Collaborative Content-Dependent Modeling: A Return to the Roots of Salient Object Detection

Salient object detection (SOD) aims to identify the most visually distinctive object(s) from each given image. Most recent progresses focus on either adding elaborative connections among different convolution blocks or introducing boundary-aware supervision to help achieve better segmentation, which...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	IEEE transactions on image processing Ročník 32; s. 4237 - 4246
Hlavní autori:	Jiao, Siyu, Goel, Vidit, Navasardyan, Shant, Yang, Zongxin, Khachatryan, Levon, Yang, Yi, Wei, Yunchao, Zhao, Yao, Shi, Humphrey
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	United States IEEE 2023 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:	Coders Collaboration content-dependent modeling Context Convolution Decoding Encoders-Decoders Feature extraction Head Image segmentation Modules Object detection Object recognition Roots Salience Salient object detection Task analysis Transformers
ISSN:	1057-7149, 1941-0042, 1941-0042
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Abstract	Salient object detection (SOD) aims to identify the most visually distinctive object(s) from each given image. Most recent progresses focus on either adding elaborative connections among different convolution blocks or introducing boundary-aware supervision to help achieve better segmentation, which is actually moving away from the essence of SOD, i.e., distinctiveness/salience. This paper goes back to the roots of SOD and investigates the principles of how to identify distinctive object(s) in a more effective and efficient way. Intuitively, the salience of one object should largely depend on its global context within the input image. Based on this, we devise a clean yet effective architecture for SOD, named Collaborative Content-Dependent Networks (CCD-Net). In detail, we propose a collaborative content-dependent head whose parameters are conditioned on the input image's global context information. Within the content-dependent head, a hand-crafted multi-scale (HMS) module and a self-induced (SI) module are carefully designed to collaboratively generate content-aware convolution kernels for prediction. Benefited from the content-dependent head, CCD-Net is capable of leveraging global context to detect distinctive object(s) while keeping a simple encoder-decoder design. Extensive experimental results demonstrate that our CCD-Net achieves state-of-the-art results on various benchmarks. Our architecture is simple and intuitive compared to previous solutions, resulting in competitive characteristics with respect to model complexity, operating efficiency, and segmentation accuracy.
AbstractList	Salient object detection (SOD) aims to identify the most visually distinctive object(s) from each given image. Most recent progresses focus on either adding elaborative connections among different convolution blocks or introducing boundary-aware supervision to help achieve better segmentation, which is actually moving away from the essence of SOD, i.e., distinctiveness/salience. This paper goes back to the roots of SOD and investigates the principles of how to identify distinctive object(s) in a more effective and efficient way. Intuitively, the salience of one object should largely depend on its global context within the input image. Based on this, we devise a clean yet effective architecture for SOD, named Collaborative Content-Dependent Networks (CCD-Net). In detail, we propose a collaborative content-dependent head whose parameters are conditioned on the input image's global context information. Within the content-dependent head, a hand-crafted multi-scale (HMS) module and a self-induced (SI) module are carefully designed to collaboratively generate content-aware convolution kernels for prediction. Benefited from the content-dependent head, CCD-Net is capable of leveraging global context to detect distinctive object(s) while keeping a simple encoder-decoder design. Extensive experimental results demonstrate that our CCD-Net achieves state-of-the-art results on various benchmarks. Our architecture is simple and intuitive compared to previous solutions, resulting in competitive characteristics with respect to model complexity, operating efficiency, and segmentation accuracy. Salient object detection (SOD) aims to identify the most visually distinctive object(s) from each given image. Most recent progresses focus on either adding elaborative connections among different convolution blocks or introducing boundary-aware supervision to help achieve better segmentation, which is actually moving away from the essence of SOD, i.e., distinctiveness/salience. This paper goes back to the roots of SOD and investigates the principles of how to identify distinctive object(s) in a more effective and efficient way. Intuitively, the salience of one object should largely depend on its global context within the input image. Based on this, we devise a clean yet effective architecture for SOD, named Collaborative Content-Dependent Networks (CCD-Net). In detail, we propose a collaborative content-dependent head whose parameters are conditioned on the input image's global context information. Within the content-dependent head, a hand-crafted multi-scale (HMS) module and a self-induced (SI) module are carefully designed to collaboratively generate content-aware convolution kernels for prediction. Benefited from the content-dependent head, CCD-Net is capable of leveraging global context to detect distinctive object(s) while keeping a simple encoder-decoder design. Extensive experimental results demonstrate that our CCD-Net achieves state-of-the-art results on various benchmarks. Our architecture is simple and intuitive compared to previous solutions, resulting in competitive characteristics with respect to model complexity, operating efficiency, and segmentation accuracy.Salient object detection (SOD) aims to identify the most visually distinctive object(s) from each given image. Most recent progresses focus on either adding elaborative connections among different convolution blocks or introducing boundary-aware supervision to help achieve better segmentation, which is actually moving away from the essence of SOD, i.e., distinctiveness/salience. This paper goes back to the roots of SOD and investigates the principles of how to identify distinctive object(s) in a more effective and efficient way. Intuitively, the salience of one object should largely depend on its global context within the input image. Based on this, we devise a clean yet effective architecture for SOD, named Collaborative Content-Dependent Networks (CCD-Net). In detail, we propose a collaborative content-dependent head whose parameters are conditioned on the input image's global context information. Within the content-dependent head, a hand-crafted multi-scale (HMS) module and a self-induced (SI) module are carefully designed to collaboratively generate content-aware convolution kernels for prediction. Benefited from the content-dependent head, CCD-Net is capable of leveraging global context to detect distinctive object(s) while keeping a simple encoder-decoder design. Extensive experimental results demonstrate that our CCD-Net achieves state-of-the-art results on various benchmarks. Our architecture is simple and intuitive compared to previous solutions, resulting in competitive characteristics with respect to model complexity, operating efficiency, and segmentation accuracy.
