https://scholars.lib.ntu.edu.tw/handle/123456789/632081
標題: | SELF-SUPERVISED BODYMAP-TO-APPEARANCE CO-ATTENTION FOR PARTIAL PERSON RE-IDENTIFICATION | 作者: | Lin C.-S YU-CHIANG WANG |
關鍵字: | Deep learning; Person re-identification; Visual attention | 公開日期: | 2021 | 卷: | 2021-September | 起(迄)頁: | 2299-2303 | 來源出版物: | Proceedings - International Conference on Image Processing, ICIP | 摘要: | Person re-identification (re-ID) aims at recognizing the same person across distinct camera views. Although a series of works have been proposed to tackle re-ID, most existing methods are based on the assumption that full body detection is available. In practice, detection of pedestrians may not be perfect due to partial occlusion or background clutter, which would result in the challenging task of partial re-ID. To tackle this problem, we propose a novel deep learning framework which jointly performs image rescaling and bodymap-to-appearance co-attention, followed by image matching for re-ID purposes. The image rescaler presented in our framework learns to produce distortion-free images in a self-supervised manner, which allows the subsequent image matching based on the associated image regions via body part attention. Our quantitative and qualitative results on two benchmark partial re-ID datasets confirm the effectiveness of our approach and its superiority over state-of-the-art partial re-ID approaches. © 2021 IEEE |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85125583096&doi=10.1109%2fICIP42928.2021.9506470&partnerID=40&md5=6ffeda108a893816fe70cbb423bc800e https://scholars.lib.ntu.edu.tw/handle/123456789/632081 |
ISSN: | 15224880 | DOI: | 10.1109/ICIP42928.2021.9506470 |
顯示於: | 電機工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。