Divide-and-Specialize CLIP: A Text-Guided Multi-expert Framework for Fine-Grained Action Recognition

Lecture notes in computer science 2026

View at publisher

Authors: Lingjie Zeng, Hailun Zhang, Xinrui Wang, Zhen Zhai, Qijun Zhao, Hanyang Lin

DOI: 10.1007/978-981-95-5676-2_10

Cited by: 0

References: 11

Fields of Study & Subjects

Human Pose and Action Recognition Multimodal Machine Learning Applications Hand Gesture Recognition Systems

References 11