{"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/target-aware-tracking-with-long-term-context","title":"Target-Aware Tracking with Long-term Context Attention","arxiv_id":"2302.13840","date":"2023-02-27","proceeding":null,"authors":["Kaijie He","Canlong Zhang","Sheng Xie","Zhixin Li","Zhiwen Wang"],"abstract":"Most deep trackers still follow the guidance of the siamese paradigms and use a template that contains only the target without any contextual information, which makes it difficult for the tracker to cope with large appearance changes, rapid target movement, and attraction from similar objects. To alleviate the above problem, we propose a long-term context attention (LCA) module that can perform extensive information fusion on the target and its context from long-term frames, and calculate the target correlation while enhancing target features. The complete contextual information contains the location of the target as well as the state around the target. LCA uses the target state from the previous frame to exclude the interference of similar objects and complex backgrounds, thus accurately locating the target and enabling the tracker to obtain higher robustness and regression accuracy. By embedding the LCA module in Transformer, we build a powerful online tracker with a target-aware backbone, termed as TATrack. In addition, we propose a dynamic online update algorithm based on the classification confidence of historical information without additional calculation burden. Our tracker achieves state-of-the-art performance on multiple benchmarks, with 71.1\\% AUC, 89.3\\% NP, and 73.0\\% AO on LaSOT, TrackingNet, and GOT-10k. The code and trained models are available on https://github.com/hekaijie123/TATrack.","url_abs":"https://arxiv.org/abs/2302.13840v1","url_pdf":"https://arxiv.org/pdf/2302.13840v1.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":"target-aware-tracking-with-long-term-context","repo_url":"https://github.com/hekaijie123/TATrack","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"object-tracking","task_name":"Object Tracking"},{"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"},{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-object-tracking-on-got-10k-1","task":"Video Object Tracking","dataset":"GOT-10k","model":"TATrack-L-GOT","rank_in_archive_order":1,"of":1,"metrics":{"Average Overlap":"76.6"},"uses_additional_data":false},{"leaderboard":"/sota/video-object-tracking-on-nv-vot211","task":"Video Object Tracking","dataset":"NT-VOT211","model":"TATrack-L","rank_in_archive_order":4,"of":43,"metrics":{"AUC":"39.29","Precision":"53.94"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-got-10k","task":"Visual Object Tracking","dataset":"GOT-10k","model":"TATrack-L-GOT","rank_in_archive_order":16,"of":42,"metrics":{"Average Overlap":"76.6","Success Rate 0.5":"85.7","Success Rate 0.75":"73.4"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-lasot","task":"Visual Object Tracking","dataset":"LaSOT","model":"TATrack-L","rank_in_archive_order":25,"of":46,"metrics":{"AUC":"71.1","Normalized Precision":"79.1","Precision":"76.1"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-trackingnet","task":"Visual Object Tracking","dataset":"TrackingNet","model":"TATrack-L","rank_in_archive_order":16,"of":40,"metrics":{"Accuracy":"85.0","Normalized Precision":"89.3","Precision":"84.5"},"uses_additional_data":false},{"leaderboard":"/sota/visual-tracking-on-lasot","task":"Visual Tracking","dataset":"LaSOT","model":"TATrack-L","rank_in_archive_order":1,"of":1,"metrics":{"AUC":"71.1"},"uses_additional_data":false},{"leaderboard":"/sota/visual-tracking-on-trackingnet","task":"Visual Tracking","dataset":"TrackingNet","model":"TATrack-L","rank_in_archive_order":1,"of":1,"metrics":{"ACCURACY":"0.85","Normalized Precision":"89.3"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2302.13840","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.13840"}},"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":"deterministic:regex_extraction","url":"https://github.com/hekaijie123/TATrack","reach":null}],"summary":{"unverified":2},"by_repo_kind":{"official":{"samples":2,"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":"2eb5f6eed1194c08","entry":"ModuleBase","repo":"hekaijie123/TATrack","repo_kind":"official","path":"videoanalyst/model/task_model/taskmodel_impl/tatrack_model.py","file_url":"https://github.com/hekaijie123/TATrack/blob/HEAD/videoanalyst/model/task_model/taskmodel_impl/tatrack_model.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":"2eb5f6eed1194c08"}},{"code_sha256_prefix":"afe3fcef6c53e280","entry":"TATrack","repo":"hekaijie123/TATrack","repo_kind":"official","path":"videoanalyst/model/task_model/taskmodel_impl/tatrack_model.py","file_url":"https://github.com/hekaijie123/TATrack/blob/HEAD/videoanalyst/model/task_model/taskmodel_impl/tatrack_model.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":"afe3fcef6c53e280"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}