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

Socpus ID

84856676368 (Scopus)

Source API URL

https://api.elsevier.com/content/abstract/scopus_id/84856676368

This document is currently not available here.

Share

COinS