Spatial-Channel Enhanced Transformer for Visible-Infrared Person Re-Identification

• Published in: IEEE transactions on multimedia Vol. 25; pp. 3668 - 3680
• Main Authors: Zhao, Jiaqi, Wang, Hanzheng, Zhou, Yong, Yao, Rui, Chen, Silin, Saddik, Abdulmotaleb El
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Computer networks; Computer vision; Convolution; Cross-modality person re-identification; deep learning; Embedding; Feature extraction; image retrieval; Infrared imagery; Modules; Object detection; Representation learning; Representations; Task analysis; Transformers; Visual discrimination; visual Transformer; Visualization

Visible-infrared person re-identification (VI-ReID) is a challenging task in computer vision, aiming at matching people across images from visible and infrared modalities. The widely used VI-ReID framework consists of a convolution neural backbone network that extracts the visual features, and a fea...