Author	Jiao, Siyu Wei, Yunchao Goel, Vidit Yang, Zongxin Navasardyan, Shant Zhao, Yao Shi, Humphrey Khachatryan, Levon Yang, Yi
Author_xml	– sequence: 1 givenname: Siyu orcidid: 0000-0002-0795-8401 surname: Jiao fullname: Jiao, Siyu email: jiaosiyu@bjtu.edu.cn organization: Beijing Key Laboratory of Advanced Information Science and Network and the Institute of Information Science, Beijing Jiaotong University, Beijing, China – sequence: 2 givenname: Vidit orcidid: 0000-0001-8483-6363 surname: Goel fullname: Goel, Vidit email: vidit.goel@picsart.com organization: Picsart AI Research (PAIR), Atlanta, GA, USA – sequence: 3 givenname: Shant surname: Navasardyan fullname: Navasardyan, Shant email: shant.navasardyan@picsart.com organization: PAIR, Yerevan, Armenia – sequence: 4 givenname: Zongxin surname: Yang fullname: Yang, Zongxin email: zongxinyang1996@gmail.com organization: College of Computer Science and Technology, Zhejiang University, Zhejiang, China – sequence: 5 givenname: Levon orcidid: 0000-0002-5840-760X surname: Khachatryan fullname: Khachatryan, Levon email: levon.khachatryan@picsart.com organization: PAIR, Yerevan, Armenia – sequence: 6 givenname: Yi orcidid: 0000-0002-0512-880X surname: Yang fullname: Yang, Yi email: yee.i.yang@gmail.com organization: College of Computer Science and Technology, Zhejiang University, Zhejiang, China – sequence: 7 givenname: Yunchao orcidid: 0000-0002-2812-8781 surname: Wei fullname: Wei, Yunchao email: yunchao.wei@bjtu.edu.cn organization: Beijing Key Laboratory of Advanced Information Science and Network and the Institute of Information Science, Beijing Jiaotong University, Beijing, China – sequence: 8 givenname: Yao orcidid: 0000-0002-8581-9554 surname: Zhao fullname: Zhao, Yao email: yzhao@bjtu.edu.cn organization: Beijing Key Laboratory of Advanced Information Science and Network and the Institute of Information Science, Beijing Jiaotong University, Beijing, China – sequence: 9 givenname: Humphrey orcidid: 0000-0002-2922-5663 surname: Shi fullname: Shi, Humphrey email: humphrey.shi@picsart.com organization: Picsart AI Research (PAIR), Atlanta, GA, USA
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/37440395$$D View this record in MEDLINE/PubMed
BookMark	eNp9kb1vFDEQxS0URD6gp0DIEg3NHmOPd23TRRcSIgUFhVBRrLy7s-DTnn1Z-5D47_HpDoRSUM0Uvzczb94pOwoxEGMvBSyEAPvu_vrzQoLEBUqLurZP2ImwSlQASh6VHmpdaaHsMTtNaQUgVC2aZ-wYtVKAtj5h35ZxmlwXZ5f9T-LLGDKFXF3QhsJQOv4pDjT58P09P-d3lLdz4Dny_IP4XYw58TjyL27yO_S2W1Gf-QXlUnwMz9nT0U2JXhzqGft6-eF--bG6ub26Xp7fVD0qkytVGzfaoTFgrBuh69AItAAgyfTaNqrT1hgxDCTNiE70WqPsBuMskSYc8Iy93c_dzPFhSym3a596Kr4CxW1qpUEj6xpkU9A3j9BVLJbKdYVSKJRsFBbq9YHadmsa2s3s127-1f55WwFgD_RzTGmm8S8ioN0l05Zk2l0y7SGZImkeSXqf3e5NeXZ--p_w1V7oieifPaK4whp_A4ytmOw
CODEN	IIPRE4
CitedBy_id	crossref_primary_10_1109_TSMC_2025_3572123 crossref_primary_10_1016_j_displa_2024_102855 crossref_primary_10_1007_s11042_024_19876_4 crossref_primary_10_1109_TITS_2023_3342811 crossref_primary_10_1109_TIM_2025_3574913
