Learning Correspondence Structures for Person Re-Identification
This paper addresses the problem of handling spatial misalignments due to camera-view changes or human-pose variations in person re-identification. We first introduce a boosting-based approach to learn a correspondence structure, which indicates the patchwise matching probabilities between images fr...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 26(2017), 5 vom: 01. Mai, Seite 2438-2453
|
|---|
| 1. Verfasser: |
Lin, Weiyao
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Shen, Yang,
Yan, Junchi,
Xu, Mingliang,
Wu, Jianxin,
Wang, Jingdong,
Lu, Ke |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2017
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
|
|---|
| Schlagworte: | Journal Article |
|---|