3 papers
cs.CV2025
SequencePAR: Understanding Pedestrian Attributes via A Sequence Generation Paradigm
Jiandong Jin, Xiao Wang, Yin Lin +4
Current pedestrian attribute recognition (PAR) algorithms use multi-label or multi-task learning frameworks with specific classification heads. These models often struggle with imb…
cs.CV2024
Pedestrian Attribute Recognition via CLIP based Prompt Vision-Language Fusion
Xiao Wang, Jiandong Jin, Chenglong Li +3
Existing pedestrian attribute recognition (PAR) algorithms adopt pre-trained CNN (e.g., ResNet) as their backbone network for visual feature learning, which might obtain sub-optima…
cs.CV2024
VFM-Det: Towards High-Performance Vehicle Detection via Large Foundation Models
Wentao Wu, Fanghua Hong, Xiao Wang +2
Existing vehicle detectors are usually obtained by training a typical detector (e.g., YOLO, RCNN, DETR series) on vehicle images based on a pre-trained backbone (e.g., ResNet, ViT)…