Title
Action Recognition Using Rank-1 Approximation Of Joint Self-Similarity Volume
Abstract
In this paper, we make three main contributions in the area of action recognition: (i) We introduce the concept of Joint Self-Similarity Volume (Joint SSV) for modeling dynamical systems, and show that by using a new optimized rank-1 tensor approximation of Joint SSV one can obtain compact low-dimensional descriptors that very accurately preserve the dynamics of the original system, e.g. an action video sequence; (ii) The descriptor vectors derived from the optimized rank-1 approximation make it possible to recognize actions without explicitly aligning the action sequences of varying speed of execution or different frame rates; (iii) The method is generic and can be applied using different low-level features such as silhouettes, histogram of oriented gradients, etc. Hence, it does not necessarily require explicit tracking of features in the space-time volume. Our experimental results on three public datasets demonstrate that our method produces remarkably good results and outperforms all baseline methods. © 2011 IEEE.
Publication Date
12-1-2011
Publication Title
Proceedings of the IEEE International Conference on Computer Vision
Number of Pages
1007-1012
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1109/ICCV.2011.6126345
Copyright Status
Unknown
Socpus ID
84856676368 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/84856676368
STARS Citation
Sun, Chuan; Junejo, Imran; and Foroosh, Hassan, "Action Recognition Using Rank-1 Approximation Of Joint Self-Similarity Volume" (2011). Scopus Export 2010-2014. 2247.
https://stars.library.ucf.edu/scopus2010/2247