Papers › GaitMixer: Skeleton-based Gait Representation Learning via Wide-spectrum Multi-axial Mixer

GaitMixer: Skeleton-based Gait Representation Learning via Wide-spectrum Multi-axial Mixer

27 Oct 2022arXiv:2210.15491archive 2025-07-28

Ekkasit Pinyoanuntapong, Ayman Ali, Pu Wang, Minwoo Lee, Chen Chen

Most existing gait recognition methods are appearance-based, which rely on the silhouettes extracted from the video data of human walking activities. The less-investigated skeleton-based gait recognition methods directly learn the gait dynamics from 2D/3D human skeleton sequences, which are theoretically more robust solutions in the presence of appearance changes caused by clothes, hairstyles, and carrying objects. However, the performance of skeleton-based solutions is still largely behind the appearance-based ones. This paper aims to close such performance gap by proposing a novel network model, GaitMixer, to learn more discriminative gait representation from skeleton sequence data. In particular, GaitMixer follows a heterogeneous multi-axial mixer architecture, which exploits the spatial self-attention mixer followed by the temporal large-kernel convolution mixer to learn rich multi-frequency signals in the gait feature maps. Experiments on the widely used gait database, CASIA-B, demonstrate that GaitMixer outperforms the previous SOTA skeleton-based methods by a large margin while achieving a competitive performance compared with the representative appearance-based solutions. Code will be available at https://github.com/exitudio/gaitmixer

PaperPDFCode

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

Code

exitudio/gaitmixer 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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Gait RecognitionMultiview Gait RecognitionRepresentation Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Multiview Gait Recognition CASIA-B GaitMixer Accuracy (Cross-View, Avg) 88.3 #9 of 12 Archive leaderboard report
Multiview Gait Recognition CASIA-B GaitMixer BG#1-2 85.6 #9 of 12 Archive leaderboard report
Multiview Gait Recognition CASIA-B GaitMixer CL#1-2 84.5 #9 of 12 Archive leaderboard report
Multiview Gait Recognition CASIA-B GaitMixer NM#5-6 94.9 #9 of 12 Archive leaderboard report
Multiview Gait Recognition CASIA-B GaitFormer Accuracy (Cross-View, Avg) 83.4 #11 of 12 Archive leaderboard report
Multiview Gait Recognition CASIA-B GaitFormer BG#1-2 81.4 #11 of 12 Archive leaderboard report
Multiview Gait Recognition CASIA-B GaitFormer CL#1-2 77.2 #11 of 12 Archive leaderboard report
Multiview Gait Recognition CASIA-B GaitFormer NM#5-6 91.5 #11 of 12 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 EncodingsAdamAttentionBPEConvolutionDense 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