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

facebooktwittermailshare

Action Recognition In RGB-D Egocentric Videos

Abstract: 

In this paper, we investigate the problem of action recognition in RGB-D egocentric videos. These self-generated and embodied videos provide richer semantic cues than the conventional videos captured from the third-person view for action recognition. Moreover, they contain both appearance information and 3D structure of the scenes from the RGB modality and depth modality respectively. Motivated by these advantages,
we first collect a video-based RGB-D egocentric dataset (THU-READ) with diverse types of daily-life actions. Then we evaluate several approaches including hand-crafted features and deep learning methods on THU-READ. To improve the performance, we further develop a tri-stream convolutional network (TCNet) method, which learns to exploit the fuse with both the RGB and depth modalities for action recognition.
Experimental results show that our model achieves competitive performance with state-of-the-art methods.

up
0 users have voted:

Paper Details

Authors:
Yansong Tang, Yi Tian, Jiwen Lu, Jianjiang Feng, Jie Zhou
Submitted On:
6 September 2017 - 9:35am
Short Link:
Type:
Poster
Event:
Presenter's Name:
Yansong Tang
Paper Code:
ICIP-2674
Document Year:
2017
Cite

Document Files

ICIP_poster.pdf

(11 downloads)

Subscribe

[1] Yansong Tang, Yi Tian, Jiwen Lu, Jianjiang Feng, Jie Zhou, "Action Recognition In RGB-D Egocentric Videos", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/1842. Accessed: Sep. 19, 2017.
@article{1842-17,
url = {http://sigport.org/1842},
author = {Yansong Tang; Yi Tian; Jiwen Lu; Jianjiang Feng; Jie Zhou },
publisher = {IEEE SigPort},
title = {Action Recognition In RGB-D Egocentric Videos},
year = {2017} }
TY - EJOUR
T1 - Action Recognition In RGB-D Egocentric Videos
AU - Yansong Tang; Yi Tian; Jiwen Lu; Jianjiang Feng; Jie Zhou
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/1842
ER -
Yansong Tang, Yi Tian, Jiwen Lu, Jianjiang Feng, Jie Zhou. (2017). Action Recognition In RGB-D Egocentric Videos. IEEE SigPort. http://sigport.org/1842
Yansong Tang, Yi Tian, Jiwen Lu, Jianjiang Feng, Jie Zhou, 2017. Action Recognition In RGB-D Egocentric Videos. Available at: http://sigport.org/1842.
Yansong Tang, Yi Tian, Jiwen Lu, Jianjiang Feng, Jie Zhou. (2017). "Action Recognition In RGB-D Egocentric Videos." Web.
1. Yansong Tang, Yi Tian, Jiwen Lu, Jianjiang Feng, Jie Zhou. Action Recognition In RGB-D Egocentric Videos [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/1842