Open-vocabulary multi-label action recognition in movies via LLM-enhanced prompt tuning

Computer Vision and Image Understanding 2026 Open access

Read full text

Authors: R. Y. Zhu, Xinxiao Wu, Shuo Yang, Yuheng Shi, Ziyi Wang

DOI: 10.1016/j.cviu.2026.104876

Cited by: 0

References: 4

Fields of Study & Subjects

Human Pose and Action Recognition Multimodal Machine Learning Applications Generative Adversarial Networks and Image Synthesis

References 4