.png){kind=icon}
Return
Human action recognition with sparse classification and multiple-view learning
.png){kind=icon}
OA
AI
DOI：10.1111/exsy.12040.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Employing multiple camera viewpoints in the recognition of human actions increases performance. This paper presents a feature fusion approach to efficiently combine 2D observations extracted from different camera viewpoints. Multiple-view dimensionality reduction is employed to learn a common parameterization of 2D action descriptors computed for each one of the available viewpoints. Canonical correlation analysis and their variants are employed to obtain such parameterizations. A sparse sequence classifier based on L1 regularization is proposed to avoid the problem of having to choose the proper number of dimensions of the common parameterization. The proposed system is employed in the classification of the Inria Xmas Motion Acquisition Sequences (IXMAS) data set with successful results.
Keywords:
Human Action Recognition
Multiple View Learning
L1 regularization
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
2.3
Papers:
2.6K
Citations:
3.8K
Organization
Cited Papers
Agreement on Indication for Systemic Therapy between Biopsied Tissue and Surgical Excision Specimens in Breast Cancer Patients.png)
PLoS ONEOAAI
PLoS ONEIF0
OAAIShareSaveShareSave
A TUTORIAL ON HIDDEN MARKOV-MODELS AND SELECTED APPLICATIONS IN SPEECH RECOGNITIONPROCEEDINGS OF THE IEEE
PROCEEDINGS OF THE IEEEIF25.9
PREAI
ShareSaveTracking disease progression by searching paths in a temporal network of biological processesPLOS ONEOAAI
PLOS ONEIF0
OAAIShareSave
View more