{"url":"/sota/visual-object-tracking-on-needforspeed","task":{"name":"Visual Object Tracking","url":"/task/visual-object-tracking","note":null},"dataset":{"name":"NeedForSpeed","url":null},"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"],"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"}},"counts":{"rows":10,"rows_with_code":10,"rows_with_paper_page":10,"rows_dated":10,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"SAMURAI-L","metrics":{"AUC":"0.692"},"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":2,"model":"ARTrackV2-L","metrics":{"AUC":"0.684"},"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":3,"model":"PiVOT-L","metrics":{"AUC":"0.682"},"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":4,"model":"HIPTrack","metrics":{"AUC":"0.681"},"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":5,"model":"LoRAT-g-378","metrics":{"AUC":"0.681"},"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":6,"model":"AiATrack","metrics":{"AUC":"0.679"},"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":7,"model":"SPMTrack-B","metrics":{"AUC":"0.674"},"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":8,"model":"LoRAT-L-378","metrics":{"AUC":"0.667"},"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":9,"model":"SeqTrack-L384","metrics":{"AUC":"0.662"},"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":10,"model":"DiMP-NCE+","metrics":{"AUC":"0.65"},"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}}],"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":6,"rows_with_any_sample_ran":4,"distinct_papers_with_graph_line":5,"distinct_papers_with_any_sample_ran":3,"samples_over_distinct_papers":{"n_ran":5,"n_unverified":8,"n_samples":13,"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":10,"n_samples":18,"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"}}}