Skip to main content
padlock icon - secure page this page is secure

Deep CNN Object Features for Improved Action Recognition in Low Quality Videos

Buy Article:

$106.51 + tax (Refund Policy)

Human action recognition from low quality video remains a challenging task for the action recognition community. Recent state-of-the-art methods such as space-time interest point (STIP) uses shape and motion features for characterization of action. However, STIP features are over-reliant on video quality and lack robust object semantics. This paper harness the robustness of deeply learned object features from off-the-shelf convolutional neural network (CNN) models to improve action recognition under low quality conditions. A two-channel framework that aggregates shape and motion features extracted using STIP detector, and frame-level object features obtained from the final few layers (i.e., FC6, FC7, softmax layer) of a state-of-the-art image-trained CNN model is proposed. Experimental results on low quality versions of two publicly available datasets—UCF-11 and HMDB51, showed that the use of CNN object features together with conventional shape and motion can greatly improve the performance of action recognition in low quality videos.
No Reference information available - sign in for access.
No Citation information available - sign in for access.
No Supplementary Data.
No Article Media
No Metrics

Keywords: Action Recognition; CNN; Deep Learning; Feature Representation; Low Quality Video; STIP

Document Type: Research Article

Affiliations: Centre for Visual Computing and Informatics, Faculty of Computing and Informatics, Multimedia University, Cyberjaya 63100, Malaysia

Publication date: November 1, 2017

More about this publication?
  • ADVANCED SCIENCE LETTERS is an international peer-reviewed journal with a very wide-ranging coverage, consolidates research activities in all areas of (1) Physical Sciences, (2) Biological Sciences, (3) Mathematical Sciences, (4) Engineering, (5) Computer and Information Sciences, and (6) Geosciences to publish original short communications, full research papers and timely brief (mini) reviews with authors photo and biography encompassing the basic and applied research and current developments in educational aspects of these scientific areas.
  • Editorial Board
  • Information for Authors
  • Subscribe to this Title
  • Ingenta Connect is not responsible for the content or availability of external websites
  • Access Key
  • Free content
  • Partial Free content
  • New content
  • Open access content
  • Partial Open access content
  • Subscribed content
  • Partial Subscribed content
  • Free trial content
Cookie Policy
X
Cookie Policy
Ingenta Connect website makes use of cookies so as to keep track of data that you have filled in. I am Happy with this Find out more