Cites_doi	10.1609/aaai.v35i3.16331 10.1109/ICCV48922.2021.00413 10.1007/978-3-030-58536-5_3 10.1007/978-3-642-33712-3_3 10.1109/TNNLS.2023.3243246 10.1109/ICCV.2019.00887 10.1109/TIP.2022.3164550 10.1109/TIP.2021.3072811 10.1109/CVPR.2019.00403 10.1109/CVPR.2015.7298731 10.1109/CVPR.2019.00766 10.1109/TPAMI.2021.3051099 10.1109/CVPR42600.2020.00943 10.1109/CVPR.2017.404 10.24963/ijcai.2018/95 10.1109/CVPR.2016.90 10.1609/aaai.v34i07.6633 10.1109/ICCV48922.2021.01196 10.1109/CVPR.2018.00187 10.1109/ICRA.2013.6630857 10.1109/CVPR.2013.153 10.1109/CVPR.2018.00330 10.1109/TGRS.2014.2357078 10.1109/TIP.2022.3220058 10.1109/CVPR.2014.43 10.1109/CVPR.2019.00404 10.24963/ijcai.2018/97 10.1109/CVPR.2019.00320 10.1109/TPAMI.2021.3140168 10.1109/CVPR46437.2021.01508 10.1109/CVPR.2016.58 10.1109/CVPR.2018.00326 10.1145/3394171.3413855 10.1109/CVPR42600.2020.00916 10.1109/ICCV48922.2021.00158 10.1109/TPAMI.2014.2353617 10.1109/CVPR.2013.407 10.1109/ICCV48922.2021.00468 10.1007/978-3-030-58452-8_17 10.1109/CVPR46437.2021.00405 10.1109/CVPR.2019.00172 10.1109/ICCV.2019.00390 10.1109/CVPR42600.2020.01304 10.1109/TPAMI.2014.2345401 10.1109/TIP.2021.3108412 10.1109/TIP.2019.2910377 10.1109/ICCV.2017.31 10.1109/ICCV48922.2021.00986 10.1007/s11432-021-3384-y 10.1109/CVPR.2009.5206596 10.1109/CVPR.2018.00445 10.1609/aaai.v35i4.16408 10.1609/aaai.v34i07.6916
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
DBID	97E RIA RIE AAYXX CITATION NPM 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8
DOI	10.1109/TIP.2023.3293759
DatabaseName	IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef PubMed Computer and Information Systems Abstracts Electronics & Communications Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional MEDLINE - Academic
DatabaseTitle	CrossRef PubMed Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional MEDLINE - Academic
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	Applied Sciences Engineering
EISSN	1941-0042
EndPage	4246
ExternalDocumentID	37440395 10_1109_TIP_2023_3293759 10183835
Genre	orig-research Journal Article
GrantInformation_xml	– fundername: Fundamental Research Funds for the Central Universities grantid: K22RC00010 funderid: 10.13039/501100012226
GroupedDBID	--- -~X .DC 0R~ 29I 4.4 53G 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABFSI ABQJQ ABVLG ACGFO ACGFS ACIWK AENEX AETIX AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 E.L EBS EJD F5P HZ~ H~9 ICLAB IFIPE IFJZH IPLJI JAVBF LAI M43 MS~ O9- OCL P2P RIA RIE RNS TAE TN5 VH1 AAYXX CITATION AAYOK NPM RIG 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8
ID	FETCH-LOGICAL-c348t-458af9d68089af0bb381390002e8c7964b79881dde28f3a1c7732bd8a9ee7e3d3
IEDL.DBID	RIE
ISICitedReferencesCount	4
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001040104200003&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1057-7149 1941-0042
IngestDate	Sun Sep 28 08:06:44 EDT 2025 Mon Jun 30 08:26:26 EDT 2025 Sun Apr 06 01:21:18 EDT 2025 Sat Nov 29 03:34:42 EST 2025 Tue Nov 18 22:18:25 EST 2025 Wed Aug 27 02:25:55 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c348t-458af9d68089af0bb381390002e8c7964b79881dde28f3a1c7732bd8a9ee7e3d3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ORCID	0000-0001-8483-6363 0000-0002-8581-9554 0000-0002-2812-8781 0000-0002-0795-8401 0000-0002-0512-880X 0000-0002-2922-5663 0000-0002-5840-760X
PMID	37440395
PQID	2843142643
PQPubID	85429
PageCount	10
ParticipantIDs	pubmed_primary_37440395 proquest_journals_2843142643 crossref_citationtrail_10_1109_TIP_2023_3293759 proquest_miscellaneous_2838255026 crossref_primary_10_1109_TIP_2023_3293759 ieee_primary_10183835
