MMSum：用于视频多模态摘要与缩略图生成的数据集
MMSum: A Dataset for Multimodal Summarization and Thumbnail Generation of Videos
AI总结：
针对现有MSMO数据集的维护、规模和分类等局限，本文构建了MMSum数据集，提供人工验证的视频与文本摘要、17个主类和170个子类的分类体系，并进行了基准测试，全面开源以促进多模态摘要研究。
摘要：
多模态输出的多模态摘要（MSMO）已成为一个极具前景的研究方向。然而，现有的公开MSMO数据集存在诸多限制，包括维护不足、数据不可访问、规模有限以及缺乏恰当的分类，这带来了重大挑战。为了解决这些挑战并为这一新方向提供全面的数据集，我们精心整理了MMSum数据集。该新数据集具有以下特点：（1）针对视频和文本内容均提供经人工验证的摘要，为多模态学习提供更优的人工指令和标签。（2）全面且细致的分类体系，涵盖17个主类别和170个子类别，以囊括多样的现实世界场景。（3）在所提出的数据集上进行基准测试，以评估各种任务和方法，包括视频摘要、文本摘要和多模态摘要。为了倡导可访问性与协作，我们将把MMSum数据集及数据收集工具作为完全开源的资源发布，促进透明度并加速未来的发展。我们的项目网站可在https://mmsum-dataset.github.io/ 找到。
英文摘要：
Multimodal summarization with multimodal output (MSMO) has emerged as a promising research direction. Nonetheless, numerous limitations exist within existing public MSMO datasets, including insufficient maintenance, data inaccessibility, limited size, and the absence of proper categorization, which pose significant challenges. To address these challenges and provide a comprehensive dataset for this new direction, we have meticulously curated the \textbf{MMSum} dataset. Our new dataset features (1) Human-validated summaries for both video and textual content, providing superior human instruction and labels for multimodal learning. (2) Comprehensively and meticulously arranged categorization, spanning 17 principal categories and 170 subcategories to encapsulate a diverse array of real-world scenarios. (3) Benchmark tests performed on the proposed dataset to assess various tasks and methods, including \textit{video summarization}, \textit{text summarization}, and \textit{multimodal summarization}. To champion accessibility and collaboration, we will release the \textbf{MMSum} dataset and the data collection tool as fully open-source resources, fostering transparency and accelerating future developments. Our project website can be found at~\url{https://mmsum-dataset.github.io/}
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
