AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Relation-Aware Pedestrian Attribute Recognition with Graph Convolutional Networks

Zichang Tan, Yang Yang, Jun Wan, Guodong Guo, Stan Z. Li

AAAI 2020 · Graph learning › Knowledge and temporal graphs · approach: Graph reasoning for visual recognition · 94 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 Attribute Relation Module (ARM) (ablation)PAR baseline · PETAmA: 84.81 -> 85.75Improved
add ARM (ablation)PAR baseline · RAPmA: 80.49 -> 82.86Improved
add Contextual Relation Module (CRM) (ablation)PAR baseline · RAPmA: 80.49 -> 83.20Improved
add CRM (ablation)PAR baseline · PA-100KmA: 81.17 -> 81.84Improved
add CRM to PAR+ARM (ablation)PAR + ARM · PA-100KmA: 82.31 -> 82.10Hurt
add BN in classifiers (ablation)PAR + ARM + CRM · PETAmA: 86.03 -> 86.96Improved
GCN instead of LSTM (ablation)ARM · PETAmean of five criteria: 84.65 -> 84.95Improved
GCN instead of LSTM (ablation)CRM · PETAmean of five criteria: 84.53 -> 85.03Improved
use both L_A,cons and L_A losses vs only one (ablation)ARM · PETAmAImproved
JLAC vs JLPLS-PAApedestrian attribute recognition · PETAmA: 84.88 -> 86.96Improved
JLAC vs CoCNNpedestrian attribute recognition · RAPmA: 81.42 -> 83.69Improved

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