Global and Local-Contrast Guides Content-Aware Fusion for RGB-D Saliency Prediction

被引：134

作者：

Zhou, Wujie ^{[1
,2
]}

Lv, Ying ^{[1
]}

Lei, Jingsheng ^{[1
]}

Yu, Lu ^{[2
]}

机构：

[1] Zhejiang Univ Sci & Technol, Sch Informat & Elect Engn, Hangzhou 310023, Peoples R China

[2] Zhejiang Univ, Inst Informat & Commun Engn, Hangzhou 310023, Peoples R China

来源：

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS | 2021年 / 51卷 / 06期

基金：

中国国家自然科学基金;

关键词：

Feature extraction; Predictive models; Fuses; Convolution; Visualization; Image resolution; Deep learning; Contrast feature; local-global feature; RGB-D image; RGB-D saliency prediction; OBJECT DETECTION; REGION;

D O I：

10.1109/TSMC.2019.2957386

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Many RGB-D visual attention models have been proposed with diverse fusion models; thus, the main challenge lies in the differences in the results between the different models. To address this challenge, we propose a local-global fusion model for fixation prediction on an RGB-D image; this method combines global and local information through a content-aware fusion module (CAFM) structure. First, it comprises a channel-based upsampling block for exploiting global contextual information and scaling up this information to the same resolution as the input. Second, our Deconv block contains a contrast feature module to utilize multilevel local features stage-by-stage for superior local feature representation. The experimental results demonstrate that the proposed model exhibits competitive performance on two databases.

引用

页码：3641 / 3649

页数：9