Overview: Can humans fly? Emphatically no. Can cars eat? Again, absolutely not. Yet, these absurd inferences result from the current disregard for particular types of actors in action understanding. There is no work we know of on simultaneously inferring actors and actions in the video, not to mention a dataset to experiment with. A2D hence marks the first effort in the computer vision community to jointly consider various types of actors undergoing various actions. To be exact, we consider seven actor classes (adult, baby, ball, bird, car, cat, and dog) and eight action classes (climb, crawl, eat, fly, jump, roll, run, and walk) not including the no-action class, which we also consider. The A2D has 3782 videos with at least 99 instances per valid actor-action tuple and videos are labeled with both pixel-level actors and actions for sampled frames. The A2D dataset serves as a novel large-scale testbed for various vision problems: video-level single- and multiple-label actor-action recognition, instance-level object segmentation/co-segmentation, as well as pixel-level actor-action semantic segmentation to name a few.
Version 2.0 with more labeled frames (more than five per video) and untrimmed videos is coming soon in this fall. Please check back later.
Version 1.0: 3782 short videos with 3 to 5 frames per video labeled.