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

facebooktwittermailshare

LEARNING TEMPORAL INFORMATION FROM SPATIAL INFORMATION USING CAPSNETS FOR HUMAN ACTION RECOGNITION

Abstract: 

Capsule Networks (CapsNets) are recently introduced to overcome some of the shortcomings of traditional Convolutional Neural Networks (CNNs). CapsNets replace neurons in CNNs with vectors to retain spatial relationships among the features. In this paper, we propose a CapsNet architecture that employs individual video frames for human action recognition without explicitly extracting motion information. We also propose weight pooling to reduce the computational complexity and improve the classification accuracy by appropriately removing some of the extracted features. We show how the capsules of the proposed architecture can encode temporal information by using the spatial features extracted from several video frames. Compared with a traditional CNN of the same complexity, the proposed CapsNet improves action recognition performance by 12.11% and 22.29% on the KTH and UCF-sports datasets, respectively.

up
0 users have voted:

Paper Details

Authors:
Abdullah M. Algamdi , Victor Sanchez , Chang-Tsun Li
Submitted On:
8 May 2019 - 8:03am
Short Link:
Type:
Poster
Event:
Presenter's Name:
Abdullah Algamdi
Paper Code:
2503
Document Year:
2019
Cite

Document Files

ICASSP_poster_2019__1_ (2).pdf

(38)

Subscribe

[1] Abdullah M. Algamdi , Victor Sanchez , Chang-Tsun Li, "LEARNING TEMPORAL INFORMATION FROM SPATIAL INFORMATION USING CAPSNETS FOR HUMAN ACTION RECOGNITION", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4079. Accessed: Dec. 06, 2019.
@article{4079-19,
url = {http://sigport.org/4079},
author = {Abdullah M. Algamdi ; Victor Sanchez ; Chang-Tsun Li },
publisher = {IEEE SigPort},
title = {LEARNING TEMPORAL INFORMATION FROM SPATIAL INFORMATION USING CAPSNETS FOR HUMAN ACTION RECOGNITION},
year = {2019} }
TY - EJOUR
T1 - LEARNING TEMPORAL INFORMATION FROM SPATIAL INFORMATION USING CAPSNETS FOR HUMAN ACTION RECOGNITION
AU - Abdullah M. Algamdi ; Victor Sanchez ; Chang-Tsun Li
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4079
ER -
Abdullah M. Algamdi , Victor Sanchez , Chang-Tsun Li. (2019). LEARNING TEMPORAL INFORMATION FROM SPATIAL INFORMATION USING CAPSNETS FOR HUMAN ACTION RECOGNITION. IEEE SigPort. http://sigport.org/4079
Abdullah M. Algamdi , Victor Sanchez , Chang-Tsun Li, 2019. LEARNING TEMPORAL INFORMATION FROM SPATIAL INFORMATION USING CAPSNETS FOR HUMAN ACTION RECOGNITION. Available at: http://sigport.org/4079.
Abdullah M. Algamdi , Victor Sanchez , Chang-Tsun Li. (2019). "LEARNING TEMPORAL INFORMATION FROM SPATIAL INFORMATION USING CAPSNETS FOR HUMAN ACTION RECOGNITION." Web.
1. Abdullah M. Algamdi , Victor Sanchez , Chang-Tsun Li. LEARNING TEMPORAL INFORMATION FROM SPATIAL INFORMATION USING CAPSNETS FOR HUMAN ACTION RECOGNITION [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4079