Title

Exploring Sparseness and Self-Similarity for Action Recognition

Authors

Authors

C. Sun; I. N. Junejo; M. Tappen;H. Foroosh

Comments

Authors: contact us about adding a copy of your work at STARS@ucf.edu

Abbreviated Journal Title

IEEE Trans. Image Process.

Keywords

Action recognition; self-similarity; tensor approximation; REPRESENTATION; FEATURES; CONTEXT; Computer Science, Artificial Intelligence; Engineering, Electrical &; Electronic

Abstract

We propose that the dynamics of an action in video data forms a sparse self-similar manifold in the space-time volume, which can be fully characterized by a linear rank decomposition. Inspired by the recurrence plot theory, we introduce the concept of Joint Self-Similarity Volume (Joint-SSV) to model this sparse action manifold, and hence propose a new optimized rank-1 tensor approximation of the Joint-SSV to obtain compact low-dimensional descriptors that very accurately characterize an action in a video sequence. We show that these descriptor vectors make it possible to recognize actions without explicitly aligning the videos in time in order to compensate for speed of execution or differences in video frame rates. Moreover, we show that the proposed method is generic, in the sense that it can be applied using different low-level features, such as silhouettes, tracked points, histogram of oriented gradients, and so forth. Therefore, our method does not necessarily require explicit tracking of features in the space-time volume. Our experimental results on five public data sets demonstrate that our method produces promising results and outperforms many baseline methods.

Journal Title

Ieee Transactions on Image Processing

Volume

24

Issue/Number

8

Publication Date

1-1-2015

Document Type

Article

Language

English

First Page

2488

Last Page

2501

WOS Identifier

WOS:000354441200002

ISSN

1057-7149

Share

COinS