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

facebooktwittermailshare

Joint Instance and Feature Importance Re-weighting for Person Reidentification

Person re-identification refers to the task of recognizing the same person under different non-overlapping camera views and across different time and places.
Abstract: 

Person reidentification refers to the task of recognizing the same person
under different non-overlapping camera views. Presently, person
reidentification based on metric learning is proved to be effective among
various techniques, which exploits the labeled data to learn
a subspace that maximizes the inter-person divergence while minimizes
the intra-person divergence. However, these methods fail to
take the different impacts of various instances and local features into
account. To address this issue, we propose to learn a projection matrix
such that the importance of different instances and local features
are re-weighted jointly. We also come up with a simplified formulation
of the proposed algorithm, thus it can be solved by the efficient
UDFS optimization algorithm. Extensive experiments on the VIPeR
and iLIDS datasets demonstrate the effectiveness and efficiency of
our algorithm.

icassp_zq.pdf

PDF icon icassp_zq.pdf (416)
Media Folder: 
up
1 user has voted: Qin Zhou

Paper Details

Authors:
Qin Zhou, Shibao Zheng, Hua Yang, Yu Wang and Hang Su
Submitted On:
13 March 2016 - 8:54am
Short Link:
Type:
Poster
Event:
Presenter's Name:
Qin Zhou
Document Year:
2016
Cite

Document Files

icassp_zq.pdf

(416)

Subscribe

[1] Qin Zhou, Shibao Zheng, Hua Yang, Yu Wang and Hang Su, "Joint Instance and Feature Importance Re-weighting for Person Reidentification", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/651. Accessed: Jul. 05, 2020.
@article{651-16,
url = {http://sigport.org/651},
author = {Qin Zhou; Shibao Zheng; Hua Yang; Yu Wang and Hang Su },
publisher = {IEEE SigPort},
title = {Joint Instance and Feature Importance Re-weighting for Person Reidentification},
year = {2016} }
TY - EJOUR
T1 - Joint Instance and Feature Importance Re-weighting for Person Reidentification
AU - Qin Zhou; Shibao Zheng; Hua Yang; Yu Wang and Hang Su
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/651
ER -
Qin Zhou, Shibao Zheng, Hua Yang, Yu Wang and Hang Su. (2016). Joint Instance and Feature Importance Re-weighting for Person Reidentification. IEEE SigPort. http://sigport.org/651
Qin Zhou, Shibao Zheng, Hua Yang, Yu Wang and Hang Su, 2016. Joint Instance and Feature Importance Re-weighting for Person Reidentification. Available at: http://sigport.org/651.
Qin Zhou, Shibao Zheng, Hua Yang, Yu Wang and Hang Su. (2016). "Joint Instance and Feature Importance Re-weighting for Person Reidentification." Web.
1. Qin Zhou, Shibao Zheng, Hua Yang, Yu Wang and Hang Su. Joint Instance and Feature Importance Re-weighting for Person Reidentification [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/651