Saliency, Scale and Image Description
International Journal of Computer Vision
Object Recognition from Local Scale-Invariant Features
ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
Proceedings of the 26th annual international ACM SIGIR conference on Research and development in informaion retrieval
The Journal of Machine Learning Research
Image Categorization by Learning and Reasoning with Regions
The Journal of Machine Learning Research
CVPRW '04 Proceedings of the 2004 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'04) Volume 12 - Volume 12
Discovering Objects and their Localization in Images
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
Learning Object Categories from Google"s Image Search
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
Graph-based multiple-instance learning for object-based image retrieval
MIR '08 Proceedings of the 1st ACM international conference on Multimedia information retrieval
Human Action Recognition by Semilatent Topic Models
IEEE Transactions on Pattern Analysis and Machine Intelligence
Image Classification via Semi-supervised pLSA
ICIG '09 Proceedings of the 2009 Fifth International Conference on Image and Graphics
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part IV
A hybrid semi-supervised topic model
IScIDE'11 Proceedings of the Second Sino-foreign-interchange conference on Intelligent Science and Intelligent Data Engineering
A jointly distributed semi-supervised topic model
Neurocomputing
Hi-index | 0.00 |
Topic models are a popular tool for visual concept learning. Current topic models are either unsupervised or fully supervised. Although lots of labeled images can significantly improve the performance of topic models, they are very costly to acquire. Meanwhile, billions of unlabeled images are freely available on the internet. In this paper, to take advantage of both limited labeled training images and rich unlabeled images, we propose a novel technique called regularized Semi-supervised Latent Dirichlet Allocation (r-SSLDA) for learning visual concept classifiers. Instead of introducing a new topic model, we attempt to find an efficient way to learn topic models in a semi-supervised way. r-SSLDA considers both semi-supervised properties and supervised topic model simultaneously in a regularization framework. Experiments on Caltech 101 and Caltech 256 have shown that r-SSLDA outperforms unsupervised LDA, and achieves competitive performance against fully supervised LDA, while sharply reducing the number of labeled images required.