Next Article in Journal
Localization with Transfer Learning Based on Fine-Grained Subcarrier Information for Dynamic Indoor Environments
Next Article in Special Issue
Vision-Based Road Rage Detection Framework in Automotive Safety Applications
Previous Article in Journal
Density Distribution Maps: A Novel Tool for Subcellular Distribution Analysis and Quantitative Biomedical Imaging
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Sensors
Volume 21
Issue 3
10.3390/s21031005
sensors-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Improved Action Recognition with Separable Spatio-Temporal Attention Using Alternative Skeletal and Video Pre-Processing

by
Pau Climent-Pérez
* and
Francisco Florez-Revuelta
Department of Computing Technology, University of Alicante, P.O. Box 99, E-03080 Alicante, Spain
*
Author to whom correspondence should be addressed.
Sensors 2021, 21(3), 1005; https://doi.org/10.3390/s21031005
Submission received: 4 January 2021 / Revised: 25 January 2021 / Accepted: 29 January 2021 / Published: 2 February 2021
(This article belongs to the Special Issue Signal, Image Processing and Computer Vision in Smart Living Applications)
Browse Figures
Versions Notes

Abstract

The potential benefits of recognising activities of daily living from video for active and assisted living have yet to be fully untapped. These technologies can be used for behaviour understanding, and lifelogging for caregivers and end users alike. The recent publication of realistic datasets for this purpose, such as the Toyota Smarthomes dataset, calls for pushing forward the efforts to improve action recognition. Using the separable spatio-temporal attention network proposed in the literature, this paper introduces a view-invariant normalisation of skeletal pose data and full activity crops for RGB data, which improve the baseline results by 9.5% (on the cross-subject experiments), outperforming state-of-the-art techniques in this field when using the original unmodified skeletal data in dataset. Our code and data are available online.
Keywords: active and assisted living; action recognition; computer vision; spatio-temporal attention; deep learning; inflated convolutional neural networks active and assisted living; action recognition; computer vision; spatio-temporal attention; deep learning; inflated convolutional neural networks

Share and Cite

MDPI and ACS Style

Climent-Pérez, P.; Florez-Revuelta, F. Improved Action Recognition with Separable Spatio-Temporal Attention Using Alternative Skeletal and Video Pre-Processing. Sensors 2021, 21, 1005. https://doi.org/10.3390/s21031005

AMA Style

Climent-Pérez P, Florez-Revuelta F. Improved Action Recognition with Separable Spatio-Temporal Attention Using Alternative Skeletal and Video Pre-Processing. Sensors. 2021; 21(3):1005. https://doi.org/10.3390/s21031005

Chicago/Turabian Style

Climent-Pérez, Pau, and Francisco Florez-Revuelta. 2021. "Improved Action Recognition with Separable Spatio-Temporal Attention Using Alternative Skeletal and Video Pre-Processing" Sensors 21, no. 3: 1005. https://doi.org/10.3390/s21031005

APA Style

Climent-Pérez, P., & Florez-Revuelta, F. (2021). Improved Action Recognition with Separable Spatio-Temporal Attention Using Alternative Skeletal and Video Pre-Processing. Sensors, 21(3), 1005. https://doi.org/10.3390/s21031005

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop