AI RESEARCH
Multimodal Abstractive Summarization of Instructional Videos with Vision-Language Models
arXiv CS.CL
•
ArXi:2605.11959v1 Announce Type: cross Multimodal video summarization requires visual features that align semantically with language generation. Traditional approaches rely on CNN features trained for object classification, which represent visual concepts as discrete categories not aligned with natural language. We propose ClipSum, a framework that leverages frozen CLIP vision-language features with explicit temporal modeling and dimension-adaptive fusion for instructional video summarization. CLIP's contrastive pre.