{"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/aiatrack-attention-in-attention-for","title":"AiATrack: Attention in Attention for Transformer Visual Tracking","arxiv_id":"2207.09603","date":"2022-07-20","proceeding":null,"authors":["Shenyuan Gao","Chunluan Zhou","Chao Ma","Xinggang Wang","Junsong Yuan"],"abstract":"Transformer trackers have achieved impressive advancements recently, where the attention mechanism plays an important role. However, the independent correlation computation in the attention mechanism could result in noisy and ambiguous attention weights, which inhibits further performance improvement. To address this issue, we propose an attention in attention (AiA) module, which enhances appropriate correlations and suppresses erroneous ones by seeking consensus among all correlation vectors. Our AiA module can be readily applied to both self-attention blocks and cross-attention blocks to facilitate feature aggregation and information propagation for visual tracking. Moreover, we propose a streamlined Transformer tracking framework, dubbed AiATrack, by introducing efficient feature reuse and target-background embeddings to make full use of temporal references. Experiments show that our tracker achieves state-of-the-art performance on six tracking benchmarks while running at a real-time speed.","url_abs":"https://arxiv.org/abs/2207.09603v2","url_pdf":"https://arxiv.org/pdf/2207.09603v2.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":"aiatrack-attention-in-attention-for","repo_url":"https://github.com/Little-Podi/AiATrack","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"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":"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/object-tracking-on-coesot","task":"Object Tracking","dataset":"COESOT","model":"AiATrack","rank_in_archive_order":10,"of":12,"metrics":{"Precision Rate":"67.4","Success Rate":"59.0"},"uses_additional_data":false},{"leaderboard":"/sota/video-object-tracking-on-nv-vot211","task":"Video Object Tracking","dataset":"NT-VOT211","model":"AiATrack","rank_in_archive_order":7,"of":43,"metrics":{"AUC":"38.91","Precision":"53.47"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-got-10k","task":"Visual Object Tracking","dataset":"GOT-10k","model":"AiATrack","rank_in_archive_order":28,"of":42,"metrics":{"Average Overlap":"69.6","Success Rate 0.5":"80.0","Success Rate 0.75":"63.2"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-lasot","task":"Visual Object Tracking","dataset":"LaSOT","model":"AiATrack","rank_in_archive_order":32,"of":46,"metrics":{"AUC":"69.0","Normalized Precision":"79.4","Precision":"73.8"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-needforspeed","task":"Visual Object Tracking","dataset":"NeedForSpeed","model":"AiATrack","rank_in_archive_order":6,"of":10,"metrics":{"AUC":"0.679"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-otb-100","task":"Visual Object Tracking","dataset":"OTB-100","model":"AiATrack","rank_in_archive_order":2,"of":2,"metrics":{"AUC":"0.696"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-trackingnet","task":"Visual Object Tracking","dataset":"TrackingNet","model":"AiATrack","rank_in_archive_order":26,"of":40,"metrics":{"Accuracy":"82.7","Normalized Precision":"87.8","Precision":"80.4"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-uav123","task":"Visual Object Tracking","dataset":"UAV123","model":"AiATrack","rank_in_archive_order":8,"of":16,"metrics":{"AUC":"0.706"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2207.09603","atlas_url":"https://app.syntology.ai/?focus=2207.09603","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.09603"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/Little-Podi/AiATrack","reach":null}],"summary":{"ran":1,"unverified":2},"by_repo_kind":{"official":{"samples":3,"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":"e90e317fcb5abb2d","entry":"InnerAttention","repo":"Little-Podi/AiATrack","repo_kind":"official","path":"lib/models/aiatrack/attention.py","file_url":"https://github.com/Little-Podi/AiATrack/blob/HEAD/lib/models/aiatrack/attention.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":"e90e317fcb5abb2d"}},{"code_sha256_prefix":"722bc19b1474dad5","entry":"AiAModule","repo":"Little-Podi/AiATrack","repo_kind":"official","path":"lib/models/aiatrack/attention.py","file_url":"https://github.com/Little-Podi/AiATrack/blob/HEAD/lib/models/aiatrack/attention.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":"722bc19b1474dad5"}},{"code_sha256_prefix":"18443b8209886f1e","entry":"CorrAttention","repo":"Little-Podi/AiATrack","repo_kind":"official","path":"lib/models/aiatrack/attention.py","file_url":"https://github.com/Little-Podi/AiATrack/blob/HEAD/lib/models/aiatrack/attention.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":"18443b8209886f1e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}