AI Paper Atlas

Research map / Video / Action recognition

Hierarchical Spatio-Temporal Representation Learning for Gait Recognition

Lei Wang, Bo Liu, Fangfang Liang, Bincheng Wang

ICCV 2023 · Video › Action recognition · approach: Skeleton-based action recognition · 48 citations (OpenAlex)

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
add ARME (region-independent 3D convolutions) over the non-grouping baseline (ablation)HSTL · CASIA-Bmean rank-1 accuracy: 91.9 -> 93.0Improved
add ASTP on top of ARME (ablation)HSTL · CASIA-Bmean rank-1 accuracy: 93.0 -> 93.4Improved
add multi-scale FTA (scales 3 and 5) with ARME and ASTP (ablation)HSTL · CASIA-Bmean rank-1 accuracy: 93.4 -> 94.3Improved
use single-scale FTA (3 or 5) instead of multi-scale fusion (ablation)HSTL · CASIA-Bmean rank-1 accuracy: 94.3 -> 93.5 (scale 3), 93.4 (scale 5)Hurt
use hierarchical non-uniform grouping 1-2-4* rather than uniform 1-2-4 (ablation)HSTL · CASIA-Bmean rank-1 accuracy: +1.0%Improved
hierarchical grouping (1-2-4) instead of non-hierarchical grouping (e.g. 1-1-1) (ablation)HSTL · CASIA-Brank-1 accuracyImproved
HSTL versus MetaGait on clothing conditionHSTL · CASIA-B CLmean rank-1 accuracy: 86.9 -> 88.9Improved
HSTL versus MetaGait on normal walkingHSTL · CASIA-B NMmean rank-1 accuracy: 98.1 -> 98.1No clear effect
HSTL versus MTSGait in the wildHSTL · GREWRank-1 accuracy: 55.32 -> 62.72Improved
HSTL versus MTSGait in uncontrolled indoor scenesHSTL · Gait3DRank-1 accuracy: 48.70 -> 61.30Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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