Disco: Disentangled identity-action extraction and spatiotemporal context modeling for LLM-based identity-aware basketball video captioning

Pattern Recognition 2026

View at publisher

Authors: Zeyu Xi, Ya Jing, Haoying Sun, Haoran Zhang, Lifang Wu

DOI: 10.1016/j.patcog.2026.113188

Cited by: 1

References: 14

Fields of Study & Subjects

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

References 14