You're currently viewing an old version of this dataset. To see the current version, click here.

Something-Something v2 (SSv2)

The Something-Something v2 (SSv2) dataset is a large collection of video clips of humans performing actions with everyday objects.

Data and Resources

This dataset has no data

Cite this as

Raghav Goyal, Samira Ebrahimi Kahou, Vincent Michalski, Joanna Materzynska, Susanne Westphal, Heuna Kim, Ingo Fruend, Peter Yianilos, Moritz Mueller-Freitag (2024). Dataset: Something-Something v2 (SSv2). https://doi.org/10.57702/3nv86o47

Private DOI This DOI is not yet resolvable.
It is available for use in manuscripts, and will be published when the Dataset is made public.

Additional Info

Field Value
Created December 3, 2024
Last update December 3, 2024
Defined In https://doi.org/10.48550/arXiv.2212.03640
Author Raghav Goyal
More Authors
Samira Ebrahimi Kahou
Vincent Michalski
Joanna Materzynska
Susanne Westphal
Heuna Kim
Ingo Fruend
Peter Yianilos
Moritz Mueller-Freitag
Homepage https://www.something-something-v2.org/