Papers › MixFormer: End-to-End Tracking with Iterative Mixed Attention

MixFormer: End-to-End Tracking with Iterative Mixed Attention

21 Mar 2022CVPR 2022 1arXiv:2203.11082archive 2025-07-28

Yutao Cui, Cheng Jiang, LiMin Wang, Gangshan Wu

Tracking often uses a multi-stage pipeline of feature extraction, target information integration, and bounding box estimation. To simplify this pipeline and unify the process of feature extraction and target information integration, we present a compact tracking framework, termed as MixFormer, built upon transformers. Our core design is to utilize the flexibility of attention operations, and propose a Mixed Attention Module (MAM) for simultaneous feature extraction and target information integration. This synchronous modeling scheme allows to extract target-specific discriminative features and perform extensive communication between target and search area. Based on MAM, we build our MixFormer tracking framework simply by stacking multiple MAMs with progressive patch embedding and placing a localization head on top. In addition, to handle multiple target templates during online tracking, we devise an asymmetric attention scheme in MAM to reduce computational cost, and propose an effective score prediction module to select high-quality templates. Our MixFormer sets a new state-of-the-art performance on five tracking benchmarks, including LaSOT, TrackingNet, VOT2020, GOT-10k, and UAV123. In particular, our MixFormer-L achieves NP score of 79.9% on LaSOT, 88.9% on TrackingNet and EAO of 0.555 on VOT2020. We also perform in-depth ablation studies to demonstrate the effectiveness of simultaneous feature extraction and information integration. Code and trained models are publicly available at https://github.com/MCG-NJU/MixFormer.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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="2203.11082")

Code

Syntology Ran 1 of 1 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 1 ran with no contract checked.

By repository: official repository: 1 sample 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.

MCG-NJU/MixFormer 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

1 sample harvested; 1 ran; 0 honoured the contract we drafted; 0 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

1ran

Licence: 0 of the 1 sample 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 MCG-NJU/MixFormer. “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.

MixFormer MCG-NJU/MixFormer/lib/models/mixformer_cvt/mixformer.py official repository ran MIT (permissive) · d59f9f66befc71af · report

Tasks

Semi-Supervised Video Object SegmentationVideo Object TrackingVisual Object Tracking

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semi-Supervised Video Object Segmentation VOT2020 MixFormer-L EAO 0.555 #14 of 20 Archive leaderboard report
Video Object Tracking NT-VOT211 Mixformer(ConvMAE) AUC 39.23 #6 of 43 Archive leaderboard report
Video Object Tracking NT-VOT211 Mixformer(ConvMAE) Precision 54.20 #6 of 43 Archive leaderboard report
Visual Object Tracking AVisT MixFormerL-22k Success Rate 56.0 #3 of 7 Archive leaderboard report
Visual Object Tracking GOT-10k MixFormer-L Average Overlap 75.6 #21 of 42 Archive leaderboard report
Visual Object Tracking GOT-10k MixFormer-L Success Rate 0.5 85.73 #21 of 42 Archive leaderboard report
Visual Object Tracking GOT-10k MixFormer-L Success Rate 0.75 72.8 #21 of 42 Archive leaderboard report
Visual Object Tracking GOT-10k MixFormer-1k Average Overlap 71.2 #25 of 42 Archive leaderboard report
Visual Object Tracking GOT-10k MixFormer-1k Success Rate 0.5 79.9 #25 of 42 Archive leaderboard report
Visual Object Tracking GOT-10k MixFormer-1k Success Rate 0.75 65.8 #25 of 42 Archive leaderboard report
Visual Object Tracking GOT-10k MixFormer Average Overlap 70.7 #27 of 42 Archive leaderboard report
Visual Object Tracking GOT-10k MixFormer Success Rate 0.5 80.0 #27 of 42 Archive leaderboard report
Visual Object Tracking GOT-10k MixFormer Success Rate 0.75 67.8 #27 of 42 Archive leaderboard report
Visual Object Tracking LaSOT MixFormer-L AUC 70.1 #30 of 46 Archive leaderboard report
Visual Object Tracking LaSOT MixFormer-L Normalized Precision 79.9 #30 of 46 Archive leaderboard report
Visual Object Tracking LaSOT MixFormer-L Precision 76.3 #30 of 46 Archive leaderboard report
Visual Object Tracking TrackingNet MixFormer-L Accuracy 83.9 #19 of 40 Archive leaderboard report
Visual Object Tracking TrackingNet MixFormer-L Normalized Precision 88.9 #19 of 40 Archive leaderboard report
Visual Object Tracking TrackingNet MixFormer-L Precision 83.1 #19 of 40 Archive leaderboard report
Visual Object Tracking UAV123 MixFormer AUC 0.704 #10 of 16 Archive leaderboard report
Visual Object Tracking UAV123 MixFormer Precision 0.918 #10 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.

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