{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/joint-feature-learning-and-relation-modeling","title":"Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework","arxiv_id":"2203.11991","date":"2022-03-22","proceeding":null,"authors":["Botao Ye","Hong Chang","Bingpeng Ma","Shiguang Shan","Xilin Chen"],"abstract":"The current popular two-stream, two-stage tracking framework extracts the template and the search region features separately and then performs relation modeling, thus the extracted features lack the awareness of the target and have limited target-background discriminability. To tackle the above issue, we propose a novel one-stream tracking (OSTrack) framework that unifies feature learning and relation modeling by bridging the template-search image pairs with bidirectional information flows. In this way, discriminative target-oriented features can be dynamically extracted by mutual guidance. Since no extra heavy relation modeling module is needed and the implementation is highly parallelized, the proposed tracker runs at a fast speed. To further improve the inference efficiency, an in-network candidate early elimination module is proposed based on the strong similarity prior calculated in the one-stream framework. As a unified framework, OSTrack achieves state-of-the-art performance on multiple benchmarks, in particular, it shows impressive results on the one-shot tracking benchmark GOT-10k, i.e., achieving 73.7% AO, improving the existing best result (SwinTrack) by 4.3\\%. Besides, our method maintains a good performance-speed trade-off and shows faster convergence. The code and models are available at https://github.com/botaoye/OSTrack.","url_abs":"https://arxiv.org/abs/2203.11991v4","url_pdf":"https://arxiv.org/pdf/2203.11991v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"joint-feature-learning-and-relation-modeling","repo_url":"https://github.com/botaoye/ostrack","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"object-tracking","task_name":"Object Tracking"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"video-object-tracking","task_name":"Video Object Tracking"},{"task_slug":"visual-object-tracking","task_name":"Visual Object Tracking"},{"task_slug":"visual-tracking","task_name":"Visual Tracking"}],"methods":[{"method_slug":"ao","method_name":"AO"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/object-tracking-on-coesot","task":"Object Tracking","dataset":"COESOT","model":"OSTrack","rank_in_archive_order":11,"of":12,"metrics":{"Precision Rate":"66.6","Success Rate":"59.0"},"uses_additional_data":false},{"leaderboard":"/sota/video-object-tracking-on-nv-vot211","task":"Video Object Tracking","dataset":"NT-VOT211","model":"OSTrack-384","rank_in_archive_order":8,"of":43,"metrics":{"AUC":"38.59","Precision":"53.06"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-got-10k","task":"Visual Object Tracking","dataset":"GOT-10k","model":"OSTrack-384","rank_in_archive_order":23,"of":42,"metrics":{"Average Overlap":"73.7","Success Rate 0.5":"83.2","Success Rate 0.75":"70.8"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-lasot","task":"Visual Object Tracking","dataset":"LaSOT","model":"OSTrack-384","rank_in_archive_order":24,"of":46,"metrics":{"AUC":"71.1","Normalized Precision":"81.1","Precision":"77.6"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-lasot-ext","task":"Visual Object Tracking","dataset":"LaSOT-ext","model":"OSTrack","rank_in_archive_order":16,"of":18,"metrics":{"AUC":"50.6","Normalized Precision":"61.3","Precision":"57.6"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-trackingnet","task":"Visual Object Tracking","dataset":"TrackingNet","model":"OSTrack-384","rank_in_archive_order":20,"of":40,"metrics":{"Accuracy":"83.9","Normalized Precision":"88.5","Precision":"83.2"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-uav123","task":"Visual Object Tracking","dataset":"UAV123","model":"OSTrack -384","rank_in_archive_order":7,"of":16,"metrics":{"AUC":"0.707"},"uses_additional_data":false},{"leaderboard":"/sota/visual-tracking-on-tnl2k","task":"Visual Tracking","dataset":"TNL2K","model":"OSTrack","rank_in_archive_order":4,"of":6,"metrics":{"AUC":"55.9"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2203.11991","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.11991"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/botaoye/ostrack","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/botaoye/OSTrack","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"98484d88923ea9d9","entry":"OSTrack","repo":"botaoye/OSTrack","repo_kind":"official","path":"lib/models/ostrack/ostrack.py","file_url":"https://github.com/botaoye/OSTrack/blob/HEAD/lib/models/ostrack/ostrack.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"98484d88923ea9d9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}