Person Re-identification via Discriminative Accumulation of Local Features

Tetsu Matsukawa, Takahiro Okabe, Yoichi Sato

Research output: Chapter in Book/Report/Conference proceedingConference contribution

10 Citations (Scopus)


Metric learning to learn a good distance metric for distinguishing different people while being insensitive to intra-person variations is widely applied to person re-identification. In previous works, local histograms are densely sampled to extract spatially localized information of each person image. The extracted local histograms are then concatenated into one vector that is used as an input of metric learning. However, the dimensionality of such a concatenated vector often becomes large while the number of training samples is limited. This leads to an over fitting problem. In this work, we argue that such a problem of over-fitting comes from that it is each local histogram dimension (e.g. color brightness bin) in the same position is treated separately to examine which part of the image is more discriminative. To solve this problem, we propose a method that analyzes discriminative image positions shared by different local histogram dimensions. A common weight map shared by different dimensions and a distance metric which emphasizes discriminative dimensions in the local histogram are jointly learned with a unified discriminative criterion. Our experiments using four different public datasets confirmed the effectiveness of the proposed method.

Original languageEnglish
Title of host publicationProceedings - International Conference on Pattern Recognition
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages6
ISBN (Electronic)9781479952083
Publication statusPublished - Dec 4 2014
Externally publishedYes
Event22nd International Conference on Pattern Recognition, ICPR 2014 - Stockholm, Sweden
Duration: Aug 24 2014Aug 28 2014

Publication series

NameProceedings - International Conference on Pattern Recognition
ISSN (Print)1051-4651


Other22nd International Conference on Pattern Recognition, ICPR 2014

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition


Dive into the research topics of 'Person Re-identification via Discriminative Accumulation of Local Features'. Together they form a unique fingerprint.

Cite this