Video Timeline Modeling For News Story Understanding
This work addresses the problem of organizing and understanding news stories from videos for applications like summarization, though it is exploratory and incremental in establishing a new research area.
The paper introduces the novel problem of video timeline modeling to create timelines from topic-related videos for story understanding, and presents a benchmark dataset with over 12k timelines and 300k YouTube news videos along with evaluation metrics and deep learning benchmarks.
In this paper, we present a novel problem, namely video timeline modeling. Our objective is to create a video-associated timeline from a set of videos related to a specific topic, thereby facilitating the content and structure understanding of the story being told. This problem has significant potential in various real-world applications, for instance, news story summarization. To bootstrap research in this area, we curate a realistic benchmark dataset, YouTube-News-Timeline, consisting of over $12$k timelines and $300$k YouTube news videos. Additionally, we propose a set of quantitative metrics to comprehensively evaluate and compare methodologies. With such a testbed, we further develop and benchmark several deep learning approaches to tackling this problem. We anticipate that this exploratory work will pave the way for further research in video timeline modeling. The assets are available via https://github.com/google-research/google-research/tree/master/video_timeline_modeling.