KE-VUM: Knowledge-enhanced video understanding model for fine-grained movie description

Neural Networks 2026 Open access

Read full text

Authors: Xiaojing Gu, Gen Xu, Xiaolu Zhang, Yijie Wang, Jiangjian Xiao

DOI: 10.1016/j.neunet.2026.108773

Cited by: 0

References: 30

Fields of Study & Subjects

Multimodal Machine Learning Applications Video Analysis and Summarization Human Pose and Action Recognition

References 30