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... (read more)

PDF Abstract CVPR 2018 PDF CVPR 2018 Abstract
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

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet