VGGSound

The VGGSound dataset is a large-scale audio-visual dataset containing 10,000 10-second video clips with corresponding audio files.

Data and Resources

Cite this as

Honglie Chen, Weidi Xie, Andrea Vedaldi, Andrew Zisserman (2024). Dataset: VGGSound. https://doi.org/10.57702/9irceuon

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.2402.17723
Citation
  • https://doi.org/10.48550/arXiv.2012.10852
  • https://doi.org/10.48550/arXiv.2402.15985
  • https://doi.org/10.48550/arXiv.2401.08415
  • https://doi.org/10.48550/arXiv.2308.05037
  • https://doi.org/10.48550/arXiv.2308.09300
  • https://doi.org/10.48550/arXiv.2110.04599
  • https://doi.org/10.48550/arXiv.2311.04066
Author Honglie Chen
More Authors
Weidi Xie
Andrea Vedaldi
Andrew Zisserman
Homepage https://www.robots.ox.ac.uk/~vgg/data/vggsound/