Cosaliency Detection Based on Intrasaliency Prior Transfer and Deep Intersaliency Mining

As an interesting and emerging topic, cosaliency detection aims at simultaneously extracting common salient objects in multiple related images. It differs from the conventional saliency detection paradigm in which saliency detection for each image is determined one by one independently without takin...

Full description

Saved in:

Bibliographic Details
Published in:	IEEE transaction on neural networks and learning systems Vol. 27; no. 6; pp. 1163 - 1176
Main Authors:	Zhang, Dingwen, Han, Junwei, Han, Jungong, Shao, Ling
Format:	Journal Article
Language:	English
Published:	United States IEEE 01.06.2016
Subjects:	Construction Cosaliency detection Data mining deep learning Encoding Feature extraction Homogeneity Image detection Learning Machine learning Mining Neural networks Object recognition prior transfer Robustness stacked denoising autoencoder (SDAE) Training Visualization stacked denoising autoencoder (SDAE) deep learning Cosaliency detection prior transfer
ISSN:	2162-237X, 2162-2388, 2162-2388
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	As an interesting and emerging topic, cosaliency detection aims at simultaneously extracting common salient objects in multiple related images. It differs from the conventional saliency detection paradigm in which saliency detection for each image is determined one by one independently without taking advantage of the homogeneity in the data pool of multiple related images. In this paper, we propose a novel cosaliency detection approach using deep learning models. Two new concepts, called intrasaliency prior transfer and deep intersaliency mining, are introduced and explored in the proposed work. For the intrasaliency prior transfer, we build a stacked denoising autoencoder (SDAE) to learn the saliency prior knowledge from auxiliary annotated data sets and then transfer the learned knowledge to estimate the intrasaliency for each image in cosaliency data sets. For the deep intersaliency mining, we formulate it by using the deep reconstruction residual obtained in the highest hidden layer of a self-trained SDAE. The obtained deep intersaliency can extract more intrinsic and general hidden patterns to discover the homogeneity of cosalient objects in terms of some higher level concepts. Finally, the cosaliency maps are generated by weighted integration of the proposed intrasaliency prior, deep intersaliency, and traditional shallow intersaliency. Comprehensive experiments over diverse publicly available benchmark data sets demonstrate consistent performance gains of the proposed method over the state-of-the-art cosaliency detection methods.
AbstractList	As an interesting and emerging topic, cosaliency detection aims at simultaneously extracting common salient objects in multiple related images. It differs from the conventional saliency detection paradigm in which saliency detection for each image is determined one by one independently without taking advantage of the homogeneity in the data pool of multiple related images. In this paper, we propose a novel cosaliency detection approach using deep learning models. Two new concepts, called intrasaliency prior transfer and deep intersaliency mining, are introduced and explored in the proposed work. For the intrasaliency prior transfer, we build a stacked denoising autoencoder (SDAE) to learn the saliency prior knowledge from auxiliary annotated data sets and then transfer the learned knowledge to estimate the intrasaliency for each image in cosaliency data sets. For the deep intersaliency mining, we formulate it by using the deep reconstruction residual obtained in the highest hidden layer of a self-trained SDAE. The obtained deep intersaliency can extract more intrinsic and general hidden patterns to discover the homogeneity of cosalient objects in terms of some higher level concepts. Finally, the cosaliency maps are generated by weighted integration of the proposed intrasaliency prior, deep intersaliency, and traditional shallow intersaliency. Comprehensive experiments over diverse publicly available benchmark data sets demonstrate consistent performance gains of the proposed method over the state-of-the-art cosaliency detection methods. As an interesting and emerging topic, cosaliency detection aims at simultaneously extracting common salient objects in multiple related images. It differs from the conventional saliency detection paradigm in which saliency detection for each image is determined one by one independently without taking advantage of the homogeneity in the data pool of multiple related images. In this paper, we propose a novel cosaliency detection approach using deep learning models. Two new concepts, called intrasaliency prior transfer and deep intersaliency mining, are introduced and explored in the proposed work. For the intrasaliency prior transfer, we build a stacked denoising autoencoder (SDAE) to learn the saliency prior knowledge from auxiliary annotated data sets and then transfer the learned knowledge to estimate the intrasaliency for each image in cosaliency data sets. For the deep intersaliency mining, we formulate it by using the deep reconstruction residual obtained in the highest hidden layer of a self-trained SDAE. The obtained deep intersaliency can extract more intrinsic and general hidden patterns to discover the homogeneity of cosalient objects in terms of some higher level concepts. Finally, the cosaliency maps are generated by weighted integration of the proposed intrasaliency prior, deep intersaliency, and traditional shallow intersaliency. Comprehensive experiments over diverse publicly available benchmark data sets demonstrate consistent performance gains of the proposed method over the state-of-the-art cosaliency detection methods.As an interesting and emerging topic, cosaliency detection aims at simultaneously extracting common salient objects in multiple related images. It differs from the conventional saliency detection paradigm in which saliency detection for each image is determined one by one independently without taking advantage of the homogeneity in the data pool of multiple related images. In this paper, we propose a novel cosaliency detection approach using deep learning models. Two new concepts, called intrasaliency prior transfer and deep intersaliency mining, are introduced and explored in the proposed work. For the intrasaliency prior transfer, we build a stacked denoising autoencoder (SDAE) to learn the saliency prior knowledge from