AI Paper Atlas

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

CarGait: Cross-Attention based Re-ranking for Gait recognition

Gavriel Habib, Noa Barzilay, Or Shimshi, Rami Ben-Ari, Nir Darshan

ICCV 2025 · Label-efficient and robust learning › Recognition and long-tail · approach: Margin-based face recognition losses · 4 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 cross-attention re-ranker CarGaitGaitBase · GREWRank-1: 60.1 -> 67.2Improved
add CarGait re-rankerSwinGait-3D · Gait3DRank-5: 86.7 -> 88.6Improved
add CarGait re-rankerDGV2-P3D · Gait3DRank-5: 88.0 -> 87.5Hurt
add CarGait instead of KR/LBR/GCR re-rankersSwinGait-3D · Gait3DRank-1: 76.3 vs 66.7, 64.0, 74.1Improved
apply KR or LBR re-ranker instead of CarGaitGaitBase · OU-MVLPRank-1: 90.8 -> 72.9 (KR), 74.4 (LBR)Hurt
add extra training of the global model (ablation)SwinGait-3D · Gait3DRank-1: 75.0 -> 75.0No clear effect
add cross-attention instead of binary classifier re-ranker (ablation)SwinGait-3D · Gait3DRank-1: 71.6 -> 76.3Improved
add classification loss (ablation)CarGait · Gait3DRank-1: 76.0 -> 76.3 R1; 89.1 -> 88.6 R5Mixed
add loss damping (beta=0.1) (ablation)CarGait · Gait3DRank-1: 75.5 -> 76.3Improved
use inference K=10 instead of K=5 (ablation)CarGait · Gait3DRank-5: 86.7 -> 88.6Improved
use inference K=20 instead of K=10 (ablation)CarGait · Gait3DmAP: 67.59 -> 67.68No clear effect
train with v=30 instead of v=20 or v=40 (ablation)CarGait · Gait3DRank-1: 76.3 (v=20), 76.0 (v=40) vs 76.3Mixed

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