Please use this identifier to cite or link to this item:
Title: Learning to predict eye fixations for semantic contents using multi-layer sparse network
Authors: Shen, C.
Zhao, Q. 
Keywords: Deep learning
Gaze prediction
Semantic saliency
Sparse coding
Issue Date: 22-Aug-2014
Citation: Shen, C., Zhao, Q. (2014-08-22). Learning to predict eye fixations for semantic contents using multi-layer sparse network. Neurocomputing 138 : 61-68. ScholarBank@NUS Repository.
Abstract: In this paper, we present a novel model for saliency prediction under a unified framework of feature integration. The model distinguishes itself by directly learning from natural images and automatically incorporating higher-level semantic information in a scalable manner for gaze prediction. Unlike most existing saliency models that rely on specific features or object detectors, our model learns multiple stages of features that mimic the hierarchical organization of the ventral stream in the visual cortex and integrate them by adapting their weights based on the ground-truth fixation data. To accomplish this, we utilize a multi-layer sparse network to learn low-, mid- and high-level features from natural images and train a linear support vector machine (SVM) for weight adaption and feature integration. Experimental results show that our model could learn high-level semantic features like faces and texts and can perform competitively among existing approaches in predicting eye fixations. © 2014 Elsevier B.V.
Source Title: Neurocomputing
ISSN: 18728286
DOI: 10.1016/j.neucom.2013.09.053
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.