Thakare, Kamalakar Vijay Dogra, Debi Prosad Choi, Heeseung 김학섭 Kim, Ig-Jae 2025-02-06T02:30:07Z 2025-02-06T02:30:07Z 2025-02-04 2024-01-05 https://pubs.kist.re.kr/handle/201004/151710 Despite poor image quality, occlusions, and small training datasets, recent pedestrian attribute recognition (PAR) methods have achieved considerable performance. However, leveraging only spatial information of different attributes limits their reliability and generalizability. This paper introduces a multi-perspective approach to reduce over-dependence on spatial clues of a single perspective and exploits other aspects available in multiple perspectives. In order to tackle image quality and occlusions, we exploit different spatial clues present across images and handpick the best attribute-specific features to classify. Precisely, we extract the class-activation energy of each attribute and correlate it with the corresponding energy present across other images using the proposed Self-Attentive Cross Relation Module. In the next stage, we fuse this correlation information with similar clues accumulated from the other images. Lastly, we train a classification neural network using combined correlation information with two different losses. We have validated our method on four widely used PAR datasets, namely Market1501, PETA, PA-100k, and Duke. Our method achieves superior performance over most existing methods, demonstrating the effectiveness of a multi-perspective approach in PAR. English Institute of Electrical and Electronics Engineers Inc. Let's Observe Them over Time: An Improved Pedestrian Attribute Recognition Approach Conference 10.1109/WACV57701.2024.00076 1 2024 IEEE Winter Conference on Applications of Computer Vision, WACV 2024, pp.697 - 706 2024 IEEE Winter Conference on Applications of Computer Vision, WACV 2024 697 706 US Waikoloa, HI, USA 2024-01-04 Proceedings - 2024 IEEE Winter Conference on Applications of Computer Vision, WACV 2024 001222964600069 2-s2.0-85191960222