The AVA dataset densely annotates 80 atomic visual actions in 57.6k movie clips with actions
localized in space and time, resulting in 210k action labels with multiple labels per human
occurring frequently. The main differences with existing video datasets are: (1) the
definition of atomic visual actions, which avoids collecting data for each and every complex
action; (2) precise spatio-temporal annotations with possibly multiple annotations for each
human; (3) the use of diverse, realistic video material (movies).
Our goal is to accelerate research on video action recognition. More details about the dataset and initial experiments can be found in our arXiv paper.