Cascaded Split-and-Aggregate Learning with Feature Recombination for Pedestrian Attribute Recognition

• Published in: International journal of computer vision Vol. 129; no. 10; pp. 2731 - 2744
• Main Authors: Yang, Yang, Tan, Zichang, Tiwari, Prayag, Pandey, Hari Mohan, Wan, Jun, Lei, Zhen, Guo, Guodong, Li, Stan Z.
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.10.2021; Springer; Springer Nature B.V
• Subjects: Artificial Intelligence; Commonality; Computer Imaging; Computer Science; Datasets; Deep learning; Feature maps; Image Processing and Computer Vision; Laboratories; Learning; Modules; Pattern Recognition; Pattern Recognition and Graphics; Semantics; Surveillance; Vision; Pedestrian attribute recognition; Split-and-aggregate learning; Feature recombination; Attention

Multi-label pedestrian attribute recognition in surveillance is inherently a challenging task due to poor imaging quality, large pose variations, and so on. In this paper, we improve its performance from the following two aspects: (1) We propose a cascaded Split-and-Aggregate Learning (SAL) to captu...