Visual dictionary learning for joint object categorization and segmentation
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part V
Top-Down Saliency Detection via Contextual Pooling
Journal of Signal Processing Systems
Visual Saliency with Statistical Priors
International Journal of Computer Vision
Hi-index | 0.00 |
Top-down visual saliency facilities object localization by providing a discriminative representation of target objects and a probability map for reducing the search space. In this paper, we propose a novel top-down saliency model that jointly learns a Conditional Random Field (CRF) and a discriminative dictionary. The proposed model is formulated based on a CRF with latent variables. By using sparse codes as latent variables, we train the dictionary modulated by CRF, and meanwhile a CRF with sparse coding. We propose a max-margin approach to train our model via fast inference algorithms. We evaluate our model on the Graz-02 and PASCAL VOC 2007 datasets. Experimental results show that our model performs favorably against the state-of-the-art top-down saliency methods. We also observe that the dictionary update significantly improves the model performance.