AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

GaitEdge: Beyond Plain End-to-End Gait Recognition for Better Practicality

Junhao Liang, Chao Fan, Saihui Hou, Chuanfu Shen, Yongzhen Huang, Shiqi Yu

ECCV 2022 · Architectures and efficiency › RNNs and normalization · approach: Differentiable optimization layers · 111 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 the trainable float mask with Gait Synthesis (trainable edge only, binary interior) in end-to-end GaitGLGaitGL-E2E · CASIA-B* to TTG-200 cross-domainrank-1 accuracy (%): 37.18 -> 49.12Improved
replace the trainable float mask with Gait SynthesisGaitGL-E2E · TTG-200 to CASIA-B* cross-domain (mean)rank-1 accuracy (%): 41.45 -> 47.59Improved
replace the trainable float mask with Gait SynthesisGaitGL-E2E · CASIA-B* single-domainrank-1 accuracy (%): 95.58 -> 93.45Hurt
replace the trainable float mask with Gait SynthesisGaitGL-E2E · TTG-200 single-domainrank-1 accuracy (%): 90.37 -> 88.66Hurt
replace binary silhouette input with float-coded segmentation output (end-to-end)GaitGL · TTG-200 to CASIA-B* cross-domain (CL)rank-1 accuracy (%): 40.34 -> 27.18Hurt
replace binary silhouette input with float-coded segmentation output (end-to-end)GaitGL · CASIA-B* single-domain (mean)rank-1 accuracy (%): 88.52 -> 95.58Improved
replace binary silhouette input with float-coded segmentation output (end-to-end)GaitGL · CASIA-B* to TTG-200 cross-domainrank-1 accuracy (%): 48.74 -> 37.18Hurt
enlarge structuring element (wider trainable edge) from 3x3 to 9x9 (ablation)GaitEdge · CASIA-B* single-domain (mean)rank-1 accuracy (%): 93.45 -> 95.42Improved
enlarge structuring element (wider trainable edge) from 3x3 to 9x9 (ablation)GaitEdge · CASIA-B* to TTG-200 cross-domainrank-1 accuracy (%): 49.12 -> 44.47Hurt
enlarge structuring element (wider trainable edge) from 3x3 to 9x9 (ablation)GaitEdge · TTG-200 to CASIA-B* cross-domain (mean)rank-1 accuracy (%): 47.59 -> 39.41Hurt
enlarge structuring element from 3x3 to 9x9 (ablation)GaitEdge · TTG-200 single-domainrank-1 accuracy (%): 88.66 -> 90.39Improved
add GaitAlign module under disturbed (offset) detection boxes (ablation)GaitEdge · CASIA-B* with random pixel offset (NM)rank-1 accuracy (%): -0.38%Hurt

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