auxiliary annotated data sets and then transfer the learned knowledge to estimate the intrasaliency for each image in cosaliency data sets. For the deep intersaliency mining, we formulate it by using the deep reconstruction residual obtained in the highest hidden layer of a self-trained SDAE. The obtained deep intersaliency can extract more intrinsic and general hidden patterns to discover the homogeneity of cosalient objects in terms of some higher level concepts. Finally, the cosaliency maps are generated by weighted integration of the proposed intrasaliency prior, deep intersaliency, and traditional shallow intersaliency. Comprehensive experiments over diverse publicly available benchmark data sets demonstrate consistent performance gains of the proposed method over the state-of-the-art cosaliency detection methods.
Author	Zhang, Dingwen Han, Jungong Shao, Ling Han, Junwei
Author_xml	– sequence: 1 givenname: Dingwen surname: Zhang fullname: Zhang, Dingwen email: zhangdingwen2006yyy@gmail.com organization: School of Automation, Northwestern Polytechnical University, Xi'an, China – sequence: 2 givenname: Junwei surname: Han fullname: Han, Junwei email: junweihan2010@gmail.com organization: School of Automation, Northwestern Polytechnical University, Xi'an, China – sequence: 3 givenname: Jungong surname: Han fullname: Han, Jungong email: jungong.han@northumbria.ac.uk organization: Department of Computer Science and Digital Technologies, Northumbria University, Newcastle upon Tyne, U.K – sequence: 4 givenname: Ling surname: Shao fullname: Shao, Ling email: ling.shao@ieee.org organization: Department of Computer Science and Digital Technologies, Northumbria University, Newcastle upon Tyne, U.K
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/26571541$$D View this record in MEDLINE/PubMed
BookMark	eNqFkb1OwzAURi1URAv0BUBCGVlSfO3ESUYof5VKQaJI3SLXuUZGqVPsdOjbk9CSgQG8-A7nXFvfd0x6trJIyBnQEQDNruaz2fR1xCjEIxZlMQg4IAMGgoWMp2mvm5NFnwy9_6DNETQWUXZE-kzECcQRDMhiXHlZGrRqG9xijao2lQ1upMciaIaJrZ3sgBdnKhfMnbReowukLRoH1y2FrqOejDX2_ZQcall6HO7vE_J2fzcfP4bT54fJ-HoaqkiIOtSR0jorlJaouRQKls3vaYZMaxZRFjNgSiFwCRHGQFGAKJArxWXCJSrOT8jlbu_aVZ8b9HW-Ml5hWUqL1cbnkIKgIo0z9j-aZMBZClG79WKPbpYrLPK1MyvptvlPcA3AdoBylfcOdYcAzduC8u-C8ragfF9QI6W_JGVq2SbepGzKv9XznWoQsXsr4SxpEuJfvlad4Q
CODEN	ITNNAL
CitedBy_id	crossref_primary_10_1016_j_cviu_2022_103611 crossref_primary_10_1142_S0218001424500149 crossref_primary_10_1109_TCSVT_2017_2701279 crossref_primary_10_1109_TCSVT_2018_2823769 crossref_primary_10_1109_TIP_2017_2769454 crossref_primary_10_1109_TIP_2017_2658957 crossref_primary_10_1109_TIP_2017_2738839 crossref_primary_10_1109_TIP_2019_2909649 crossref_primary_10_1109_TMM_2022_3167805 crossref_primary_10_1109_MGRS_2018_2853555 crossref_primary_10_1109_ACCESS_2017_2776344 crossref_primary_10_1007_s11042_017_4563_7 crossref_primary_10_1016_j_neucom_2017_09_031 crossref_primary_10_1016_j_neucom_2017_11_003 crossref_primary_10_1016_j_neucom_2017_07_021 crossref_primary_10_1109_ACCESS_2017_2764503 crossref_primary_10_1109_TNNLS_2019_2920374 crossref_primary_10_1109_TIP_2021_3087401 crossref_primary_10_1007_s00138_023_01462_7 crossref_primary_10_1016_j_jvcir_2017_12_002 crossref_primary_10_1016_j_neucom_2017_03_016 crossref_primary_10_1109_TIP_2017_2760512 crossref_primary_10_1109_TNNLS_2019_2901273 