AI Paper Atlas

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

Maximum Margin Metric Learning Over Discriminative Nullspace for Person Re-identification

T M Feroz Ali, Subhasis Chaudhuri

ECCV 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Supervised person re-identification · 29 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 NK3ML instead of NFSTWHOS features · PRID450SRank-1 accuracy (%): 42.58 -> 50.67Improved
use NK3ML instead of KNFSTLOMO features · GRIDRank-1 accuracy (%): 14.88 -> 18.24Improved
use NK3ML instead of XQDAGOG features · GRIDRank-1 accuracy (%): 24.80 -> 26.96Improved
use NK3ML instead of XQDAWHOS features · PRID450SRank-1 accuracy (%): 43.38 -> 50.67Improved
use NK3ML instead of NFSTGOG features · PRID450SRank-1 accuracy (%): 67.60 -> 68.04No clear effect
use NK3ML instead of XQDAGOG features · PRID450SRank-1 accuracy (%): 68.00 -> 68.04No clear effect
use NK3ML instead of KNFSTWHOS features · GRIDRank-1 accuracy (%): 21.12 -> 21.20No clear effect
use NK3ML instead of GOG+XQDACUHK01 single-shot · CUHK01Rank-1 accuracy (%): 57.89 -> 67.09Improved
use NK3ML instead of GOG+XQDACUHK01 multi-shot · CUHK01Rank-1 accuracy (%): 67.28 -> 76.77Improved
use NK3ML instead of GOG+XQDAPRID450S · PRID450SRank-1 accuracy (%): 68.00 -> 73.42Improved
use NK3ML instead of the previous best (DCIA, with post-processing)VIPeR · VIPeRRank-1 accuracy (%): 63.9 -> 99.8Improved
use NK3ML instead of NFST (training cost)VIPeR · VIPeRTraining time (s): 1.47 -> 1.64No clear effect

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