence-Level Training for Visual Tracking","code":"https://github.com/byminji/SLTtrack","n_code_links":2,"syntology":{"n_ran":3,"n_unverified":2,"n_samples":5,"n_pointer_only_licence":5}},{"rank_in_archive_order":37,"model":"TransT","metrics":{"AUC":"64.9","Normalized Precision":"73.8","Precision":"69.0"},"uses_additional_data":false,"paper_date":"2021-03-29","paper":"/paper/2103-15436","paper_url":"https://arxiv.org/abs/2103.15436v1","paper_title":"Transformer Tracking","code":"https://github.com/chenxin-dlut/TransT","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":38,"model":"Siam R-CNN","metrics":{"AUC":"64.8","Normalized Precision":"72.2"},"uses_additional_data":false,"paper_date":"2019-11-28","paper":"/paper/siam-r-cnn-visual-tracking-by-re-detection","paper_url":"https://arxiv.org/abs/1911.12836v2","paper_title":"Siam R-CNN: Visual Tracking by Re-Detection","code":"https://github.com/VisualComputingInstitute/SiamR-CNN","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":4,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":39,"model":"TrDiMP","metrics":{"AUC":"63.7","Precision":"61.4"},"uses_additional_data":false,"paper_date":"2021-03-22","paper":"/paper/transformer-meets-tracker-exploiting-temporal","paper_url":"https://arxiv.org/abs/2103.11681v2","paper_title":"Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking","code":"https://github.com/594422814/TransformerTrack","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":3,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":40,"model":"DiMP-NCE+","metrics":{"AUC":"63.7"},"uses_additional_data":false,"paper_date":"2020-05-04","paper":"/paper/how-to-train-your-energy-based-model-for","paper_url":"https://arxiv.org/abs/2005.01698v2","paper_title":"How to Train Your Energy-Based Model for Regression","code":"https://github.com/fregu856/ebms_regression","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":41,"model":"TRASFUST","metrics":{"AUC":"57.6"},"uses_additional_data":false,"paper_date":"2020-07-08","paper":"/paper/a-distilled-model-for-tracking-and-tracker","paper_url":"https://arxiv.org/abs/2007.04108v2","paper_title":"Tracking-by-Trackers with a Distilled and Reinforced Model","code":"https://github.com/dontfollowmeimcrazy/vot-kd-rl","n_code_links":1,"syntology":null},{"rank_in_archive_order":42,"model":"SiamBAN-ACM","metrics":{"AUC":"57.2","Normalized Precision":"65.3","Precision":"58.7"},"uses_additional_data":false,"paper_date":"2020-12-04","paper":"/paper/learning-to-fuse-asymmetric-feature-maps-in","paper_url":"https://arxiv.org/abs/2012.02776v2","paper_title":"Learning to Fuse Asymmetric Feature Maps in Siamese Trackers","code":"https://github.com/wencheng256/SiamBAN-ACM","n_code_links":1,"syntology":null},{"rank_in_archive_order":43,"model":"DiMP","metrics":{"AUC":"56.8","Normalized Precision":"65.0","Precision":"56.7"},"uses_additional_data":false,"paper_date":"2019-04-15","paper":"/paper/190407220","paper_url":"https://arxiv.org/abs/1904.07220v2","paper_title":"Learning Discriminative Model Prediction for Tracking","code":"https://github.com/visionml/pytracking","n_code_links":2,"syntology":null},{"rank_in_archive_order":44,"model":"ATOM","metrics":{"AUC":"51.4","Normalized Precision":"57.6","Precision":"50.5"},"uses_additional_data":false,"paper_date":"2018-11-19","paper":"/paper/atom-accurate-tracking-by-overlap","paper_url":"http://arxiv.org/abs/1811.07628v2","paper_title":"ATOM: Accurate Tracking by Overlap Maximization","code":"https://github.com/visionml/pytracking","n_code_links":4,"syntology":{"n_ran":3,"n_unverified":6,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":45,"model":"DiMP-50","metrics":{"Precision":"68.7"},"uses_additional_data":false,"paper_date":"2019-04-15","paper":"/paper/190407220","paper_url":"https://arxiv.org/abs/1904.07220v2","paper_title":"Learning Discriminative Model Prediction for Tracking","code":"https://github.com/visionml/pytracking","n_code_links":2,"syntology":null},{"rank_in_archive_order":46,"model":"ToMP","metrics":{"Precision":"67.1"},"uses_additional_data":false,"paper_date":"2022-03-21","paper":"/paper/transforming-model-prediction-for-tracking","paper_url":"https://arxiv.org/abs/2203.11192v1","paper_title":"Transforming Model Prediction for Tracking","code":"https://github.com/visionml/pytracking","n_code_links":1,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":26,"rows_with_any_sample_ran":18,"distinct_papers_with_graph_line":20,"distinct_papers_with_any_sample_ran":14,"samples_over_distinct_papers":{"n_ran":38,"n_unverified":40,"n_samples":78,"n_pointer_only_licence":20,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":49,"n_unverified":46,"n_samples":95,"n_pointer_only_licence":20,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}