Top-down visual saliency via joint CRF and dictionary learning

Authors:
Jimei Yang
Affiliations:
University of California at Merced
Venue:
CVPR '12 Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Year:
2012

Citing 0
Cited 5

Visual dictionary learning for joint object categorization and segmentation

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part V
Superpixel based color contrast and color distribution driven salient object detection

Image Communication
Top-Down Saliency Detection via Contextual Pooling

Journal of Signal Processing Systems
Mimicking visual searching with integrated top down cues and low-level features

Neurocomputing
Visual Saliency with Statistical Priors

International Journal of Computer Vision

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.