atlas

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

Single Camera Training for Person Re-Identification

AAAI 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Cross-modality and occlusion re-identification · 30 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
Replace Triplet with MCNLResNet-50 trained on Duke-SCT · Duke-SCTRank-1: 21.2 -> 66.4Helped
Replace Triplet with MCNLResNet-50 trained on Market-SCT · Market-SCTRank-1: 39.7 -> 66.2Helped
Restrict hardest-negative selection to the anchor's camera (ablation)Triplet on Duke-SCT · Duke-SCTRank-1: 21.2 -> 54.6Helped
Restrict hardest-negative selection to the anchor's camera (ablation)Triplet on Market-SCT · Market-SCTRank-1: 39.7 -> 51.3Helped
Select the hardest negative only from other cameras (ablation)Triplet on Duke-SCT · Duke-SCTRank-1: 21.2 -> 9.9Hurt
Select the hardest negative only from other cameras (ablation)Triplet on Market-SCT · Market-SCTRank-1: 39.7 -> 25.2Hurt
Add MCNL to MAR using SCT target dataMAR on Duke · DukeRank-1: +4.3%Helped
Add MCNL to MAR using SCT target dataMAR on Duke · DukemAP: +5.3%Helped
Add MCNL to ECN using SCT target dataECN on Market · MarketmAP: +8.2%Helped

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