Multimodal fusion using learned text concepts for image categorization
MULTIMEDIA '06 Proceedings of the 14th annual ACM international conference on Multimedia
The Pyramid Match Kernel: Efficient Learning with Sets of Features
The Journal of Machine Learning Research
Self-taught learning: transfer learning from unlabeled data
Proceedings of the 24th international conference on Machine learning
Hybrid Generative-Discriminative Visual Categorization
International Journal of Computer Vision
Efficient Learning of Relational Object Class Models
International Journal of Computer Vision
Document image analysis for digital libraries
Proceedings of the 2006 international workshop on Research issues in digital libraries
A New Generative Feature Set Based on Entropy Distance for Discriminative Classification
ICIAP '09 Proceedings of the 15th International Conference on Image Analysis and Processing
SMC'09 Proceedings of the 2009 IEEE international conference on Systems, Man and Cybernetics
Learning compositional categorization models
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part III
MRCS'06 Proceedings of the 2006 international conference on Multimedia Content Representation, Classification and Security
The research on Fisher-RBF data fusion model of network security detection
ISNN'12 Proceedings of the 9th international conference on Advances in Neural Networks - Volume Part II
| Hi-index | 0.00 |
Learning models for detecting and classifying object categories is a challenging problem in machine vision. While discriminative approaches to learning and classification have, in principle, superior performance, generative approaches provide many useful features, one of which is the ability to naturally establish explicit correspondence between model components and scene features 驴 this, in turn, allows for the handling of missing data and unsupervised learning in clutter. We explore a hybrid generative/discriminativeapproach using 驴Fisher kernels驴 [1] which retains most of the desirable properties of generative methods, while increasing the classification performance through a discriminative setting. Furthermore, we demonstrate how this kernel framework can be used to combine different types of features and models into a single classifier. Our experiments, conducted on a number of popular benchmarks, show strong performance improvements over the corresponding generative approach and are competitive with the best results reported in the literature.