CineCap: Structured Reasoning with Spatio-Temporal Anchors for Cinematographic Video Captioning
Paper • 2606.24636 • Published • 2
Xinyu Mao
hector-mao
AI & ML interests
Multimodal Large Language Models, Vision Language Models
Recent Activity
authored a paper 24 days ago
CineCap: Structured Reasoning with Spatio-Temporal Anchors for Cinematographic Video Captioning updated a model 25 days ago
hector-mao/CineCap-GRPO-8BOrganizations
None yet