crossref_primary_10_1109_TCSVT_2017_2724940 crossref_primary_10_1016_j_displa_2024_102767 crossref_primary_10_1016_j_neucom_2017_09_028 crossref_primary_10_1007_s11042_018_6009_2 crossref_primary_10_1007_s11042_017_5182_z crossref_primary_10_1007_s11042_018_6026_1 crossref_primary_10_1109_TMM_2021_3138246 crossref_primary_10_1007_s10489_021_02307_4 crossref_primary_10_1109_TIP_2017_2754941 crossref_primary_10_1145_3158674 crossref_primary_10_1109_TIP_2017_2695887 crossref_primary_10_1109_TMM_2016_2638207 crossref_primary_10_1007_s11063_017_9755_7 crossref_primary_10_1016_j_image_2016_06_002 crossref_primary_10_1007_s10772_021_09842_y crossref_primary_10_1109_TIP_2017_2733200 crossref_primary_10_1007_s11042_022_13148_9 crossref_primary_10_1016_j_neucom_2018_07_079 crossref_primary_10_1145_3313874 crossref_primary_10_1109_TIP_2018_2843680 crossref_primary_10_1016_j_knosys_2022_109356 crossref_primary_10_1109_TIP_2017_2722691 crossref_primary_10_1007_s11042_020_08678_z crossref_primary_10_1109_TPAMI_2017_2662005 crossref_primary_10_1007_s11042_017_4748_0 crossref_primary_10_1007_s11042_017_5125_8 crossref_primary_10_1016_j_imavis_2025_105623 crossref_primary_10_1016_j_patcog_2017_10_008 crossref_primary_10_1002_cpe_4273 crossref_primary_10_1016_j_neucom_2018_02_004 crossref_primary_10_1109_ACCESS_2019_2956508 crossref_primary_10_1109_TIP_2017_2745204 crossref_primary_10_1109_TITS_2017_2740303 crossref_primary_10_1016_j_patcog_2018_11_003 crossref_primary_10_1007_s00530_018_0585_x crossref_primary_10_1109_TIP_2017_2699623 crossref_primary_10_1109_TIP_2017_2696747 crossref_primary_10_1109_TNNLS_2020_2967471 crossref_primary_10_1016_j_ijleo_2017_03_029 crossref_primary_10_1109_TCSVT_2017_2723302 crossref_primary_10_1007_s11042_017_5087_x crossref_primary_10_1109_TCSVT_2022_3150923 crossref_primary_10_3390_rs10081229 crossref_primary_10_1109_TMM_2020_2972165 crossref_primary_10_1016_j_ins_2017_01_019 crossref_primary_10_1007_s00371_025_04155_6 crossref_primary_10_1109_TPAMI_2021_3060412 crossref_primary_10_1155_2021_8956396 crossref_primary_10_1007_s11704_016_6066_5 crossref_primary_10_1109_TII_2019_2934144 crossref_primary_10_1007_s00371_021_02231_1 crossref_primary_10_1109_ACCESS_2017_2756081 crossref_primary_10_1109_TNNLS_2017_2731999 crossref_primary_10_1109_TIP_2017_2755766 crossref_primary_10_1109_TNNLS_2017_2691545 crossref_primary_10_1109_TIP_2017_2781424 crossref_primary_10_1109_TITS_2017_2766093 crossref_primary_10_1109_TMM_2019_2936803 crossref_primary_10_1109_TIP_2018_2859752 crossref_primary_10_1016_j_neucom_2017_09_064 crossref_primary_10_1109_TMM_2021_3054526 crossref_primary_10_1016_j_neucom_2016_11_064 crossref_primary_10_1007_s00521_019_04265_y crossref_primary_10_1109_LSP_2021_3049997 crossref_primary_10_1109_JPROC_2017_2675998 crossref_primary_10_1109_TCSVT_2017_2706264 crossref_primary_10_1109_TMM_2017_2769801 crossref_primary_10_1109_TIP_2018_2861217 crossref_primary_10_1109_TCSVT_2018_2804438 crossref_primary_10_1109_TCSVT_2020_2992054 crossref_primary_10_1109_TPAMI_2023_3336015 crossref_primary_10_1109_ACCESS_2018_2885507 crossref_primary_10_1109_ACCESS_2019_2943899 crossref_primary_10_1049_iet_cvi_2018_5591 crossref_primary_10_3390_s19061354 crossref_primary_10_1016_j_neucom_2017_03_020 crossref_primary_10_1109_TMM_2022_3198848 