AI Paper Atlas

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

Stepwise Metric Promotion for Unsupervised Video Person Re-Identification

Zimo Liu, Dong Wang, Huchuan Lu

ICCV 2017 · Label-efficient and robust learning › Recognition and long-tail · approach: Supervised person re-identification · 179 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
extend nearest neighbor number K from 1 to 5 (ablation)Ours (LOMO) · PRID 2011rank-1 (%): 70.8 -> 80.9Improved
extend K from 1 to 20 (ablation)Ours (LOMO) · PRID 2011rank-1 (%): 70.8 -> 84.27Improved
extend K from 20 to 50 (ablation)Ours (LOMO) · PRID 2011rank-1 (%): 84.27 -> 78.65Hurt
extend K from 1 to 10 on label recall (ablation)Ours (LOMO) · PRID 2011Recall: 0.5168 -> 0.8314Improved
iterative negative label propagation training (ablation)Ours (LOMO) · PRID 2011rank-1 matching rate: improves by around 30%Improved
use set-to-set distance instead of max-pooling at test time (ablation)Ours (LOMO) · PRID 2011CMC: no numbers givenImproved
use supervised XQDA instead of unsupervised method on MARSOurs · MARS (LOMO)rank-1 (%): 26.92 vs 23.59Hurt
use unsupervised method versus supervised XQDA on iLIDS-VIDOurs (LOMO) · iLIDS-VIDrank-1 (%): 58.7 vs 41.7Hurt

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