Title
Human action recognition in RGB-D videos using motion sequence information and deep learning.
Abstract
•An approach to recognize human actions in RGB-D videos using motion sequence information and deep learning is proposed.•Proposed a new representation of motion information for human action recognition that emphasizes motion in various temporal regions.•The use of motion information in RGB and depth video streams.•Analysis using t-SNE visualization of ConvNet features to show the discriminative characteristics of the proposed representation.
Year
DOI
Venue
2017
10.1016/j.patcog.2017.07.013
Pattern Recognition
Keywords
Field
DocType
Multi-modal action recognition,Deep learning,Motion information,Extreme learning machines
Computer vision,Pattern recognition,Visualization,Convolutional neural network,Computer science,Gesture,Action recognition,RGB color model,Artificial intelligence,Deep learning,Discriminative model,Machine learning
Journal
Volume
Issue
ISSN
72
1
0031-3203
Citations 
PageRank 
References 
17
0.67
36
Authors
2
Name
Order
Citations
PageRank
Earnest Paul Ijjina1675.34
C. Krishna Mohan212417.83