Reuters Video-Language News Dataset

The Reuters Video-Language News Dataset (ReutersViLNews) is a large-scale video-language understanding dataset containing 1,974 long-form news videos with an average video length of 91.2 seconds.

Data and Resources

Cite this as

Shih-Han Chou, Matthew Kowal, Yasmin Niknam, Diana Moyano, Shayaan Mehdi, Richard Pito, Cheng Zhang, Ian Knopke, Sedef Akinli Kocak, Leonid Sigal, Yalda Mohsenzadeh (2024). Dataset: Reuters Video-Language News Dataset. https://doi.org/10.57702/t5b89p6p

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Defined In https://doi.org/10.48550/arXiv.2401.12419
Author Shih-Han Chou
More Authors
Matthew Kowal
Yasmin Niknam
Diana Moyano
Shayaan Mehdi
Richard Pito
Cheng Zhang
Ian Knopke
Sedef Akinli Kocak
Leonid Sigal
Yalda Mohsenzadeh
Homepage https://arxiv.org/abs/2106.09567