Saved in:
Bibliographic Details
Main Authors: Rajpal, Shreya, Golovanevsky, Michal, Eickhoff, Carsten
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.12243
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915761752113152
author Rajpal, Shreya
Golovanevsky, Michal
Eickhoff, Carsten
author_facet Rajpal, Shreya
Golovanevsky, Michal
Eickhoff, Carsten
contents Video summarization helps turn long videos into clear, concise representations that are easier to review, document, and analyze, especially in high-stakes domains like surgical training. Prior work has progressed from using basic visual features like color, motion, and structural changes to using pre-trained vision-language models that can better understand what's happening in the video (semantics) and capture temporal flow, resulting in more context-aware video summarization. We propose a three-stage framework, PRISM: Procedural Representation via Integrated Semantic and Multimodal analysis, that produces semantically grounded video summaries. PRISM combines adaptive visual sampling, label-driven keyframe anchoring, and contextual validation using a large language model (LLM). Our method ensures that selected frames reflect meaningful and procedural transitions while filtering out generic or hallucinated content, resulting in contextually coherent summaries across both domain-specific and instructional videos. We evaluate our method on instructional and activity datasets, using reference summaries for instructional videos. Despite sampling fewer than 5% of the original frames, our summaries retain 84% semantic content while improving over baselines by as much as 33%. Our approach generalizes across procedural and domain-specific video tasks, achieving strong performance with both semantic alignment and precision.
format Preprint
id arxiv_https___arxiv_org_abs_2601_12243
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Less is More: Label-Guided Summarization of Procedural and Instructional Videos
Rajpal, Shreya
Golovanevsky, Michal
Eickhoff, Carsten
Computer Vision and Pattern Recognition
Artificial Intelligence
Video summarization helps turn long videos into clear, concise representations that are easier to review, document, and analyze, especially in high-stakes domains like surgical training. Prior work has progressed from using basic visual features like color, motion, and structural changes to using pre-trained vision-language models that can better understand what's happening in the video (semantics) and capture temporal flow, resulting in more context-aware video summarization. We propose a three-stage framework, PRISM: Procedural Representation via Integrated Semantic and Multimodal analysis, that produces semantically grounded video summaries. PRISM combines adaptive visual sampling, label-driven keyframe anchoring, and contextual validation using a large language model (LLM). Our method ensures that selected frames reflect meaningful and procedural transitions while filtering out generic or hallucinated content, resulting in contextually coherent summaries across both domain-specific and instructional videos. We evaluate our method on instructional and activity datasets, using reference summaries for instructional videos. Despite sampling fewer than 5% of the original frames, our summaries retain 84% semantic content while improving over baselines by as much as 33%. Our approach generalizes across procedural and domain-specific video tasks, achieving strong performance with both semantic alignment and precision.
title Less is More: Label-Guided Summarization of Procedural and Instructional Videos
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2601.12243