AI Paper Atlas

Research map / Image generation / Image restoration

Gait Recognition from a Single Image using a Phase-Aware Gait Cycle Reconstruction Network

Chi Xu, Yasushi Makihara, Xiang Li, Yasushi Yagi, Jianfeng Lu

ECCV 2020 · Image generation › Image restoration · approach: Inverse imaging with learned priors · 30 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 PA-GCR gait cycle reconstruction (ablation)GaitSet · OU-MVLPRank-1 identification rate (%): 34.4 -> 80.3Improved
add unified (joint) training of PA-GCR and GaitSet (ablation)PA-GCRNet · OU-MVLPRank-1 identification rate (%): 50.5 -> 80.3Improved
add phase estimator, feature transformer and similarity loss (ablation)PA-GCRNet · OU-MVLPRank-1 identification rate (%): 77.4 -> 80.3Improved
use ground-truth phase instead of estimated phase (ablation)PA-GCRNet · OU-MVLPRank-1 identification rate (%): 80.3 -> 80.6No clear effect
feed ground-truth gait cycle instead of reconstruction (ablation)GaitSet · OU-MVLPRank-1 identification rate (%): 80.3 -> 97.7Improved
fine-tune PA-GCR from OU-MVLP pretrained model instead of training from scratchPA-GCRNet · CASIA-BRank-1 identification rate (%): 39.4 -> 74.7Improved
fine-tune PA-GCR from OU-MVLP pretrained model instead of training from scratchPA-GCRNet · OUTD-DRank-1 identification rate (%): 73 -> 91Improved
cross-dataset testing of OU-MVLP model instead of training from scratchPA-GCRNet · OUTD-DRank-1 identification rate (%): 73 -> 75Improved
cross-dataset testing of OU-MVLP model instead of training from scratchPA-GCRNet · CASIA-BRank-1 identification rate (%): 39.4 -> 74.7Improved
train PA-GCRNet from scratch on only 24 subjects vs GaitSetPA-GCRNet vs GaitSet · CASIA-BRank-1 identification rate (%): 33.3 -> 39.4Improved

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