{"url":"/sota/visual-object-tracking-on-uav123","task":{"name":"Visual Object Tracking","url":"/task/visual-object-tracking","note":null},"dataset":{"name":"UAV123","url":"/dataset/uav123"},"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","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","Precision":"higher"}},"counts":{"rows":16,"rows_with_code":16,"rows_with_paper_page":16,"rows_dated":16,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"LoRAT-g-378","metrics":{"AUC":"0.739"},"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":2,"model":"NeighborTrack-OSTrack","metrics":{"AUC":"0.725","Precision":"0.9337"},"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":3,"model":"LoRAT-L-378","metrics":{"AUC":"0.725"},"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":4,"model":"ARTrackV2-L","metrics":{"AUC":"0.717"},"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":5,"model":"SPMTrack-B","metrics":{"AUC":"0.717"},"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":6,"model":"ARTrack-L","metrics":{"AUC":"0.712"},"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":7,"model":"OSTrack -384","metrics":{"AUC":"0.707"},"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":8,"model":"AiATrack","metrics":{"AUC":"0.706"},"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":9,"model":"HIPTrack","metrics":{"AUC":"0.705"},"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":10,"model":"MixFormer","metrics":{"AUC":"0.704","Precision":"0.918"},"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":11,"model":"KeepTrack","metrics":{"AUC":"0.697"},"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":12,"model":"SeqTrack-L384","metrics":{"AUC":"0.685"},"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":13,"model":"TRASFUST","metrics":{"AUC":"0.679","Precision":"0.873"},"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":14,"model":"ATOM(Resnet18)+EnergyRegression","metrics":{"AUC":"0.672"},"uses_additional_data":false,"paper_date":"2019-09-26","paper":"/paper/dctd-deep-conditional-target-densities-for","paper_url":"https://arxiv.org/abs/1909.12297v4","paper_title":"Energy-Based Models for Deep Probabilistic Regression","code":"https://github.com/fregu856/ebms_regression","n_code_links":2,"syntology":null},{"rank_in_archive_order":15,"model":"DiMP-NCE+","metrics":{"AUC":"0.672"},"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":16,"model":"TREG","metrics":{"AUC":"0.669","Precision":"0.884"},"uses_additional_data":false,"paper_date":"2021-04-01","paper":"/paper/target-transformed-regression-for-accurate","paper_url":"https://arxiv.org/abs/2104.00403v1","paper_title":"Target Transformed Regression for Accurate Tracking","code":"https://github.com/MCG-NJU/TREG","n_code_links":1,"syntology":null}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"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":7,"rows_with_any_sample_ran":4,"distinct_papers_with_graph_line":6,"distinct_papers_with_any_sample_ran":3,"samples_over_distinct_papers":{"n_ran":5,"n_unverified":9,"n_samples":14,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":8,"n_unverified":11,"n_samples":19,"n_pointer_only_licence":0,"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"}}}