AI Paper Atlas

Research map / Video / Action recognition

Context-Sensitive Temporal Feature Learning for Gait Recognition

Xiaohu Huang, Duowang Zhu, Hao Wang, Xinggang Wang, Bo Yang, Botao He, Wenyu Liu, Bin Feng

ICCV 2021 · Video › Action recognition · approach: Skeleton-based action recognition · 205 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 multi-scale temporal extraction (MSTE) (ablation)Baseline · CASIA-B meanMean rank-1 accuracy (%): 85.4 -> 89.6Improved
add adaptive temporal aggregation (ATA) to MSTE (ablation)Baseline + MSTE · CASIA-B meanMean rank-1 accuracy (%): 89.6 -> 90.1Improved
add salient spatial feature learning (SSFL) to MSTE (ablation)Baseline + MSTE · CASIA-B meanMean rank-1 accuracy (%): 89.6 -> 91.1Improved
add SSFL on top of MSTE and ATA (ablation)Baseline + MSTE + ATA · CASIA-B meanMean rank-1 accuracy (%): 90.1 -> 91.9Improved
add ATA to MSTE on the coat-wearing condition (ablation)Baseline + MSTE · CASIA-B CL probeRank-1 accuracy (%): 81.0 -> 79.1Hurt
add SSFL to MSTE on the coat-wearing condition (ablation)Baseline + MSTE · CASIA-B CL probeRank-1 accuracy (%): 81.0 -> 83.7Improved
use all three temporal scales instead of short-term only (ablation)CSTL · CASIA-B meanMean rank-1 accuracy (%): 90.2 -> 91.9Improved
use long-term features alone instead of frame-level alone (ablation)CSTL · CASIA-B meanMean rank-1 accuracy (%): 88.5 -> 87.5Hurt
use short-term features alone instead of frame-level alone (ablation)CSTL · CASIA-B meanMean rank-1 accuracy (%): 88.5 -> 90.2Improved
use ATA instead of max pooling (ablation)CSTL · CASIA-B meanMean rank-1 accuracy (%): 91.1 -> 91.9Improved
use ATA instead of average pooling (ablation)CSTL · CASIA-B meanMean rank-1 accuracy (%): 90.6 -> 91.9Improved
use max pooling instead of average pooling (ablation)CSTL · CASIA-B meanMean rank-1 accuracy (%): 90.6 -> 91.1Improved

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