1 Guangzhou Academy of Fine Arts, School of Visual Arts Design, Guangzhou, China 2 The Innovation School of Great Bay Area, Guangzhou Academy of Fine Arts, Guangzhou, China Project-based learning (PBL ...

Abstract: Traditional hybrid video coding framework using block based predictive coding and transform coding, such as the High Efficiency Video Coding (HEVC), cannot further dig out the redundancy ...

Abstract: Recent video large language models (Video LLMs) often depend on costly human annotations or proprietary APIs (e.g., GPT-4o) to produce training data, which limits their training at scale. In ...