Title
Human Action Recognition In Large-Scale Datasets Using Histogram Of Spatiotemporal Gradients
Abstract
Research in human action recognition has advanced along multiple fronts in recent years to address various types of actions including simple, isolated actions in staged data (e.g., KTH dataset), complex actions (e.g., Hollywood dataset) and naturally occurring actions in surveillance videos (e.g, VIRAT dataset [1]). Several techniques including those based on gradient, flow and interest-points have been developed for their recognition. Most perform very well in standard action recognition datasets, but fail to produce similar results in more complex, large-scale datasets. Here we analyze the reasons for this less than successful generalization by considering a state-of-the-art technique, histogram of oriented gradients in spatiotemporal volumes as an example. This analysis may prove useful in developing robust and effective techniques for action recognition. © 2012 IEEE.
Publication Date
11-6-2012
Publication Title
Proceedings - 2012 IEEE 9th International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2012
Number of Pages
106-111
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1109/AVSS.2012.40
Copyright Status
Unknown
Socpus ID
84868230243 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/84868230243
STARS Citation
Reddy, Kishore K.; Cuntoor, Naresh; Perera, Amitha; and Hoogs, Anthony, "Human Action Recognition In Large-Scale Datasets Using Histogram Of Spatiotemporal Gradients" (2012). Scopus Export 2010-2014. 4755.
https://stars.library.ucf.edu/scopus2010/4755