AI Paper Atlas

Research map / Video / Action recognition

GaitPart: Temporal Part-Based Model for Gait Recognition

Chao Fan, Yunjie Peng, Chunshui Cao, Xu Liu, Saihui Hou, Jiannan Chi, Yongzhen Huang, Qing Li, Zhiqiang He

CVPR 2020 · Video › Action recognition · approach: Skeleton-based action recognition · 584 citations (OpenAlex)

Check 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
Use GaitPart instead of GaitSetGait recognition · CASIA-B NM#5-6rank-1 accuracy: 95.0 -> 96.2Improved
Use GaitPart instead of GaitSetGait recognition · CASIA-B BG#1-2rank-1 accuracy: 87.2 -> 91.5Improved
Use GaitPart instead of GaitSetGait recognition · CASIA-B CL#1-2rank-1 accuracy: 70.4 -> 78.7Improved
Use GaitPart instead of GaitSetGait recognition · OU-MVLPmean rank-1 accuracy: 87.1 -> 88.7Improved
Add Focal Convolution in deeper blocks (ablation)GaitPart · CASIA-B BGrank-1 accuracy: 88.4 -> 91.5Improved
Add Focal Convolution in deeper blocks (ablation)GaitPart · CASIA-B CLrank-1 accuracy: 76.1 -> 78.7Improved
Add Focal Convolution to block 1 (ablation)GaitPart · CASIA-B NMrank-1 accuracy: 96.2 -> 95.8Hurt
Use both MTB scales (window sizes 3 and 5) (ablation)GaitPart MCM · CASIA-B BGrank-1 accuracy: 90.8 -> 91.5Improved
Add channel-wise attention to MTB (ablation)GaitPart MCM · CASIA-B CLrank-1 accuracy: 73.1 -> 78.7Improved
Use max rather than mean temporal pooling (ablation)GaitPart MCM · CASIA-B CLrank-1 accuracy: 70.1 -> 78.7Improved
Preserve temporal order instead of shuffling frames (ablation)GaitPart · CASIA-B CLrank-1 accuracy: 71.5 -> 78.7Improved

Later papers that compared with this method

3 later accepted papers report GaitPart as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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