Filters








2 Hits in 2.6 sec

DotSCN: Group Re-identification via Domain-Transferred Single and Couple Representation Learning [article]

Ziling Huang, Zheng Wang, Chung-Chi Tsai, Shin'ichi Satoh, Chia-Wen Lin
2020 arXiv   pre-print
To gain the superiority of deep learning models, we treat a group as multiple persons and transfer the domain of a labeled ReID dataset to a G-ReID target dataset style to learn single representations.  ...  So the key task of G-ReID is to learn representations robust to such changes. To address this issue, we propose a Transferred Single and Couple Representation Learning Network (TSCN).  ...  We have also propose an adaptive fusion method to fuse the single and couple representation results for better group re-identification.  ... 
arXiv:1905.04854v2 fatcat:p7zlkanozbfp5dtjuabbmdivku

Table of contents

2021 IEEE transactions on circuits and systems for video technology (Print)  
Ye 2725 DotSCN: Group Re-Identification via Domain-Transferred Single and Couple Representation Learning ................ .................................................................... Z.  ...  Hu 2751 Semantic-Aware Occlusion-Robust Network for Occluded Person Re-Identification ........................................ ..........................................................................  ... 
doi:10.1109/tcsvt.2021.3088315 fatcat:o4w4amn5rvaijcxllxa6dlq2u4