Hierarchical Gaussian descriptor based on local pooling for action recognition

In this paper, we propose a new approach based on Gaussian descriptors for action recognition. We first develop a feature representation technique that encodes high-order statistics of local features in two levels, where single Gaussians are used to capture the distributions involved. To deal with t...

Full description

Saved in:
Bibliographic Details
Published in:Machine vision and applications 2019-03, Vol.30 (2), p.321-343
Main Authors: Nguyen, Xuan Son, Mouaddib, Abdel-Illah, Nguyen, Thanh Phuong
Format: Article
Language:English
Subjects:
Cluster analysis
Clustering
Communications Engineering
Computer Science
Computer Vision and Pattern Recognition
Datasets
Discrete Mathematics
Feature recognition
Image Processing and Computer Vision
Networks
Object recognition
Original Paper
Pattern Recognition
Representations
Vector quantization
Vision systems
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, we propose a new approach based on Gaussian descriptors for action recognition. We first develop a feature representation technique that encodes high-order statistics of local features in two levels, where single Gaussians are used to capture the distributions involved. To deal with the possible loss of information about the distribution of features caused by heterogeneous feature vectors when summarizing them, we use K-means clustering and Sparse Coding to construct some sets of feature vectors over which the summarization is performed. We then present two methods based on depth images and pose data for action recognition. In both methods, the proposed feature representation technique is applied to effectively obtain discriminative action descriptors. Experimental evaluation on the seven benchmark datasets, i.e., MSRAction3D, MSRGesture3D, DHA, SKIG, Florence, UTKinect, and HDM05, shows that our methods achieve very promising results on all the datasets.
ISSN:0932-8092
1432-1769
DOI:10.1007/s00138-018-0989-9