DEEP PARTIAL PERSON RE-IDENTIFICATION VIA ATTENTION MODEL

Citations

WEB OF SCIENCE

10
Citations

SCOPUS

10

초록

This paper considers a novel algorithm referred to as deep partial person re-identification (DPPR) for partial person re identification where only a part of a person is observed and full body images are available for identification. The DPPR is based on an end-to-end deep model which make use of convolutional neural network (CNN), RoI Pooling layer and attention model. The RoI Pooling layer enables the extraction of feature vector corresponding to predefined part of input image. The attention model selects a subset of CNN feature vectors. For qualitative evaluation of proposed model, data from CUHK03 are randomly cropped in constructing p-CUHK03. Experimental results show that DPPR outperforms our baseline model on p-CUHK03.

키워드

Partial person re-identification; Convolutional Neural Network; RoI Pooling; Attention model; DPPR
제목
DEEP PARTIAL PERSON RE-IDENTIFICATION VIA ATTENTION MODEL
저자
Kim, Junyeong; Yoo, Chang D.
DOI
10.1109/ICIP.2017.8296918
발행일
2017-09
유형
Proceedings Paper
저널명
2017 24TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)
페이지
3425 ~ 3429