crossref_primary_10_1109_TCSVT_2017_2710120 crossref_primary_10_1109_TCYB_2017_2761361 crossref_primary_10_1109_TNNLS_2018_2890310 crossref_primary_10_1145_3661312 crossref_primary_10_1016_j_neucom_2017_10_052 crossref_primary_10_1007_s13042_022_01531_9 crossref_primary_10_1016_j_neucom_2017_04_066 crossref_primary_10_1016_j_neucom_2017_10_057 crossref_primary_10_1109_TMM_2020_3021251 crossref_primary_10_1007_s00371_020_01842_4 crossref_primary_10_1109_LSP_2017_2688136 crossref_primary_10_1049_cit2_12020 crossref_primary_10_1109_TIP_2017_2694224 crossref_primary_10_1007_s00530_020_00650_z crossref_primary_10_1007_s11042_017_4550_z crossref_primary_10_1016_j_cviu_2017_04_015 crossref_primary_10_1007_s11042_025_20888_x crossref_primary_10_1109_TIP_2016_2639440 crossref_primary_10_1007_s11042_018_5856_1 crossref_primary_10_1016_j_isprsjprs_2018_09_014
Cites_doi	10.1109/CVPR.2009.5206596 10.1109/TNNLS.2014.2330900 10.1109/CVPR.2011.5995415 10.1109/CVPR.2013.412 10.1109/TCSVT.2005.859028 10.1109/ICASSP.2013.6638027 10.1145/1866029.1866066 10.1109/TMM.2013.2271476 10.1109/TCYB.2014.2358647 10.1007/978-3-642-35289-8_26 10.1109/TPAMI.2012.28 10.1109/TIP.2011.2156803 10.1007/978-3-642-42051-1_31 10.1109/TPAMI.2013.50 10.1109/CVPR.2013.153 10.1007/s11263-012-0538-3 10.1109/LGRS.2014.2358994 10.1109/TPAMI.2012.277 10.1016/j.isprsjprs.2013.12.011 10.1109/CVPR.2012.6247721 10.1007/978-3-319-10578-9_23 10.1109/TPAMI.2014.2345401 10.1109/TGRS.2014.2374218 10.1109/CVPR.2013.407 10.1109/CVPR.2010.5540080 10.1109/CVPR.2011.5995420 10.1109/CVPR.2014.81 10.1109/LSP.2013.2292873 10.1109/TPAMI.2011.158 10.1109/TCSVT.2014.2381471 10.1109/TIP.2014.2332399 10.1109/CVPR.2007.382973 10.1109/CVPR.2013.271 10.1109/TPAMI.2012.120 10.1109/TCSVT.2013.2242594 10.1007/s00138-013-0558-1 10.1109/TMM.2011.2162399 10.1109/BTAS.2014.6996300 10.1023/B:VISI.0000022288.19776.77 10.5244/C.26.78 10.1109/ICIP.2010.5650014 10.1109/TIP.2013.2260166
ContentType	Journal Article
DBID	97E RIA RIE AAYXX CITATION NPM 7X8 7SC 7SP 8FD F28 FR3 JQ2 L7M L~C L~D
DOI	10.1109/TNNLS.2015.2495161
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef PubMed MEDLINE - Academic Computer and Information Systems Abstracts Electronics & Communications Abstracts Technology Research Database ANTE: Abstracts in New Technology & Engineering Engineering Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional
DatabaseTitle	CrossRef PubMed MEDLINE - Academic Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Engineering Research Database Advanced Technologies Database with Aerospace ANTE: Abstracts in New Technology & Engineering Computer and Information Systems Abstracts Professional
DatabaseTitleList	Technology Research Database PubMed MEDLINE - Academic
Database_xml	– sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher – sequence: 3 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Computer Science
EISSN	2162-2388
EndPage	1176
ExternalDocumentID	26571541 10_1109_TNNLS_2015_2495161 7327212
Genre	orig-research Journal Article
GrantInformation_xml	– fundername: National Natural Science Foundation of China; National Science Foundation of China grantid: 61473231; 61522207 funderid: 10.13039/501100001809 – fundername: Doctorate Foundation through Northwestern Polytechnical University
