Skip to content Skip to navigation
University of Warwick
  • Study
  • |
  • Research
  • |
  • Business
  • |
  • Alumni
  • |
  • News
  • |
  • About

University of Warwick
Publications service & WRAP

Highlight your research

  • WRAP
    • Home
    • Search WRAP
    • Browse by Warwick Author
    • Browse WRAP by Year
    • Browse WRAP by Subject
    • Browse WRAP by Department
    • Browse WRAP by Funder
    • Browse Theses by Department
  • Publications Service
    • Home
    • Search Publications Service
    • Browse by Warwick Author
    • Browse Publications service by Year
    • Browse Publications service by Subject
    • Browse Publications service by Department
    • Browse Publications service by Funder
  • Help & Advice
University of Warwick

The Library

  • Login
  • Admin

Learning temporal information from spatial information using CAPSNETS for human action recognition

Tools
- Tools
+ Tools

Algamdi, Abdullah M., Sanchez Silva, Victor and Li, Chang-Tsun (2019) Learning temporal information from spatial information using CAPSNETS for human action recognition. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, UK, 12-17 May 2019 ISBN 9781479981311. ISSN 2379-190X. doi:10.1109/ICASSP.2019.8683720

[img]
Preview
PDF
WRAP-learning-temporal-information-spatial-information-using-CAPSNETS-human-action-recognition-Li-2019.pdf - Accepted Version - Requires a PDF viewer.

Download (1030Kb) | Preview
Official URL: http://dx.doi.org/10.1109/ICASSP.2019.8683720

Request Changes to record.

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.

Item Type: Conference Item (Paper)
Subjects: Q Science > QA Mathematics > QA76 Electronic computers. Computer science. Computer software
T Technology > TA Engineering (General). Civil engineering (General)
Divisions: Faculty of Science > Computer Science
Library of Congress Subject Headings (LCSH): Optical pattern recognition, Image processing -- Digital techniques, Computer vision, Computer vision -- Mathematical models, Pattern perception, Neural networks (Computer science) , Human face recognition (Computer science)
Publisher: IEEE
ISBN: 9781479981311
ISSN: 2379-190X
Official Date: 2019
Dates:
DateEvent
2019Published
17 April 2019Available
15 December 2018Accepted
DOI: 10.1109/ICASSP.2019.8683720
Status: Peer Reviewed
Publication Status: Published
Publisher Statement: © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Access rights to Published version: Restricted or Subscription Access
RIOXX Funder/Project Grant:
Project/Grant IDRIOXX Funder NameFunder ID
690907Horizon 2020 Framework Programmehttp://dx.doi.org/10.13039/100010661
Conference Paper Type: Paper
Title of Event: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Type of Event: Conference
Location of Event: Brighton, UK
Date(s) of Event: 12-17 May 2019

Request changes or add full text files to a record

Repository staff actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics

twitter

Email us: wrap@warwick.ac.uk
Contact Details
About Us