Zhang, Haosong

2 publications

WACV 2024 PGVT: Pose-Guided Video Transformer for Fine-Grained Action Recognition Haosong Zhang, Mei Chee Leong, Liyuan Li, Weisi Lin

CVPR 2024 PeVL: Pose-Enhanced Vision-Language Model for Fine-Grained Human Action Recognition Haosong Zhang, Mei Chee Leong, Liyuan Li, Weisi Lin