GroupedDBID	0R~ 4.4 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACIWK ACPRK AENEX AFRAH AGQYO AGSQL AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS EJD IFIPE IPLJI JAVBF M43 MS~ O9- OCL PQQKQ RIA RIE RNS AAYXX CITATION NPM RIG 7X8 7SC 7SP 8FD F28 FR3 JQ2 L7M L~C L~D
ID	FETCH-LOGICAL-c466t-f4cff9dcfaef3a6c1b38809e2ff24025212cce13a14e510e616de3cc3a73aec33
IEDL.DBID	RIE
ISICitedReferencesCount	153
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000377113300005&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	2162-237X 2162-2388
IngestDate	Sun Sep 28 11:53:35 EDT 2025 Sat Sep 27 19:05:48 EDT 2025 Mon Jul 21 05:48:08 EDT 2025 Sat Nov 29 01:39:53 EST 2025 Tue Nov 18 22:27:46 EST 2025 Wed Aug 27 08:30:57 EDT 2025
IsDoiOpenAccess	false
IsOpenAccess	true
IsPeerReviewed	false
IsScholarly	true
Issue	6
Keywords	stacked denoising autoencoder (SDAE) deep learning Cosaliency detection prior transfer
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c466t-f4cff9dcfaef3a6c1b38809e2ff24025212cce13a14e510e616de3cc3a73aec33
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
OpenAccessLink	https://ueaeprints.uea.ac.uk/id/eprint/62880/1/Accepted_manuscript.pdf
PMID	26571541
PQID	1791328143
PQPubID	23479
PageCount	14
ParticipantIDs	proquest_miscellaneous_1816068592 crossref_primary_10_1109_TNNLS_2015_2495161 crossref_citationtrail_10_1109_TNNLS_2015_2495161 pubmed_primary_26571541 proquest_miscellaneous_1791328143 ieee_primary_7327212
PublicationCentury	2000
PublicationDate	2016-June 2016-6-00 2016-06-00 20160601
PublicationDateYYYYMMDD	2016-06-01
PublicationDate_xml	– month: 06 year: 2016 text: 2016-June
PublicationDecade	2010
PublicationPlace	United States
PublicationPlace_xml	– name: United States
PublicationTitle	IEEE transaction on neural networks and learning systems
PublicationTitleAbbrev	TNNLS
PublicationTitleAlternate	IEEE Trans Neural Netw Learn Syst
PublicationYear	2016
Publisher	IEEE
Publisher_xml	– name: IEEE
References	ref13 kim (ref5) 2011 ref12 ref15 lin (ref42) 2014 ref14 ref53 ref52 ref11 bengio (ref22) 2011 ref10 zhang (ref49) 2015 ref17 ref16 han (ref47) 0 ref18 rumelhart (ref30) 1988 ref51 ref50 ref46 ref45 ref41 ref44 ref43 bengio (ref25) 2011 ref8 ref9 ref4 ref3 ref6 fu (ref7) 2013 ref40 ref35 ref34 ref37 ref36 ref31 ref32 ref2 ref1 ref39 ref38 shen (ref33) 2012 ref24 ref23 ref26 ref20 cao (ref19) 2013 ref21 ref28 ref27 vincent (ref29) 2010; 11 han (ref48) 2015; 25
References_xml	– ident: ref35 doi: 10.1109/CVPR.2009.5206596 – ident: ref24 doi: 10.1109/TNNLS.2014.2330900 – ident: ref13 doi: 10.1109/CVPR.2011.5995415 – ident: ref9 doi: 10.1109/CVPR.2013.412 – start-page: 853 year: 2012 ident: ref33 article-title: A unified approach to salient object detection via low rank matrix recovery publication-title: Proc IEEE Conf Comput Vis Pattern Recognit – ident: ref1 doi: 10.1109/TCSVT.2005.859028 – ident: ref18 doi: 10.1109/ICASSP.2013.6638027 – ident: ref16 doi: 10.1145/1866029.1866066 – ident: ref11 doi: 10.1109/TMM.2013.2271476 – ident: ref53 doi: 10.1109/TCYB.2014.2358647 – ident: ref45 doi: 10.1007/978-3-642-35289-8_26 – ident: ref40 doi: 10.1109/TPAMI.2012.28 – ident: ref12 doi: 10.1109/TIP.2011.2156803 – ident: ref43 doi: 10.1007/978-3-642-42051-1_31 – ident: ref26 doi: 10.1109/TPAMI.2013.50 – ident: