Video Timeline Modeling for News Story Understanding
Abstract
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.
Cite
Text
Liu et al. "Video Timeline Modeling for News Story Understanding." Neural Information Processing Systems, 2023.Markdown
[Liu et al. "Video Timeline Modeling for News Story Understanding." Neural Information Processing Systems, 2023.](https://mlanthology.org/neurips/2023/liu2023neurips-video/)BibTeX
@inproceedings{liu2023neurips-video,
title = {{Video Timeline Modeling for News Story Understanding}},
author = {Liu, Meng and Zhang, Mingda and Liu, Jialu and Dai, Hanjun and Yang, Ming-Hsuan and Ji, Shuiwang and Feng, Zheyun and Gong, Boqing},
booktitle = {Neural Information Processing Systems},
year = {2023},
url = {https://mlanthology.org/neurips/2023/liu2023neurips-video/}
}