AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Free Lunch for Gait Recognition: A Novel Relation Descriptor

Jilong Wang, Saihui Hou, Yan Huang, Chunshui Cao, Xu Liu, Yongzhen Huang, Tianzhu Zhang, Liang Wang

ECCV 2024 · Label-efficient and robust learning › Recognition and long-tail · approach: Margin-based face recognition losses · 11 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
replace embedding with relation descriptor, FAS and SVDGaitBase · GREWRank-1 accuracy (%): 60.1 -> 65.5Improved
replace embedding with relation descriptor and FASGaitBase · Gait3DRank-1 accuracy (%): 64.6 -> 70.1Improved
use relation descriptor on OU-MVLPGaitBase · OU-MVLPmean rank-1 accuracy (%): 90.8 -> 91.3Improved
use plain relation descriptor with only 74 anchors (ablation)GaitGL · CASIA-Bmean accuracy (%): 92.8 -> 91.4Hurt
add orthogonal regularization loss to relation descriptor (ablation)GaitGL · CASIA-Bmean accuracy (%): 91.4 -> 93.4Improved
use plain relation descriptor with all classifier weights as anchors (ablation)GaitBase · Gait3DRank-1 accuracy (%): 64.6 -> 68.8Improved
add Farthest gait-Anchor Selection (ablation)relation descriptor on GaitBase · Gait3DRank-1 accuracy (%): 68.8 -> 70.1Improved
apply relation descriptor to other backbonesGaitSet, GaitPart, GaitGL · Gait3DRank-1 accuracy (%): 36.7 -> 42.5, 28.2 -> 38.0, 29.7 -> 37.1Improved
vary number of selected anchors N, and use all weights or too few (ablation)FAS · Gait3DRank-1 accuracy (%)Mixed
select anchors with FAS instead of randomly (ablation)relation descriptor · Gait3DRank-1 accuracy (%)Improved
use relation descriptor instead of embedding in cross-domain testingGaitBase · cross-domain (Gait3D to CCPG)Rank-1 accuracy (%): +7.0%Improved
use relation descriptor on CASIA-B with GaitBaseGaitBase · CASIA-Bmean rank-1 accuracy (%): 94.0 -> 94.1 (BG), 77.4 -> 77.9 (CL)No clear effect

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