期刊
IEEE TRANSACTIONS ON IMAGE PROCESSING
卷 27, 期 10, 页码 5142-5154出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIP.2018.2851672
关键词
Saliency; human eye fixations; convolutional neural networks; deep learning
资金
- CINECA award under the ISCRA initiative
- Facebook AI Research
- NVIDIA Corporation
Data-driven saliency has recently gained a lot of attention thanks to the use of convolutional neural networks for predicting gaze fixations. In this paper, we go beyond standard approaches to saliency prediction, in which gaze maps are computed with a feed-forward network, and present a novel model which can predict accurate saliency maps by incorporating neural attentive mechanisms. The core of our solution is a convolutional long short-term memory that focuses on the most salient regions of the input image to iteratively refine the predicted saliency map. In addition, to tackle the center bias typical of human eye fixations, our model can learn a set of prior maps generated with Gaussian functions. We show, through an extensive evaluation, that the proposed architecture outperforms the current state-of-the-art on public saliency prediction datasets. We further study the contribution of each key component to demonstrate their robustness on different scenarios.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据