Exploring Sparseness And Self-Similarity For Action Recognition
Keywords
Action recognition; self-similarity; tensor approximation
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.
Publication Date
8-6-2015
Publication Title
IEEE Transactions on Image Processing
Volume
24
Issue
8
Number of Pages
2488-2501
Document Type
Article
Personal Identifier
scopus
DOI Link
https://doi.org/10.1109/TIP.2015.2424316
Copyright Status
Unknown
Socpus ID
84929190420 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/84929190420
STARS Citation
Sun, Chuan; Junejo, Imran Nazir; Tappen, Marshall; and Foroosh, Hassan, "Exploring Sparseness And Self-Similarity For Action Recognition" (2015). Scopus Export 2015-2019. 608.
https://stars.library.ucf.edu/scopus2015/608