ref32 doi: 10.1109/CVPR.2013.153 – start-page: 1 year: 2013 ident: ref19 article-title: Saliency map fusion based on rank-one constraint publication-title: Proc IEEE Int Conf Multimedia Expo – start-page: 169 year: 2011 ident: ref5 article-title: Distributed cosegmentation via submodular optimization on anisotropic diffusion publication-title: Proc IEEE Int Conf Comput Vis – ident: ref21 doi: 10.1007/s11263-012-0538-3 – ident: ref51 doi: 10.1109/LGRS.2014.2358994 – ident: ref41 doi: 10.1109/TPAMI.2012.277 – year: 0 ident: ref47 article-title: Two-stage learning to predict human eye fixations via stacked denoising autoencoders publication-title: IEEE Trans Cybern – ident: ref52 doi: 10.1016/j.isprsjprs.2013.12.011 – ident: ref39 doi: 10.1109/CVPR.2012.6247721 – ident: ref27 doi: 10.1007/978-3-319-10578-9_23 – ident: ref3 doi: 10.1109/TPAMI.2014.2345401 – ident: ref50 doi: 10.1109/TGRS.2014.2374218 – ident: ref34 doi: 10.1109/CVPR.2013.407 – ident: ref4 doi: 10.1109/CVPR.2010.5540080 – ident: ref6 doi: 10.1109/CVPR.2011.5995420 – start-page: 17 year: 2011 ident: ref22 article-title: Deep learning of representations for unsupervised and transfer learning publication-title: Proceedings of the Unsupervised and Transfer Learning Challenge and Workshop – ident: ref23 doi: 10.1109/CVPR.2014.81 – ident: ref15 doi: 10.1109/LSP.2013.2292873 – ident: ref38 doi: 10.1109/TPAMI.2011.158 – volume: 25 start-page: 1309 year: 2015 ident: ref48 article-title: Background prior-based salient object detection via deep reconstruction residual publication-title: IEEE Trans Circuits Syst Video Technol doi: 10.1109/TCSVT.2014.2381471 – year: 1988 ident: ref30 publication-title: Learning Representations by Back-propagating Errors – ident: ref28 doi: 10.1109/TIP.2014.2332399 – ident: ref10 doi: 10.1109/CVPR.2007.382973 – year: 2014 ident: ref42 article-title: Saliency detection within a deep convolutional architecture publication-title: Proc AAAI Conf Artif Intell – ident: ref46 doi: 10.1109/CVPR.2013.271 – start-page: 164 year: 2011 ident: ref25 article-title: Deep learners benefit more from out-of-distribution examples publication-title: Proc Int Conf Artif Intell Statist – ident: ref36 doi: 10.1109/TPAMI.2012.120 – start-page: 3166 year: 2013 ident: ref7 article-title: Object-based multiple foreground video co-segmentation publication-title: Proc IEEE Conf Comput Vis Pattern Recognit – ident: ref31 doi: 10.1109/TCSVT.2013.2242594 – ident: ref2 doi: 10.1007/s00138-013-0558-1 – ident: ref8 doi: 10.1109/TMM.2011.2162399 – volume: 11 start-page: 3371 year: 2010 ident: ref29 article-title: Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion publication-title: J Mach Learn Res – ident: ref44 doi: 10.1109/BTAS.2014.6996300 – ident: ref37 doi: 10.1023/B:VISI.0000022288.19776.77 – start-page: 2994 year: 2015 ident: ref49 article-title: Co-saliency detection via looking deep and wide publication-title: Proc IEEE Conf Comput Vis Pattern Recognit – ident: ref20 doi: 10.5244/C.26.78 – ident: ref17 doi: 10.1109/ICIP.2010.5650014 – ident: ref14 doi: 10.1109/TIP.2013.2260166
SSID	ssj0000605649
Score	2.5537002
Snippet	As an interesting and emerging topic, cosaliency detection aims at simultaneously extracting common salient objects in multiple related images. It differs from...
