AI Paper Atlas

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

Gait Recognition in the Wild: A Benchmark

Zheng Zhu, Xianda Guo, Tian Yang, Junjie Huang, Jiankang Deng, Guan Huang, Dalong Du, Jiwen Lu, Jie Zhou

ICCV 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Margin-based face recognition losses · 113 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
increase training identities from 1K to 20K (ablation)GaitSet · GREW testRank-1 accuracy (%): 28.0% -> 46.28%Improved
increase training identities from 1K to 20K (ablation)TS-CNN · GREW testRank-1 accuracy (%): 9.50% -> 13.55%Improved
increase training identities from 1K to 20K (ablation)GEINet · GREW testRank-1 accuracy (%): 5.32 -> 6.82No clear effect
increase training identities from 1K to 20K (ablation)GaitPart · GREW testRank-1 accuracy (%): 26.39 -> 44.01Improved
increase training identities from 1K to 20K (ablation)PoseGait and GaitGraph · GREW testRank-1 accuracy (%): 0.13 -> 0.23 (PoseGait), 0.25 -> 1.31 (GaitGraph)No clear effect
double test identities from 1K to 2K (ablation)GaitSet · GREW testRank-1 accuracy (%): 57.45% -> 49.83%Hurt
add 233K distractor sequences to the gallery (ablation)GaitSet · GREW testRank-1 accuracy (%): 46.28% -> 41.97%Hurt
pre-train on GREW then fine-tune on CASIA-B (ablation)GaitSet · CASIA-BRank-1 accuracy (%): 83.64% -> 84.48%Improved
train on GREW and test directly on CASIA-B without fine-tuning (ablation)GaitSet · CASIA-BRank-1 accuracy (%): 83.64% -> 45.14%Hurt
use carrying (backpack) versus no carryingGaitSet · GREW testRank-1 accuracy (%): 52.36 -> 48.83Hurt
probe with lift-stuff versus no carryingGaitSet · GREW testRank-1 accuracy (%): 52.36 -> 45.66Hurt
probe with skirt versus all dressingGaitSet · GREW testRank-1 accuracy (%): 46.28 -> 44.30Hurt

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