AI Paper Atlas

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

Unsupervised Person Re-identification by Deep Learning Tracklet Association

Minxian Li, Xiatian Zhu, Shaogang Gong

ECCV 2018 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Geometric alignment and synthetic-to-real adaptation · 256 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 per-camera tracklet discrimination instead of joint-camera classification (ablation)TAUDL without CCTA · CUHK03Rank-1 (%): 29.8 -> 33.8Improved
use per-camera tracklet discrimination instead of joint-camera classification (ablation)TAUDL without CCTA · Market-1501Rank-1 (%): 17.5 -> 52.1Improved
use per-camera tracklet discrimination instead of joint-camera classification (ablation)TAUDL without CCTA · DukeMTMC-reIDRank-1 (%): 14.9 -> 51.2Improved
use per-camera tracklet discrimination instead of joint-camera classification (ablation)TAUDL without CCTA · MARSRank-1 (%): 18.1 -> 38.0Improved
add cross-camera tracklet association (ablation)TAUDL · CUHK03Rank-1 (%): 33.8 -> 44.7Improved
add cross-camera tracklet association (ablation)TAUDL · Market-1501Rank-1 (%): 52.1 -> 63.7Improved
add cross-camera tracklet association (ablation)TAUDL · DukeMTMC-reIDRank-1 (%): 51.2 -> 61.7Improved
add cross-camera tracklet association (ablation)TAUDL · MARSRank-1 (%): 38.0 -> 43.8Improved
increase ID duplication rate in tracklet labels from 0 to 50% (ablation)TAUDL · MARSRank-1 (%): 43.8 -> 40.7Hurt
train on small video datasets (few tracklets) instead of MARSTAUDL · PRID2011 / iLIDS-VID vs MARSRank-1 (%): MARS 43.8 vs 36.8 (best competitor); iLIDS-VID 26.7 vs 41.7Mixed

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