SourceID	proquest pubmed crossref ieee
SourceType	Aggregation Database Index Database Enrichment Source Publisher
StartPage	1163
SubjectTerms	Construction Cosaliency detection Data mining deep learning Encoding Feature extraction Homogeneity Image detection Learning Machine learning Mining Neural networks Object recognition prior transfer Robustness stacked denoising autoencoder (SDAE) Training Visualization
Title	Cosaliency Detection Based on Intrasaliency Prior Transfer and Deep Intersaliency Mining
URI	https://ieeexplore.ieee.org/document/7327212 https://www.ncbi.nlm.nih.gov/pubmed/26571541 https://www.proquest.com/docview/1791328143 https://www.proquest.com/docview/1816068592
Volume	27
WOSCitedRecordID	wos000377113300005&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 2162-2388 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000605649 issn: 2162-237X databaseCode: RIE dateStart: 20120101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1JS8UwEA4qHry4L8_lUcGbVpumL2mPbg8FfQgq9FbykgkI0spb_P3OpAsIKnjLYbKQmWS-mWRmGDuRSWQp70nIE0ADxcYm1HLMQ5twJRPObWYiX2xCjUZpnmdPC-ysi4UBAP_5DM6p6d_ybWXm5Cq7UCJGgwUv3EWlVB2r1flTIsTl0qPdmMs4jIXK2xiZKLt4GY0enukj1-Ccii0jzKEswHKgEEHwbyrJ11j5HW56tTNc-9-C19lqAy-Dy1oeNtgClJtsrS3dEDQneYvl19UUETjFXQY3MPP_scrgClWaDbBxTy7fjuBp8lZNAq_VHA6iS4t94CPw3sSO6tGXmthmr8Pbl-u7sCmyEJpEylnoEuNcZo3T4ISWho8pPUwGsXP08EKhvcYAFxqZiecXJJcWhDFCK6HBCLHDlsqqhD0WcKPHMR5qrREzcLIEE1DKgHVA98S4x3i7z4VpMpBTIYz3wlsiUVZ4NhXEpqJhU4-ddn0-6vwbf1JvERM6ymb_e-y4ZWeBp4eeRHQJ1XxaUHJWEacIGv-gSTlaeekgw3F2a1noJmhFaP_niQ_YCi5P1l_LDtnSbDKHI7ZsPmdv00kfxThP-16MvwAKjeua
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1ZSxxBEC5EA_ElJjExqzkmkLdkdPrYnp3HxESUrIOQDezb0NtdDYLMyB7-fqt6DhASwbd-qD7o6u76qroOgC9GZ57znqRCIykoXrrUmoVIvRa50UL4wmWx2ERelpP5vLjagm9DLAwiRuczPOZm_Mv3jduwqewkV5IUFnpwd8ZaS9FGaw0WlYyQuYl4VwojU6nyeR8lkxUns7Kc_mFXrvExl1smoMN5gM04JwwhHgilWGXl_4AzCp6zvact-SW86ABm8r09Ea9gC-vXsNcXb0i6u7wP89NmRRicIy-Tn7iOHll18oOEmk-occFG34HganndLJMo1wINYmtPffA2ifbEgeoyFpt4A3_Pfs1Oz9OuzELqtDHrNGgXQuFdsBiUNU4sOEFMgTIE_nrh4F7nUChL7KQbjEYYj8o5ZXNl0Sn1FrbrpsZ3kAhnF5KutbWEGgTrghrz3KEPyC_FYgSi3-fKdTnIuRTGTRV1kayoIpsqZlPVsWkEX4c-t20Gjkep95kJA2W3_yP43LOzovvDnyK2xmazqjg9q5ITgo2P0EwE6XmTcUHjHLRnYZigP0KH_574Ezw_n11Oq-lF-fsIdmmppnU0ew_b6-UGP8Azd7e-Xi0_xsN8D-Ip7fk
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Cosaliency+Detection+Based+on+Intrasaliency+Prior+Transfer+and+Deep+Intersaliency+Mining&rft.jtitle=IEEE+transaction+on+neural+networks+and+learning+systems&rft.au=Zhang%2C+Dingwen&rft.au=Han%2C+Junwei&rft.au=Han%2C+Jungong&rft.au=Shao%2C+Ling&rft.date=2016-06-01&rft.pub=IEEE&rft.issn=2162-237X&rft.volume=27&rft.issue=6&rft.spage=1163&rft.epage=1176&rft_id=info:doi/10.1109%2FTNNLS.2015.2495161&rft_id=info%3Apmid%2F26571541&rft.externalDocID=7327212
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2162-237X&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2162-237X&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2162-237X&client=summon