M 2 -CLIP++: Dual-branch high-order vision–language adaptation with dynamic semantic prompting for efficient video recognition

Computer Vision and Image Understanding 2026 Open access

Read full text

Authors: Chao Liang, Shigang Wang, Bingbing Zhang

DOI: 10.1016/j.cviu.2026.104708

Cited by: 0

References: 32

Fields of Study & Subjects

Human Pose and Action Recognition Multimodal Machine Learning Applications Domain Adaptation and Few-Shot Learning

References 32