AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions
Authors:
Preprint
Abstract
This paper introduces a video dataset of spatio-temporally localized Atomic Visual Actions (AVA). 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). This departs from existing datasets for spatio-temporal action recognition, such as JHMDB and UCF datasets, which provide annotations for at most 24 composite actions, such as basketball dunk, captured in specific environments, i.e., basketball court. We implement a state-of-the-art approach for action localization. Despite this, the performance on our dataset remains low and underscores the need for developing new approaches for video understanding. The AVA dataset is the first step in this direction, and enables the measurement of performance and progress in realistic scenarios.Keywords
All Related Versions
This publication has 25 references indexed in Scilit:
- Every Moment Counts: Dense Detailed Labeling of Actions in Complex VideosInternational Journal of Computer Vision, 2017
- Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding2016
- Spot On: Action Localization from Pointly-Supervised Proposals2016
- The Pascal Visual Object Classes Challenge: A RetrospectiveInternational Journal of Computer Vision, 2014
- Large-Scale Video Classification with Convolutional Neural Networks2014
- A Naturalistic Open Source Movie for Optical Flow Evaluation2012
- Action MACH a spatio-temporal Maximum Average Correlation Height filter for action recognition2008
- Perceiving, remembering, and communicating structure in events.Journal of Experimental Psychology: General, 2001
- Event structure in perception and conception.Psychological Bulletin, 2001
- Attribution and the unit of perception of ongoing behavior.Journal of Personality and Social Psychology, 1973