Sorry, you need to enable JavaScript to visit this website.

Egok360: A 360 Egocentric Kinetic Human Activity Video Dataset

Primary tabs

Citation Author(s):
Mario A. DeLaGarza, Ziliang Zong, Hugo Latapie, Yan Yan
Submitted by:
Keshav Bhandari
Last updated:
2 November 2020 - 10:59am
Document Type:
Presentation Slides
Document Year:
2020
Event:
Presenters Name:
Keshav Bhandari
Paper Code:
1398

Abstract 

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/.

up
0 users have voted:

Dataset Files

icip_presentation.pdf

(325)