AI Paper Atlas

Research map / Video / Action recognition

GaitSnippet: Gait Recognition Beyond Unordered Sets and Ordered Sequences

Saihui Hou, Chenye Wang, Wenpeng Lang, Zhengxiang Lan, Yongzhen Huang

ICLR 2026 · Video › Action recognition · approach: Skeleton-based action recognition

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Snippet Sampling instead of set sampling (ablation)DeepGaitV2-2D · Gait3Drank-1: 68.2 -> 69.5Improved
sequence-based continuous sampling instead of set sampling (ablation)DeepGaitV2-2D · Gait3Drank-1: 68.2 -> 66.0Hurt
add Gathering (intra-snippet pooling and snippet-level supervision) (ablation)GaitSnippet · Gait3Drank-1: 73.3 -> 77.5Improved
add smoothing 1x1 conv layer after Gathering (ablation)GaitSnippet · Gait3Drank-1: 74.8 -> 77.5Improved
add residual merge of snippet context with frame features (ablation)GaitSnippet · Gait3Drank-1: 72.5 -> 77.5Improved
add snippet-level supervision (alpha 0 to 0.75) (ablation)GaitSnippet · Gait3Drank-1: 75.8 -> 77.5Improved
share weights between sequence-level and snippet-level branches (ablation)GaitSnippet · Gait3Drank-1: 77.5 -> 75.5Hurt
segment length L=16 versus 8 or 32 (ablation)GaitSnippet · Gait3Drank-1: 76.4 (L=8), 74.7 (L=32) -> 77.5Improved
N=8 frames per snippet versus 4 or 16 (ablation)GaitSnippet · Gait3Drank-1: 74.3 (N=4), 75.2 (N=16) -> 77.5Improved
ensemble of multiple segment partitions at evaluation (L1 in {8,16}) (ablation)GaitSnippet · Gait3DmAP: 69.4 -> 69.8No clear effect
evaluate with snippet-level instead of sequence-level features (ablation)GaitSnippet · Gait3Drank-1: 77.5 -> 65.2Hurt
add snippet sampling and Snippet Block to GaitSet (ablation)GaitSet · Gait3Drank-1: 36.7 -> 48.2Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy