Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/95702
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Type: | Journal article |
Title: | Modeling geometric-temporal context with directional pyramid co-occurrence for action recognition |
Author: | Yuan, C. Li, X. Hu, W. Ling, H. Maybank, S. |
Citation: | IEEE Transactions on Image Processing, 2014; 23(2):658-672 |
Publisher: | IEEE |
Issue Date: | 2014 |
ISSN: | 1057-7149 1941-0042 |
Statement of Responsibility: | Chunfeng Yuan, Xi Li, Weiming Hu, Haibin Ling and Stephen J. Maybank |
Abstract: | In this paper, we present a new geometric-temporal representation for visual action recognition based on local spatio-temporal features. First, we propose a modified covariance descriptor under the log-Euclidean Riemannian metric to represent the spatio-temporal cuboids detected in the video sequences. Compared with previously proposed covariance descriptors, our descriptor can be measured and clustered in Euclidian space. Second, to capture the geometric-temporal contextual information, we construct a directional pyramid co-occurrence matrix (DPCM) to describe the spatio-temporal distribution of the vector-quantized local feature descriptors extracted from a video. DPCM characterizes the co-occurrence statistics of local features as well as the spatio-temporal positional relationships among the concurrent features. These statistics provide strong descriptive power for action recognition. To use DPCM for action recognition, we propose a directional pyramid co-occurrence matching kernel to measure the similarity of videos. The proposed method achieves the state-of-the-art performance and improves on the recognition performance of the bag-of-visual-words (BOVWs) models by a large margin on six public data sets. For example, on the KTH data set, it achieves 98.78% accuracy while the BOVW approach only achieves 88.06%. On both Weizmann and UCF CIL data sets, the highest possible accuracy of 100% is achieved. |
Keywords: | Covariance cuboid descriptor; log-Euclidean Riemannian metric; spatio-temporal directional pyramid co-occurrence matrix; kernel machine; action recognition |
Rights: | © 2013 IEEE |
DOI: | 10.1109/TIP.2013.2291319 |
Published version: | http://dx.doi.org/10.1109/tip.2013.2291319 |
Appears in Collections: | Aurora harvest 7 Computer Science publications |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.