{"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/transformer-meets-tracker-exploiting-temporal","title":"Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking","arxiv_id":"2103.11681","date":"2021-03-22","proceeding":"CVPR 2021 1","authors":["Ning Wang","Wengang Zhou","Jie Wang","Houqaing Li"],"abstract":"In video object tracking, there exist rich temporal contexts among successive frames, which have been largely overlooked in existing trackers. In this work, we bridge the individual video frames and explore the temporal contexts across them via a transformer architecture for robust object tracking. Different from classic usage of the transformer in natural language processing tasks, we separate its encoder and decoder into two parallel branches and carefully design them within the Siamese-like tracking pipelines. The transformer encoder promotes the target templates via attention-based feature reinforcement, which benefits the high-quality tracking model generation. The transformer decoder propagates the tracking cues from previous templates to the current frame, which facilitates the object searching process. Our transformer-assisted tracking framework is neat and trained in an end-to-end manner. With the proposed transformer, a simple Siamese matching approach is able to outperform the current top-performing trackers. By combining our transformer with the recent discriminative tracking pipeline, our method sets several new state-of-the-art records on prevalent tracking benchmarks.","url_abs":"https://arxiv.org/abs/2103.11681v2","url_pdf":"https://arxiv.org/pdf/2103.11681v2.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":"transformer-meets-tracker-exploiting-temporal","repo_url":"https://github.com/594422814/TransformerTrack","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"object","task_name":"Object"},{"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":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/object-tracking-on-coesot","task":"Object Tracking","dataset":"COESOT","model":"TrDiMP","rank_in_archive_order":8,"of":12,"metrics":{"Precision Rate":"66.9","Success Rate":"60.1"},"uses_additional_data":false},{"leaderboard":"/sota/video-object-tracking-on-nv-vot211","task":"Video Object Tracking","dataset":"NT-VOT211","model":"TrDiMP","rank_in_archive_order":14,"of":43,"metrics":{"AUC":"36.66","Precision":"50.68"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-lasot","task":"Visual Object Tracking","dataset":"LaSOT","model":"TrDiMP","rank_in_archive_order":39,"of":46,"metrics":{"AUC":"63.7","Precision":"61.4"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2103.11681","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.11681"}},"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/594422814/TransformerTrack","reach":null}],"summary":{"ran":5,"ran_draft_wrong":1,"unverified":3},"by_repo_kind":{"official":{"samples":9,"ran":6,"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":"c39d16d0426c394c","entry":"InstanceL2Norm","repo":"594422814/TransformerTrack","repo_kind":"official","path":"ltr/models/target_classifier/transformer.py","file_url":"https://github.com/594422814/TransformerTrack/blob/HEAD/ltr/models/target_classifier/transformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c39d16d0426c394c"}},{"code_sha256_prefix":"1b733e1fccc5d345","entry":"MultiheadAttention","repo":"594422814/TransformerTrack","repo_kind":"official","path":"ltr/models/target_classifier/transformer.py","file_url":"https://github.com/594422814/TransformerTrack/blob/HEAD/ltr/models/target_classifier/transformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1b733e1fccc5d345"}},{"code_sha256_prefix":"81552d44911a524a","entry":"TransformerDecoderLayer","repo":"594422814/TransformerTrack","repo_kind":"official","path":"ltr/models/target_classifier/transformer.py","file_url":"https://github.com/594422814/TransformerTrack/blob/HEAD/ltr/models/target_classifier/transformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"81552d44911a524a"}},{"code_sha256_prefix":"f9081530a58aa58c","entry":"TransformerEncoder","repo":"594422814/TransformerTrack","repo_kind":"official","path":"ltr/models/target_classifier/transformer.py","file_url":"https://github.com/594422814/TransformerTrack/blob/HEAD/ltr/models/target_classifier/transformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f9081530a58aa58c"}},{"code_sha256_prefix":"81d1975ee00caff6","entry":"TransformerEncoderLayer","repo":"594422814/TransformerTrack","repo_kind":"official","path":"ltr/models/target_classifier/transformer.py","file_url":"https://github.com/594422814/TransformerTrack/blob/HEAD/ltr/models/target_classifier/transformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"81d1975ee00caff6"}},{"code_sha256_prefix":"18c99336939119a2","entry":"_get_clones","repo":"594422814/TransformerTrack","repo_kind":"official","path":"ltr/models/target_classifier/transformer.py","file_url":"https://github.com/594422814/TransformerTrack/blob/HEAD/ltr/models/target_classifier/transformer.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"18c99336939119a2"}},{"code_sha256_prefix":"aad0f1f277edccd0","entry":"RelationUnit","repo":"594422814/TransformerTrack","repo_kind":"official","path":"ltr/models/target_classifier/transformer.py","file_url":"https://github.com/594422814/TransformerTrack/blob/HEAD/ltr/models/target_classifier/transformer.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":"aad0f1f277edccd0"}},{"code_sha256_prefix":"c072f3a3619491c0","entry":"Transformer","repo":"594422814/TransformerTrack","repo_kind":"official","path":"ltr/models/target_classifier/transformer.py","file_url":"https://github.com/594422814/TransformerTrack/blob/HEAD/ltr/models/target_classifier/transformer.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":"c072f3a3619491c0"}},{"code_sha256_prefix":"b5c213461ba61b6f","entry":"TransformerDecoder","repo":"594422814/TransformerTrack","repo_kind":"official","path":"ltr/models/target_classifier/transformer.py","file_url":"https://github.com/594422814/TransformerTrack/blob/HEAD/ltr/models/target_classifier/transformer.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":"b5c213461ba61b6f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}