Egok360: A 360 Egocentric Kinetic Human Activity Video Dataset
arXiv:2010.08055
Abstract
Recently, there has been a growing interest in wearable sensors which provides new research perspectives for 360 ° video analysis. However, the lack of 360 ° datasets in literature hinders the research in this field. To bridge this gap, in this paper we propose a novel Egocentric (first-person) 360° Kinetic human activity video dataset (EgoK360). The EgoK360 dataset contains annotations of human activity with different sub-actions, e.g., activity Ping-Pong with four sub-actions which are pickup-ball, hit, bounce-ball and serve. To the best of our knowledge, EgoK360 is the first dataset in the domain of first-person activity recognition with a 360° environmental setup, which will facilitate the egocentric 360 ° video understanding. We provide experimental results and comprehensive analysis of variants of the two-stream network for 360 egocentric activity recognition. The EgoK360 dataset can be downloaded from https://egok360.github.io/.
arXiv comment5 pages, 5 figures, 1 table, 2020 IEEE International Conference on Image Processing (ICIP)
References in corpus (9)
- Two-Stream Convolutional Networks for Action Recognition in Videos
- UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
- The Kinetics Human Action Video Dataset
- Learning Deep Features for Discriminative Localization
- Learning Spherical Convolution for Fast Features from 360° Imagery
- Charades-Ego: A Large-Scale Dataset of Paired Third and First Person Videos
- Kernel Transformer Networks for Compact Spherical Convolution
- Cube Padding for Weakly-Supervised Saliency Prediction in 360° Videos
- Simple to Complex Cross-modal Learning to Rank