arXiv cs.AI
Seeing Before Synthesizing: VLM-Guided Transition Event Discovery for Weakly-Supervised Dense Video Captioning
합성하기 전에 보기: 약하게 지도된 밀집 비디오 캡셔닝을 위한 VLM 기반 전이 이벤트 발견
No write-up yet — this entry is still just the auto-fetched hook. Aaron's own summary (200–500 words) will replace this note once he's written it.