Papers › AiATrack: Attention in Attention for Transformer Visual Tracking

AiATrack: Attention in Attention for Transformer Visual Tracking

20 Jul 2022arXiv:2207.09603archive 2025-07-28

Shenyuan Gao, Chunluan Zhou, Chao Ma, Xinggang Wang, Junsong Yuan

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.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2207.09603")

Code

Syntology Ran 1 of 3 code samples harvested from 1 repository linked to this paper; 2 have no recorded run. Of those that ran: 1 ran with no contract checked.

By repository: official repository: 3 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Little-Podi/AiATrack officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

3 samples harvested; 1 ran; 0 honoured the contract we drafted; 2 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran
2unverified

Licence: 0 of the 3 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from Little-Podi/AiATrack. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

InnerAttention Little-Podi/AiATrack/lib/models/aiatrack/attention.py official repository ran · metamorphic tier: deterministic MIT (permissive) · e90e317fcb5abb2d · report
AiAModule Little-Podi/AiATrack/lib/models/aiatrack/attention.py official repository unverified MIT (permissive) · 722bc19b1474dad5 · report
CorrAttention Little-Podi/AiATrack/lib/models/aiatrack/attention.py official repository unverified MIT (permissive) · 18443b8209886f1e · report

Tasks

Object TrackingVideo Object TrackingVisual Object TrackingVisual Tracking

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Tracking COESOT AiATrack Precision Rate 67.4 #10 of 12 Archive leaderboard report
Object Tracking COESOT AiATrack Success Rate 59.0 #10 of 12 Archive leaderboard report
Video Object Tracking NT-VOT211 AiATrack AUC 38.91 #7 of 43 Archive leaderboard report
Video Object Tracking NT-VOT211 AiATrack Precision 53.47 #7 of 43 Archive leaderboard report
Visual Object Tracking GOT-10k AiATrack Average Overlap 69.6 #28 of 42 Archive leaderboard report
Visual Object Tracking GOT-10k AiATrack Success Rate 0.5 80.0 #28 of 42 Archive leaderboard report
Visual Object Tracking GOT-10k AiATrack Success Rate 0.75 63.2 #28 of 42 Archive leaderboard report
Visual Object Tracking LaSOT AiATrack AUC 69.0 #32 of 46 Archive leaderboard report
Visual Object Tracking LaSOT AiATrack Normalized Precision 79.4 #32 of 46 Archive leaderboard report
Visual Object Tracking LaSOT AiATrack Precision 73.8 #32 of 46 Archive leaderboard report
Visual Object Tracking NeedForSpeed AiATrack AUC 0.679 #6 of 10 Archive leaderboard report
Visual Object Tracking OTB-100 AiATrack AUC 0.696 #2 of 2 Archive leaderboard report
Visual Object Tracking TrackingNet AiATrack Accuracy 82.7 #26 of 40 Archive leaderboard report
Visual Object Tracking TrackingNet AiATrack Normalized Precision 87.8 #26 of 40 Archive leaderboard report
Visual Object Tracking TrackingNet AiATrack Precision 80.4 #26 of 40 Archive leaderboard report
Visual Object Tracking UAV123 AiATrack AUC 0.706 #8 of 16 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections