Video Timeline Modeling For News Story Understanding
Dec 10, 2023
Speakers
Mingda Zhang
Speaker · 0 followers
Hanjun Dai
Speaker · 1 follower
Ming-Hsuan Yang
Speaker · 0 followers
Shuiwang Ji
Speaker · 0 followers
Zheyun Feng
Speaker · 0 followers
Boqing Gong
Speaker · 1 follower
About
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, such as news story summarization. To bootstrap research in this area, we curate a realistic benchmark dataset, YouTube-News-Timeline, consisting of over 12k timelines and 300k YouTube news videos. Additionally, we propose a set of quantitative metrics as the protocol to comprehensively evaluate and compare methodologies. With such a testbed, we further develop and benchmark exploratory deep learning approaches to tackle 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.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, such as news story summarization. To bootstrap research in this area, we curate a realistic benchmark dataset, YouTube-News-Timeline, consisting of over 12k t…
Organizer
NeurIPS 2023
Account · 645 followers
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale
Watch later
Matthew Le, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Faster Margin Maximization Rates for Generic Optimization Methods
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Opening Remarks
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Learning Repeatable Speech Embeddings Using An Intra-class Correlation Regularizer
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Open Catalyst Runner-up Talk
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
![[Re] End-to-end Algorithm Synthesis with Recurrent Networks: Logical Extrapolation Without Overthinking](https://ma.slideslive.com/library/presentations/39011091/thumbnail/re-endtoend-algorithm-synthesis-with-recurrent-networks-logical-extrapolation-without-overthinking_FsthNS_small.png)
[Re] End-to-end Algorithm Synthesis with Recurrent Networks: Logical Extrapolation Without Overthinking
Watch later
Sean McLeish, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%