Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

UNSUPERVISED DOMAIN-ADAPTIVE PERSON RE-IDENTIFICATION BASED ON ATTRIBUTES

Abstract: 

Pedestrian attributes, e.g., hair length, clothes type and color, locally describe the semantic appearance of a person. Training person re-identification (ReID) algorithms under the supervision of such attributes have proven to be effective in extracting local features. Different from person identity, at- tributes are consistent across different domains (or datasets). However, most of ReID datasets lack attribute annotations. On the other hand, there are several datasets labeled with sufficient attributes for the case of pedestrian attribute recognition. Exploiting such data for ReID purpose can be a way to alleviate the shortage of attribute annotations in ReID case. In this work, an unsupervised domain adaptive ReID feature learning framework is proposed to make full use of attribute annotations. We propose to transfer attribute-related features from their original domain to the ReID one: to this end, we introduce an adversarial discriminative domain adaptation method in order to learn invariant features for encoding semantic attributes across domains. Experiments on three large-scale datasets validate the effectiveness of the proposed ReID framework.

up
0 users have voted:

Paper Details

Authors:
Xiangping Zhu, Pietro Morerio and Vittorio Murino
Submitted On:
16 September 2019 - 10:17am
Short Link:
Type:
Poster
Document Year:
2019
Cite

Document Files

#2281_poster

(25)

Subscribe

[1] Xiangping Zhu, Pietro Morerio and Vittorio Murino, "UNSUPERVISED DOMAIN-ADAPTIVE PERSON RE-IDENTIFICATION BASED ON ATTRIBUTES", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4640. Accessed: Feb. 18, 2020.
@article{4640-19,
url = {http://sigport.org/4640},
author = {Xiangping Zhu; Pietro Morerio and Vittorio Murino },
publisher = {IEEE SigPort},
title = {UNSUPERVISED DOMAIN-ADAPTIVE PERSON RE-IDENTIFICATION BASED ON ATTRIBUTES},
year = {2019} }
TY - EJOUR
T1 - UNSUPERVISED DOMAIN-ADAPTIVE PERSON RE-IDENTIFICATION BASED ON ATTRIBUTES
AU - Xiangping Zhu; Pietro Morerio and Vittorio Murino
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4640
ER -
Xiangping Zhu, Pietro Morerio and Vittorio Murino. (2019). UNSUPERVISED DOMAIN-ADAPTIVE PERSON RE-IDENTIFICATION BASED ON ATTRIBUTES. IEEE SigPort. http://sigport.org/4640
Xiangping Zhu, Pietro Morerio and Vittorio Murino, 2019. UNSUPERVISED DOMAIN-ADAPTIVE PERSON RE-IDENTIFICATION BASED ON ATTRIBUTES. Available at: http://sigport.org/4640.
Xiangping Zhu, Pietro Morerio and Vittorio Murino. (2019). "UNSUPERVISED DOMAIN-ADAPTIVE PERSON RE-IDENTIFICATION BASED ON ATTRIBUTES." Web.
1. Xiangping Zhu, Pietro Morerio and Vittorio Murino. UNSUPERVISED DOMAIN-ADAPTIVE PERSON RE-IDENTIFICATION BASED ON ATTRIBUTES [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4640