Spatio-Temporal Side Tuning Pre-trained Foundation Models for Video-based Pedestrian Attribute Recognition

arXiv:2404.17929v1 Announce Type: new
Abstract: Existing pedestrian attribute recognition (PAR) algorithms are mainly developed based on a static image, however, the performance is unreliable in challenging scenarios, such as heavy occlusion, motion blur, etc. In this work, we propose to understand human attributes using video frames that can fully use temporal information by fine-tuning a pre-trained multi-modal foundation model efficiently. Specifically, we formulate the video-based PAR as a vision-language fusion problem and adopt a pre-trained foundation model CLIP to extract …

arxiv cs.ai cs.cl cs.cv foundation pedestrian recognition temporal type video