PaperScope
LIVE · 2026-09-15 05:40 UTC

Zero-shot video highlight detection based on text descriptions and synthetic images

Michal Byra, Alberto Presta, Grzegorz Stefanski, Krzysztof Arendt

Latestcs.CLcs.LGcs.AIcs.CV
arXiv ID
2609.14790 v1
Category
Submitted
2026-09-13

Abstract

Detecting video highlights, the most informative or engaging moments in a video, is important for applications such as video summarization and content recommendation. We propose a zero-shot framework that combines CLIP, large language models (LLMs), and diffusion models. Given lightweight video metadata, such as a title or category, an LLM generates textual descriptions of likely highlight events. These descriptions are further converted into synthetic visual prototypes using a diffusion model. Textual and visual representations are matched to video frames using CLIP, enabling frame-level highlight detection without highlight annotations or dataset-specific training. Experiments on TVSum and SumMe demonstrate strong zero-shot performance, with particularly favorable results on TVSum. The proposed approach provides an effective framework for metadata-conditioned zero-shot video highlight detection.

Comment: 5 pages

arXiv abs page · PDF · same-day batch