SummDiff: Generative Modeling of Video Summarization with Diffusion

• URL: http://arxiv.org/abs/2510.08458v1
• Date: Thu, 09 Oct 2025 17:03:51 GMT
• Title: SummDiff: Generative Modeling of Video Summarization with Diffusion
• Authors: Kwanseok Kim, Jaehoon Hahm, Sumin Kim, Jinhwan Sul, Byunghak Kim, Joonseok Lee,
• Abstract summary: Video summarization is a task of shortening a video by choosing a subset of frames while preserving its essential moments.<n>Previous works have deterministically regressed to an averaged frame score over multiple raters, ignoring the inherent subjectivity of what constitutes a good summary.<n>We propose a novel problem formulation by framing video summarization as a conditional generation task.<n>Adopting diffusion models for the first time in video summarization, our proposed method, SummDiff, dynamically adapts to visual contexts and generates multiple candidate summaries conditioned on the input video.
• Score: 17.773776413936435
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Video summarization is a task of shortening a video by choosing a subset of frames while preserving its essential moments. Despite the innate subjectivity of the task, previous works have deterministically regressed to an averaged frame score over multiple raters, ignoring the inherent subjectivity of what constitutes a good summary. We propose a novel problem formulation by framing video summarization as a conditional generation task, allowing a model to learn the distribution of good summaries and to generate multiple plausible summaries that better reflect varying human perspectives. Adopting diffusion models for the first time in video summarization, our proposed method, SummDiff, dynamically adapts to visual contexts and generates multiple candidate summaries conditioned on the input video. Extensive experiments demonstrate that SummDiff not only achieves the state-of-the-art performance on various benchmarks but also produces summaries that closely align with individual annotator preferences. Moreover, we provide a deeper insight with novel metrics from an analysis of the knapsack, which is an important last step of generating summaries but has been overlooked in evaluation.

Related papers

• Personalized Video Summarization using Text-Based Queries and Conditional Modeling [3.4447129363520337]
  This thesis explores enhancing video summarization by integrating text-based queries and conditional modeling. Evaluation metrics such as accuracy and F1-score assess the quality of the generated summaries.
  arXiv  Detail & Related papers  (2024-08-27T02:43:40Z)
• Scaling Up Video Summarization Pretraining with Large Language Models [73.74662411006426]
  We introduce an automated and scalable pipeline for generating a large-scale video summarization dataset. We analyze the limitations of existing approaches and propose a new video summarization model that effectively addresses them. Our work also presents a new benchmark dataset that contains 1200 long videos each with high-quality summaries annotated by professionals.
  arXiv  Detail & Related papers  (2024-04-04T11:59:06Z)
• A Modular Approach for Multimodal Summarization of TV Shows [55.20132267309382]
  We present a modular approach where separate components perform specialized sub-tasks. Our modules involve detecting scene boundaries, reordering scenes so as to minimize the number of cuts between different events, converting visual information to text, summarizing the dialogue in each scene, and fusing the scene summaries into a final summary for the entire episode. We also present a new metric, PRISMA, to measure both precision and recall of generated summaries, which we decompose into atomic facts.
  arXiv  Detail & Related papers  (2024-03-06T16:10:01Z)
• Conditional Modeling Based Automatic Video Summarization [70.96973928590958]
  The aim of video summarization is to shorten videos automatically while retaining the key information necessary to convey the overall story. Video summarization methods rely on visual factors, such as visual consecutiveness and diversity, which may not be sufficient to fully understand the content of the video. A new approach to video summarization is proposed based on insights gained from how humans create ground truth video summaries.
  arXiv  Detail & Related papers  (2023-11-20T20:24:45Z)
• Causal Video Summarizer for Video Exploration [74.27487067877047]
  Causal Video Summarizer (CVS) is proposed to capture the interactive information between the video and query. Based on the evaluation of the existing multi-modal video summarization dataset, experimental results show that the proposed approach is effective.
  arXiv  Detail & Related papers  (2023-07-04T22:52:16Z)
• VideoXum: Cross-modal Visual and Textural Summarization of Videos [54.0985975755278]
  We propose a new joint video and text summarization task. The goal is to generate both a shortened video clip along with the corresponding textual summary from a long video. The generated shortened video clip and text narratives should be semantically well aligned.
  arXiv  Detail & Related papers  (2023-03-21T17:51:23Z)
• Video Summarization Based on Video-text Modelling [0.0]
  We propose a multimodal self-supervised learning framework to obtain semantic representations of videos. We also introduce a progressive video summarization method, where the important content in a video is pinpointed progressively to generate better summaries. An objective evaluation framework is proposed to measure the quality of video summaries based on video classification.
  arXiv  Detail & Related papers  (2022-01-07T15:21:46Z)
• How Good is a Video Summary? A New Benchmarking Dataset and Evaluation Framework Towards Realistic Video Summarization [11.320914099324492]
  We introduce a new benchmarking video dataset called VISIOCITY which comprises of longer videos across six different categories. We show strategies to automatically generate multiple reference summaries from indirect ground truth present in VISIOCITY. We propose an evaluation framework for better quantitative assessment of summary quality which is closer to human judgment.
  arXiv  Detail & Related papers  (2021-01-26T01:42:55Z)
• Multi-Fact Correction in Abstractive Text Summarization [98.27031108197944]
  Span-Fact is a suite of two factual correction models that leverages knowledge learned from question answering models to make corrections in system-generated summaries via span selection. Our models employ single or multi-masking strategies to either iteratively or auto-regressively replace entities in order to ensure semantic consistency w.r.t. the source text. Experiments show that our models significantly boost the factual consistency of system-generated summaries without sacrificing summary quality in terms of both automatic metrics and human evaluation.
  arXiv  Detail & Related papers  (2020-10-06T02:51:02Z)
• Realistic Video Summarization through VISIOCITY: A New Benchmark and Evaluation Framework [15.656965429236235]
  We take steps towards making automatic video summarization more realistic by addressing several challenges. Firstly, the currently available datasets either have very short videos or have few long videos of only a particular type. We introduce a new benchmarking dataset VISIOCITY which comprises of longer videos across six different categories.
  arXiv  Detail & Related papers  (2020-07-29T02:44:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.