We are part of the Perception Team at Google AI, which tackles the hard problems of understanding images, sounds, music and video. Our long-term technology mission is to enable machines to achieve human-level intelligence in sensory perception, at super-human scales.

In particular, we are excited about imbuing computers with "social visual intelligence" -- the ability to perceive what humans are doing, what might they do next, and what they are trying to achieve. We believe that AVA's fine spatio-temporal granularity, together with its scale, will help foster AI research aimed towards this goal both at Google and elsewhere.

If you have questions about the dataset, or would like to be notified of updates, please subscribe to Google Group: ava-dataset-users.

The people who worked extensively to bring you the AVA Actions dataset:

Those who brought you the AVA Spoken Activity dataset:

And finally the people behind the AVA-Kinetics dataset: