No AI summary available for this article.
Why It Matters
Weakly-Supervised Dense Video Captioning aims to localize and describe multiple events in untrimmed videos given only an ordered set of event-level captions per video.
Provenance
Discovered via ArXiv and published by ArXiv.
Key Claims
Original description
Weakly-Supervised Dense Video Captioning aims to localize and describe multiple events in untrimmed videos given only an ordered set of event-level captions per video. Recent work synthesizes auxiliary transition captions via LLM to provide additional vision-language alignment, but these captions lack visual grounding and are rigidly assigned to every inter-event gap at a fixed location and duration. To address these, we propose Seeing Before Synthesizing (SBS), a framework that adaptively provides visually grounded linguistic guidance only where warranted. Leveraging a VLM, we generate frame-...
Discovered via ArXiv
Research papers and preprints from arXiv.
Publisher: arxiv.org
ID: http://arxiv.org/abs/2609.04183v1 · Indexed about 2 hours ago