Perceive, Query Reason: Enhancing Video QA with Question-Guided Temporal Queries
IEEE/CVF Winter Conference on Applications of Computer Vision(2025)
关键词
video question answering,question-guided temporal modeling,multimodal large language models
AI 理解论文
溯源树
样例

生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要