AI Paper Atlas

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

Identity-Guided Human Semantic Parsing for Person Re-Identification

Kuan Zhu, Haiyun Guo, Zhiwei Liu, Ming Tang, Jinqiao Wang

ECCV 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Supervised person re-identification · 395 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
use learned semantic parts (ISP) instead of extra semantics from SCHP (ablation)ISP, HRNet-W32 · DukeMTMC-reIDmAP: 79.1 -> 80.0Improved
use learned semantic parts (ISP) instead of extra semantics from SCHP (ablation)ISP, HRNet-W32 · CUHK03-NP DetectedmAP: 69.6 -> 71.4Improved
add extra SCHP semantics to the baseline (ablation)HRNet-W32 baseline · DukeMTMC-reIDmAP: 77.2 -> 79.1Improved
add learned ISP parsing to the baseline (ablation)HRNet-W32 baseline · CUHK03-NP LabeledRank-1: 71.9 -> 76.5Improved
add aligned representation matching with shared-visible parts (arm) (ablation)ISP · Occluded-DukeMTMCRank-1: 59.5 -> 62.8Improved
add aligned representation matching with shared-visible parts (arm) (ablation)ISP · Occluded-DukeMTMCmAP: 51.4 -> 52.3Improved
use HRNet-W32 backbone instead of ResNet50 (ablation)ISP · DukeMTMC-reIDmAP: 78.9 -> 80.0Improved
use HRNet-W32 backbone instead of SeResNet50 (ablation)ISP · DukeMTMC-reIDRank-1: 88.8 -> 89.6Improved
set number of parts K to 5 instead of 4 or 7 (ablation)ISP · DukeMTMC-reIDRank-1: 89.6 -> 88.6Hurt
vary number of parts K from 4 to 8 (ablation)ISP · Market1501mAP: 88.6, 87.7, 88.4, 88.4, 88.6 for K=4..8No clear effect

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