Video summarization aims to distill the most important information from a source video to produce either an abridged clip or a textual narrative. Traditionally, different methods have been proposed depending on whether the output is a video or text, thus ignoring the correlation between the two semantically related tasks of visual summarization and textual summarization. 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, collectively referred to as a cross-modal summary. The generated shortened video clip and text narratives should be semantically well aligned. To this end, we first build a large-scale human-annotated dataset -- VideoXum (X refers to different modalities). The dataset is reannotated based on ActivityNet. After we filter out the videos that do not meet the length requirements, 14,001 long videos remain in our new dataset. Each video in our reannotated dataset has human-annotated video summaries and the corresponding narrative summaries. We then design a novel end-to-end model -- VTSUM-BILP to address the challenges of our proposed task. Moreover, we propose a new metric called VT-CLIPScore to help evaluate the semantic consistency of cross-modality summary. The proposed model achieves promising performance on this new task and establishes a benchmark for future research.

翻译：视频摘要旨在从源视频中提炼出最重要的信息，以生成精简片段或文本描述。传统上，根据输出是视频还是文本，不同的方法被提出，从而忽略了视觉摘要与文本摘要这两个语义相关任务之间的关联性。我们提出了一项新的联合视频与文本摘要任务，目标是从长视频中同时生成精简视频片段及其对应文本摘要，统称为跨模态摘要。生成的精简视频片段与文本描述应在语义上良好对齐。为此，我们首先构建了一个大规模人工标注数据集——VideoXum（X代表不同模态）。该数据集基于ActivityNet重新标注，在过滤掉不符合长度要求的视频后，新数据集中保留了14,001个长视频。每个视频都包含人工标注的视频摘要及其对应叙述性摘要。接着，我们设计了一种新颖的端到端模型——VTSUM-BILP，以应对所提出任务的挑战。此外，我们提出了一种新指标VT-CLIPScore，用于评估跨模态摘要的语义一致性。该模型在新任务上取得了有前景的性能，为未来研究建立了基准。