CSMMI: Class-Specific Maximization of Mutual Information for Action and Gesture Recognition
Authors:
- 3 June 2014
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 23 (7) , 3152-3165
Abstract
In this paper, we propose a novel approach called class-specific maximization of mutual information (CSMMI) using a submodular method, which aims at learning a compact and discriminative dictionary for each class. Unlike traditional dictionary-based algorithms, which typically learn a shared dictionary for all of the classes, we unify the intraclass and interclass mutual information (MI) into an single objective function to optimize class-specific dictionary. The objective function has two aims: 1) maximizing the MI between dictionary items within a specific class (intrinsic structure) and 2) minimizing the MI between the dictionary items in a given class and those of the other classes (extrinsic structure). We significantly reduce the computational complexity of CSMMI by introducing an novel submodular method, which is one of the important contributions of this paper. This paper also contributes a state-of-the-art end-to-end system for action and gesture recognition incorporating CSMMI, with feature extraction, learning initial dictionary per each class by sparse coding, CSMMI via submodularity, and classification based on reconstruction errors. We performed extensive experiments on synthetic data and eight benchmark data sets. Our experimental results show that CSMMI outperforms shared dictionary methods and that our end-to-end system is competitive with other state-of-the-art approaches.Keywords
Funding Information
- National Natural Science Foundation of China (61172128)
- National Key Basic Research Program of China (2012CB316304)
- New Century Excellent Talents in University (NCET-12-0768)
- Program for Innovative Research Team in University, Ministry of Education of China (IRT201206)
- Beijing Higher Education Young Elite Teacher (YETP0544)
- National Science Foundation (IIS-1055062, CNS-1059235, CNS-1035913, CNS-1338118)
This publication has 43 references indexed in Scilit:
- ChaLearn multi-modal gesture recognition 20132013
- Action Recognition From Video Using Feature Covariance MatricesIEEE Transactions on Image Processing, 2013
- ChaLearn gesture challenge: Design and first results2012
- Learning semantic features for action recognition via diffusion mapsComputer Vision and Image Understanding, 2012
- Actions in context2009
- Human Action Recognition in Videos Using Kinematic Features and Multiple Instance LearningIEEE Transactions on Pattern Analysis and Machine Intelligence, 2008
- Action MACH a spatio-temporal Maximum Average Correlation Height filter for action recognition2008
- Classification using intersection kernel support vector machines is efficient2008
- Actions as Space-Time ShapesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2007
- Actions as space-time shapes2005