AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Unsupervised Tracklet Person Re-Identification

Minxian Li, Xiatian Zhu, Shaogang Gong

TPAMI 2019 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Geometric alignment and synthetic-to-real adaptation · 187 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 per-camera tracklet discrimination (multi-task) instead of single-task classification (ablation)UTAL · MARSRank-1: 15.9 -> 43.8Improved
add per-camera tracklet discrimination instead of single-task classification (ablation)UTAL · DukeTrackletRank-1: 3.9 -> 31.7Improved
use soft labels instead of hard one-hot labels (ablation)UTAL · MARSRank-1: 35.5 -> 49.9Improved
use soft labels instead of hard one-hot labels (ablation)UTAL · DukeTrackletRank-1: 24.5 -> 43.8Improved
soft labels vs hard labels with one tracklet per ID per camera (cross-ID transfer) (ablation)UTAL · MARSRank-1: 45.1 -> 46.5Improved
add cross-camera tracklet association learning (ablation)UTAL · MARSRank-1: 43.8 -> 49.9Improved
add cross-camera tracklet association learning (ablation)UTAL · DukeTrackletRank-1: 31.7 -> 43.8Improved
reciprocal 2-way 1-NN instead of 1-way 1-NN (ablation)UTAL · MARSRank-1 / mAP: 50.5 -> 49.9 Rank-1; 33.2 -> 35.2 mAPMixed
use 10 neighbours instead of 1 in 2-way matching (ablation)UTAL · DukeTrackletRank-1: 43.8 -> 33.9Hurt
use all tracklets instead of SSTT sampling (ablation)UTAL · MARSRank-1: 45.1 -> 49.9Improved
use all tracklets instead of SSTT sampling (ablation)UTAL · DukeTrackletRank-1: 31.7 -> 43.8Improved
replace ResNet-50 backbone with DenseNet-121 (ablation)UTAL · MARSRank-1: 49.9 -> 51.6Improved

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