OPT OpenIR  > 光学影像学习与分析中心
CNNs-Based RGB-D Saliency Detection via Cross-View Transfer and Multiview Fusion
Han, Junwei1; Chen, Hao1; Liu, Nian1; Yan, Chenggang2; Li, Xuelong3
Department光学影像学习与分析中心
2018-11
Source PublicationIEEE TRANSACTIONS ON CYBERNETICS
ISSN2168-2267;2168-2275
Volume48Issue:11Pages:3171-3183
Contribution Rank3
Abstract

Salient object detection from RGB-D images aims to utilize both the depth view and RGB view to automatically localize objects of human interest in the scene. Although a few earlier efforts have been devoted to the study of this paper in recent years, two major challenges still remain: 1) how to leverage the depth view effectively to model the depth-induced saliency and 2) how to implement an optimal combination of the RGB view and depth view, which can make full use of complementary information among them. To address these two challenges, this paper proposes a novel framework based on convolutional neural networks (CNNs), which transfers the structure of the RGB-based deep neural network to be applicable for depth view and fuses the deep representations of both views automatically to obtain the final saliency map. In the proposed framework, the first challenge is modeled as a cross-view transfer problem and addressed by using the task-relevant initialization and adding deep supervision in hidden layer. The second challenge is addressed by a multiview CNN fusion model through a combination layer connecting the representation layers of RGB view and depth view. Comprehensive experiments on four benchmark datasets demonstrate the significant and consistent improvements of the proposed approach over other state-of-the-art methods.

KeywordConvolutional Neural Networks (Cnns) Crossview Transfer Multiview Fusion Rgb-d Salient Object Detection
DOI10.1109/TCYB.2017.2761775
Indexed BySCI ; EI
Language英语
WOS IDWOS:000447825400013
PublisherIEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
EI Accession Number20174704417332
Citation statistics
Cited Times:7[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.opt.ac.cn/handle/181661/30683
Collection光学影像学习与分析中心
Corresponding AuthorHan, Junwei
Affiliation1.Northwestern Polytech Univ, Sch Automat, Xian 710129, Shaanxi, Peoples R China
2.Hangzhou Dianzi Univ, Inst Informat & Control, Hangzhou 310018, Zhejiang, Peoples R China
3.Chinese Acad Sci, Xian Inst Opt & Precis Mech, State Key Lab Transient Opt & Photon, Ctr Opt Imagery Anal & Learning, Xian 710119, Shaanxi, Peoples R China
Recommended Citation
GB/T 7714
Han, Junwei,Chen, Hao,Liu, Nian,et al. CNNs-Based RGB-D Saliency Detection via Cross-View Transfer and Multiview Fusion[J]. IEEE TRANSACTIONS ON CYBERNETICS,2018,48(11):3171-3183.
APA Han, Junwei,Chen, Hao,Liu, Nian,Yan, Chenggang,&Li, Xuelong.(2018).CNNs-Based RGB-D Saliency Detection via Cross-View Transfer and Multiview Fusion.IEEE TRANSACTIONS ON CYBERNETICS,48(11),3171-3183.
MLA Han, Junwei,et al."CNNs-Based RGB-D Saliency Detection via Cross-View Transfer and Multiview Fusion".IEEE TRANSACTIONS ON CYBERNETICS 48.11(2018):3171-3183.
Files in This Item:
File Name/Size DocType Version Access License
CNNs-Based RGB-D Sal(2454KB)期刊论文出版稿开放获取CC BY-NC-SAView Application Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Han, Junwei]'s Articles
[Chen, Hao]'s Articles
[Liu, Nian]'s Articles
Baidu academic
Similar articles in Baidu academic
[Han, Junwei]'s Articles
[Chen, Hao]'s Articles
[Liu, Nian]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Han, Junwei]'s Articles
[Chen, Hao]'s Articles
[Liu, Nian]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: CNNs-Based RGB-D Saliency Detection via Cross-View Transfer and Multiview Fusion.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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