Preprint
Aug 2026
Beyond Visual Boundaries: Rethinking Scene Segmentation for Movie RAG
Understanding long-form video remains a fundamental challenge for multimodal large language models (MLLMs). Sparse frame sampling fails to capture fine-grained visual details, while dense sampling quickly exceeds context length limits. Retrieval-augmented generation (RAG) offers a promising middle ground by selectively...
Dong-Hee Kim, Seonwoo Choi, Changbeen Kim et al.
· 0 citations