AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions

This paper introduces a video dataset of spatio-temporally localized Atomic Visual Actions (AVA). The AVA dataset densely annotates 80 atomic visual actions in 430 15-minute video clips, where actions are localized in space and time, resulting in 1.58M action labels with multiple labels per person occurring frequently... The key characteristics of our dataset are: (1) the definition of atomic visual actions, rather than composite actions; (2) precise spatio-temporal annotations with possibly multiple annotations for each person; (3) exhaustive annotation of these atomic actions over 15-minute video clips; (4) people temporally linked across consecutive segments; and (5) using movies to gather a varied set of action representations. This departs from existing datasets for spatio-temporal action recognition, which typically provide sparse annotations for composite actions in short video clips. We will release the dataset publicly. AVA, with its realistic scene and action complexity, exposes the intrinsic difficulty of action recognition. To benchmark this, we present a novel approach for action localization that builds upon the current state-of-the-art methods, and demonstrates better performance on JHMDB and UCF101-24 categories. While setting a new state of the art on existing datasets, the overall results on AVA are low at 15.6% mAP, underscoring the need for developing new approaches for video understanding. read more

PDF Abstract CVPR 2018 PDF CVPR 2018 Abstract

Datasets


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Temporal Action Localization J-HMDB-21 Faster-RCNN + two-stream I3D conv Frame-mAP 73.3 # 2
Video-mAP 0.5 78.6 # 2
Temporal Action Localization UCF101-24 Faster-RCNN + two-stream I3D conv Frame-mAP 76.3 # 2
Video-mAP 0.5 59.9 # 1

Results from Other Papers


Task Dataset Model Metric Name Metric Value Rank Source Paper Compare
Action Recognition AVA v2.1 S3D-G w/ ResNet RPN (Kinetics-400 pretraining( mAP (Val) 22.0 # 9

Methods


No methods listed for this paper. Add relevant methods here