Integrating Video and Text: A Balanced Approach to Multimodal Summary Generation and Evaluation

• URL: http://arxiv.org/abs/2505.06594v1
• Date: Sat, 10 May 2025 10:52:23 GMT
• Title: Integrating Video and Text: A Balanced Approach to Multimodal Summary Generation and Evaluation
• Authors: Galann Pennec, Zhengyuan Liu, Nicholas Asher, Philippe Muller, Nancy F. Chen,
• Abstract summary: We propose a zero-shot video-to-text summarization approach that builds its own screenplay representation of an episode.<n>Unlike previous approaches, we simultaneously generate screenplays and name the characters in zero-shot, using only the audio, video, and transcripts as input.
• Score: 35.50845951376099
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision-Language Models (VLMs) often struggle to balance visual and textual information when summarizing complex multimodal inputs, such as entire TV show episodes. In this paper, we propose a zero-shot video-to-text summarization approach that builds its own screenplay representation of an episode, effectively integrating key video moments, dialogue, and character information into a unified document. Unlike previous approaches, we simultaneously generate screenplays and name the characters in zero-shot, using only the audio, video, and transcripts as input. Additionally, we highlight that existing summarization metrics can fail to assess the multimodal content in summaries. To address this, we introduce MFactSum, a multimodal metric that evaluates summaries with respect to both vision and text modalities. Using MFactSum, we evaluate our screenplay summaries on the SummScreen3D dataset, demonstrating superiority against state-of-the-art VLMs such as Gemini 1.5 by generating summaries containing 20% more relevant visual information while requiring 75% less of the video as input.

Related papers

• VidText: Towards Comprehensive Evaluation for Video Text Understanding [54.15328647518558]
  VidText is a benchmark for comprehensive and in-depth evaluation of video text understanding.<n>It covers a wide range of real-world scenarios and supports multilingual content.<n>It introduces a hierarchical evaluation framework with video-level, clip-level, and instance-level tasks.
  arXiv  Detail & Related papers  (2025-05-28T19:39:35Z)
• SD-VSum: A Method and Dataset for Script-Driven Video Summarization [6.076406622352117]
  We introduce the task of script-driven video summarization (VideoXum)<n>We produce natural language descriptions of the different human-annotated summaries that are available per video.<n>We develop a new network architecture for script-driven video summarization (SD-VSum)
  arXiv  Detail & Related papers  (2025-05-06T08:47:14Z)
• Summarization of Multimodal Presentations with Vision-Language Models: Study of the Effect of Modalities and Structure [5.332290080594085]
  Vision-Language Models (VLMs) can process visual and textual information in multiple formats.<n>We suggest cost-effective strategies for generating summaries from text-heavy multimodal documents.
  arXiv  Detail & Related papers  (2025-04-14T09:55:01Z)
• MMTrail: A Multimodal Trailer Video Dataset with Language and Music Descriptions [69.9122231800796]
  We present MMTrail, a large-scale multi-modality video-language dataset incorporating more than 20M trailer clips with visual captions.<n>We propose a systemic captioning framework, achieving various modality annotations with more than 27.1k hours of trailer videos.<n>Our dataset potentially paves the path for fine-grained large multimodal-language model training.
  arXiv  Detail & Related papers  (2024-07-30T16:43:24Z)
• UBiSS: A Unified Framework for Bimodal Semantic Summarization of Videos [52.161513027831646]
  We focus on a more comprehensive video summarization task named Bimodal Semantic Summarization of Videos (BiSSV) We propose a Unified framework UBiSS for the BiSSV task, which models the saliency information in the video and generates a TM-summary and VM-summary simultaneously. Experiments show that our unified framework achieves better performance than multi-stage summarization pipelines.
  arXiv  Detail & Related papers  (2024-06-24T03:55:25Z)
• V2Xum-LLM: Cross-Modal Video Summarization with Temporal Prompt Instruction Tuning [76.26890864487933]
  Video summarization aims to create short, accurate, and cohesive summaries of longer videos. Most existing datasets are created for video-to-video summarization. Recent efforts have been made to expand from unimodal to multimodal video summarization.
  arXiv  Detail & Related papers  (2024-04-18T17:32:46Z)
• DeVAn: Dense Video Annotation for Video-Language Models [68.70692422636313]
  We present a novel human annotated dataset for evaluating the ability for visual-language models to generate descriptions for real-world video clips. The dataset contains 8.5K YouTube video clips of 20-60 seconds in duration and covers a wide range of topics and interests.
  arXiv  Detail & Related papers  (2023-10-08T08:02:43Z)
• Learning Summary-Worthy Visual Representation for Abstractive Summarization in Video [34.202514532882]
  We propose a novel approach to learning the summary-worthy visual representation that facilitates abstractive summarization. Our method exploits the summary-worthy information from both the cross-modal transcript data and the knowledge that distills from the pseudo summary.
  arXiv  Detail & Related papers  (2023-05-08T16:24:46Z)
• Hierarchical3D Adapters for Long Video-to-text Summarization [79.01926022762093]
  multimodal information offers superior performance over more memory-heavy and fully fine-tuned textual summarization methods. Our experiments demonstrate that multimodal information offers superior performance over more memory-heavy and fully fine-tuned textual summarization methods.
  arXiv  Detail & Related papers  (2022-10-10T16:44:36Z)
• See, Hear, Read: Leveraging Multimodality with Guided Attention for Abstractive Text Summarization [14.881597737762316]
  We introduce the first large-scale dataset for abstractive text summarization with videos of diverse duration, compiled from presentations in well-known academic conferences like NDSS, ICML, NeurIPS, etc. We then propose name, a factorized multi-modal Transformer based decoder-only language model, which inherently captures the intra-modal and inter-modal dynamics within various input modalities for the text summarization task.
  arXiv  Detail & Related papers  (2021-05-20T08:56:33Z)

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.