{"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-tracking-with-cyclic-shifting","title":"Transformer Tracking with Cyclic Shifting Window Attention","arxiv_id":"2205.03806","date":"2022-05-08","proceeding":"CVPR 2022 1","authors":["Zikai Song","Junqing Yu","Yi-Ping Phoebe Chen","Wei Yang"],"abstract":"Transformer architecture has been showing its great strength in visual object tracking, for its effective attention mechanism. Existing transformer-based approaches adopt the pixel-to-pixel attention strategy on flattened image features and unavoidably ignore the integrity of objects. In this paper, we propose a new transformer architecture with multi-scale cyclic shifting window attention for visual object tracking, elevating the attention from pixel to window level. The cross-window multi-scale attention has the advantage of aggregating attention at different scales and generates the best fine-scale match for the target object. Furthermore, the cyclic shifting strategy brings greater accuracy by expanding the window samples with positional information, and at the same time saves huge amounts of computational power by removing redundant calculations. Extensive experiments demonstrate the superior performance of our method, which also sets the new state-of-the-art records on five challenging datasets, along with the VOT2020, UAV123, LaSOT, TrackingNet, and GOT-10k benchmarks.","url_abs":"https://arxiv.org/abs/2205.03806v1","url_pdf":"https://arxiv.org/pdf/2205.03806v1.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-tracking-with-cyclic-shifting","repo_url":"https://github.com/skyesong38/cswintt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-tracking","task_name":"Object Tracking"},{"task_slug":"visual-object-tracking","task_name":"Visual Object Tracking"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2205.03806","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.03806"}},"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/skyesong38/cswintt","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/SkyeSong38/CSWinTT","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"unverified":3},"by_repo_kind":{"official":{"samples":4,"ran":1,"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":"4d8dc443ac7d55fa","entry":"TransformerDecoderLayer","repo":"SkyeSong38/CSWinTT","repo_kind":"official","path":"lib/models/cswintt/transformer_cs.py","file_url":"https://github.com/SkyeSong38/CSWinTT/blob/HEAD/lib/models/cswintt/transformer_cs.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4d8dc443ac7d55fa"}},{"code_sha256_prefix":"59d31f3151914df3","entry":"Attention","repo":"SkyeSong38/CSWinTT","repo_kind":"official","path":"lib/models/cswintt/transformer_cs.py","file_url":"https://github.com/SkyeSong38/CSWinTT/blob/HEAD/lib/models/cswintt/transformer_cs.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":"59d31f3151914df3"}},{"code_sha256_prefix":"9a4b8a925c8b46b4","entry":"TransformerLayer","repo":"SkyeSong38/CSWinTT","repo_kind":"official","path":"lib/models/cswintt/transformer_cs.py","file_url":"https://github.com/SkyeSong38/CSWinTT/blob/HEAD/lib/models/cswintt/transformer_cs.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":"9a4b8a925c8b46b4"}},{"code_sha256_prefix":"a2d427bbc37ec14c","entry":"Transformer_CS","repo":"SkyeSong38/CSWinTT","repo_kind":"official","path":"lib/models/cswintt/transformer_cs.py","file_url":"https://github.com/SkyeSong38/CSWinTT/blob/HEAD/lib/models/cswintt/transformer_cs.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":"a2d427bbc37ec14c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}