Kinetics-400

Motion has shown to be useful for video understanding, where motion is typically represented by optical flow. However, computing flow from video frames is very time-consuming. Recent works directly leverage the motion vectors and residuals readily available in the compressed video to represent motion at no cost.

Data and Resources

Cite this as

Will Kay, Joao Carreira, Karen Simonyan, Brian Zhang, Chloe Hillier, Sudheendra Vijayanarasimhan, Fabio Viola, Tim Green, Trevor Back, Paul Natsev (2024). Dataset: Kinetics-400. https://doi.org/10.57702/y88acueb

DOI retrieved: November 25, 2024

Additional Info

Field Value
Created November 25, 2024
Last update December 2, 2024
Defined In https://doi.org/10.48550/arXiv.2207.12859
Citation
  • https://doi.org/10.1109/ASAP57973.2023.00030
  • https://doi.org/10.48550/arXiv.2201.08377
  • https://doi.org/10.48550/arXiv.2406.18011
  • https://doi.org/10.48550/arXiv.2003.04298
  • https://doi.org/10.48550/arXiv.2308.14843
  • https://doi.org/10.48550/arXiv.2210.05895
  • https://doi.org/10.48550/arXiv.2110.09075
  • https://doi.org/10.48550/arXiv.2304.10465
  • https://doi.org/10.48550/arXiv.2110.10348
  • https://doi.org/10.48550/arXiv.1901.03460
  • https://doi.org/10.48550/arXiv.2207.09067
  • https://doi.org/10.48550/arXiv.2212.03640
  • https://doi.org/10.48550/arXiv.2405.01337
  • https://doi.org/10.48550/arXiv.1906.03857
  • https://doi.org/10.48550/arXiv.2302.12252
  • https://doi.org/10.48550/arXiv.2104.00682
  • https://doi.org/10.48550/arXiv.1812.03982
Author Will Kay
More Authors
Joao Carreira
Karen Simonyan
Brian Zhang
Chloe Hillier
Sudheendra Vijayanarasimhan
Fabio Viola
Tim Green
Trevor Back
Paul Natsev
Homepage https://www.kinetics-dataset.org/