AI RESEARCH

Scene-VLM: Multimodal Video Scene Segmentation via Vision-Language Models

arXiv CS.CV

ArXi:2512.21778v2 Announce Type: replace Segmenting long-form videos into semantically coherent scenes is a fundamental task in large-scale video understanding. Existing encoder-based methods are limited by visual-centric biases, classify each shot in isolation without leveraging sequential dependencies, and lack both narrative understanding and explainability. In this paper, we present Scene-VLM, the first fine-tuned vision-language model (VLM) framework for video scene segmentation.