AI Paper Atlas

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

A Systematic Evaluation and Benchmark for Person Re-Identification: Features, Metrics, and Datasets

Srikrishna Karanam, Mengran Gou, Ziyan Wu, Angels Rates-Borras, Octavia Camps, Richard J. Radke

TPAMI 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Supervised person re-identification · 315 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 multi-shot ranking SRID instead of feature averaging AVER (ablation)GOG-KISSME · multi-shot datasetsrank-1Improved
add metric learning to multi-shot ranking (ablation)multi-shot ranking · multi-shot datasetsrank-1Improved
apply PCA to 100 dimensions on GOG (ablation)GOG · single-shot datasetsrank-1Hurt
increase number of horizontal strips from 6 to 9 or 15 (ablation)GOG · single- and multi-shot datasetsrank-1No clear effect
increase PCA dimension from 50 to 500 (ablation)GOG · VIPeR and Market1501rank-1 and training timeMixed
use IDE-ResNet instead of other features with NFST_expNFST_exp · 7 single-shot datasetsrank-1: best on 4 of 7 datasetsMixed
use GOG instead of other features with SRID and KISSMESRID-KISSME · 11 multi-shot datasetsrank-1: best on all 11 datasetsImproved
use KISSME instead of other metric learners with GOG and SRIDGOG-SRID · 11 multi-shot datasetsrank-1: best across all datasetsImproved
use IDE-ResNet instead of IDE-CaffeNetIDE · single-shot, variation VVmean rank-1: 29.2 -> 40.7Improved
use IDE-ResNet instead of GOGfeature · single-shot, variation RESmean rank-1: 19.5 -> 38.3Improved
use GOG instead of IDE-ResNetfeature · multi-shot, variation RESmean rank-1: 34.0 -> 28.4Hurt
use IDE-ResNet instead of IDE-VGGIDE · multi-shot, variation IVmean rank-1: 61.5 -> 65.1Improved

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