Okutama-Action: An Aerial View Video Dataset for Concurrent Human Action Detection

Abstract

Despite significant progress in the development of human action detection datasets and algorithms, no current dataset is representative of real-world aerial view scenarios. We present Okutama-Action, a new video dataset for aerial view concurrent human action detection. It consists of 43 minute-long fully-annotated sequences with 12 action classes. Okutama-Action features many challenges missing in current datasets, including dynamic transition of actions, significant changes in scale and aspect ratio, abrupt camera movement, as well as multi-labeled actors. As a result, our dataset is more challenging than existing ones, and will help push the field forward to enable real-world applications.

arXiv commentComputer Vision and Pattern Recognition Workshops (CVPRW), Hawaii, USA, 2017

References in corpus (5)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
• Speed/accuracy trade-offs for modern convolutional object detectors
• Human Action Localization with Sparse Spatial Supervision
• Review of Action Recognition and Detection Methods

Cited by in corpus (3)

• Deep Learning for UAV-based Object Detection and Tracking: A Survey
• Convolutional Neural Networks for Aerial Multi-Label Pedestrian Detection
• Convolutional Neural Networks for Aerial Vehicle Detection and Recognition