Showing 2026Show all
3 papers · 1 filter
cs.CV2026
SuperClip Pyramid for Video Temporal Grounding
Sanghyeok Lee, Juyeon Ko, Joonmyung Choi +4
With the rapid expansion of online video content, video temporal grounding has become essential for localizing moments based on user-specific queries, comprising two subtasks: mome…
cs.CV2026
Grounding Confusable Movie Moments
Dong-Hee Kim, Seonwoo Choi, Changbeen Kim +5
Characters, locations, and actions recur throughout a movie, so many of its moments differ only in fine-grained details. Grounding such a moment in a full-length movie requires res…
cs.CV2026
Beyond Visual Boundaries: Rethinking Scene Segmentation for Movie RAG
Dong-Hee Kim, Seonwoo Choi, Changbeen Kim +6
Understanding long-form video remains a fundamental challenge for multimodal large language models (MLLMs). Sparse frame sampling fails to capture fine-grained visual details, whil…