PublicationCentury	2000
PublicationDate	20230000 2023-00-00 20230101
PublicationDateYYYYMMDD	2023-01-01
PublicationDate_xml	– year: 2023 text: 20230000
PublicationDecade	2020
PublicationPlace	United States
PublicationPlace_xml	– name: United States – name: New York
PublicationTitle	IEEE transactions on image processing
PublicationTitleAbbrev	TIP
PublicationTitleAlternate	IEEE Trans Image Process
PublicationYear	2023
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref57 ref12 ref15 ref58 ref11 ref10 ref54 ref17 ref16 ref18 loshchilov (ref60) 2017 yang (ref44) 2019; 32 hassani (ref51) 2021 xu (ref3) 2015 ref46 li (ref19) 2015 ref48 ref47 xie (ref53) 2021; 34 ref42 jia (ref43) 2016; 29 ref41 vaswani (ref50) 2017 yang (ref55) 2021; 34 ref49 zhuge (ref34) 2023; 45 ref8 ref7 ref9 ref4 ref6 ref5 ref40 liu (ref36) 2022; 44 ref35 ref37 yang (ref56) 2022; 44 ref31 ref30 ref33 ref32 ref2 ref1 ref39 qi (ref45) 2023; 45 ref38 ref70 ref24 ref68 ref23 ref67 ref26 ha (ref13) 2016 ref25 ref69 ref20 ref64 ref63 ref22 ref66 ref21 ref65 zhang (ref14) 2021; 34 ref28 ref27 ref29 carion (ref52) 2020 ref62 liu (ref59) 2021 ref61
References_xml	– year: 2021 ident: ref51 article-title: Escaping the big data paradigm with compact transformers publication-title: arXiv 2104 05704 – volume: 45 start-page: 3738 year: 2023 ident: ref34 article-title: Salient object detection via integrity learning publication-title: IEEE Trans Pattern Anal Mach Intell – ident: ref24 doi: 10.1609/aaai.v35i3.16331 – ident: ref48 doi: 10.1109/ICCV48922.2021.00413 – ident: ref7 doi: 10.1007/978-3-030-58536-5_3 – volume: 44 start-page: 4701 year: 2022 ident: ref56 article-title: Collaborative video object segmentation by multi-scale foreground-background integration publication-title: IEEE Trans Pattern Anal Mach Intell – year: 2016 ident: ref13 article-title: HyperNetworks publication-title: arXiv 1609 09106 – ident: ref23 doi: 10.1007/978-3-642-33712-3_3 – year: 2021 ident: ref59 article-title: Polarized self-attention: Towards high-quality pixel-wise regression publication-title: arXiv 2107 00782 – ident: ref57 doi: 10.1109/TNNLS.2023.3243246 – start-page: 5998 year: 2017 ident: ref50 article-title: Attention is all you need publication-title: Proc Adv Neural Inf Process Syst – ident: ref9 doi: 10.1109/ICCV.2019.00887 – ident: ref31 doi: 10.1109/TIP.2022.3164550 – ident: ref67 doi: 10.1109/TIP.2021.3072811 – ident: ref66 doi: 10.1109/CVPR.2019.00403 – volume: 34 start-page: 2491 year: 2021 ident: ref55 article-title: Associating objects with transformers for video object segmentation publication-title: Proc Adv Neural Inf Process Syst – ident: ref25 doi: 10.1109/CVPR.2015.7298731 – ident: ref29 doi: 10.1109/CVPR.2019.00766 – volume: 32 start-page: 1 year: 2019 ident: ref44 article-title: CondConv: Conditionally parameterized convolutions for efficient inference publication-title: Proc Adv Neural Inf Process Syst – ident: ref21 doi: 10.1109/TPAMI.2021.3051099 – ident: ref6 doi: 10.1109/CVPR42600.2020.00943 – ident: ref16 doi: 10.1109/CVPR.2017.404 – start-page: 2048 year: 2015 ident: ref3 article-title: Show, attend and tell: Neural image caption generation with visual attention publication-title: Proc Int Conf Mach Learn – ident: ref33 doi: 10.24963/ijcai.2018/95 – ident: ref61 doi: 10.1109/CVPR.2016.90 – ident: ref8 doi: 10.1609/aaai.v34i07.6633 – ident: ref54 doi: 10.1109/ICCV48922.2021.01196 – volume: 34 start-page: 17388 year: 2021 ident: ref14 article-title: Dynamic neural representational decoders for high-resolution semantic segmentation publication-title: Proc Adv Neural Inf Process Syst – ident: ref28 doi: 10.1109/CVPR.2018.00187 – ident: ref4 doi: 10.1109/ICRA.2013.6630857 – ident: ref17 doi: 10.1109/CVPR.2013.153 – ident: ref42 doi: 10.1109/CVPR.2018.00330 – ident: ref2 doi: 10.1109/TGRS.2014.2357078 – ident: ref32 doi: 10.1109/TIP.2022.3220058 – year: 2017 ident: ref60 article-title: Decoupled weight decay regularization publication-title: arXiv 1711 05101 – ident: ref18 doi: 10.1109/CVPR.2014.43 – ident: ref30 doi: 10.1109/CVPR.2019.00404 – ident: ref64 doi: 10.24963/ijcai.2018/97 – ident: ref37 doi: 10.1109/CVPR.2019.00320 – ident: ref68 doi: 10.1109/TPAMI.2021.3140168 – ident: ref70 doi: 10.1109/CVPR46437.2021.01508 – ident: ref26 doi: 10.1109/CVPR.2016.58 – volume: 44 start-page: 8321 year: 2022 ident: ref36 article-title: Instance-level relative saliency ranking with graph reasoning publication-title: IEEE Trans Pattern Anal Mach Intell – ident: ref27 doi: 10.1109/CVPR.2018.00326 – ident: ref40 doi: 10.1145/3394171.3413855 – start-page: 5455 year: 2015 ident: ref19 article-title: Visual saliency based on multiscale deep features publication-title: Proc IEEE Conf Comput Vis Pattern Recognit (CVPR) – ident: ref12 doi: 10.1109/CVPR42600.2020.00916 – ident: ref49 doi: 10.1109/ICCV48922.2021.00158 – ident: ref1 doi: 10.1109/TPAMI.2014.2353617 – ident: ref20 doi: 10.1109/CVPR.2013.407 – ident: ref58 doi: 10.1109/ICCV48922.2021.00468 – ident: ref15 doi: 10.1007/978-3-030-58452-8_17 – ident: ref47 doi: 10.1109/CVPR46437.2021.00405 – ident: ref39 doi: 10.1109/CVPR.2019.00172 – start-page: 213 year: 2020 ident: ref52 article-title: End-to-end object detection with transformers publication-title: Proc Eur Conf Comput Vis – ident: ref65 doi: 10.1109/ICCV.2019.00390 – ident: ref11 doi: 10.1109/CVPR42600.2020.01304 – ident: ref22 doi: 10.1109/TPAMI.2014.2345401 – ident: ref10 doi: 10.1109/TIP.2021.3108412 – ident: ref35 doi: 10.1109/TIP.2019.2910377 – ident: ref38 doi: 10.1109/ICCV.2017.31 – ident: ref62 doi: 10.1109/ICCV48922.2021.00986 – ident: ref69 doi: 10.1007/s11432-021-3384-y – ident: ref63 doi: 10.1109/CVPR.2009.5206596 – ident: ref46 doi: 10.1109/CVPR.2018.00445 – volume: 45 start-page: 8743 year: 2023 ident: ref45 article-title: Open world entity segmentation publication-title: IEEE Trans Pattern Anal Mach Intell – ident: ref41 doi: 10.1609/aaai.v35i4.16408 – volume: 34 start-page: 12077 year: 2021 ident: ref53 article-title: SegFormer: Simple and efficient design for semantic segmentation with transformers publication-title: Proc Adv Neural Inf Process Syst – volume: 29 start-page: 667 year: 2016 ident: ref43 article-title: Dynamic filter networks publication-title: Proc Adv Neural Inf Process Syst – ident: ref5 doi: 10.1609/aaai.v34i07.6916
SSID	ssj0014516
Score	2.437433
Snippet	Salient object detection (SOD) aims to identify the most visually distinctive object(s) from each given image. Most recent progresses focus on either adding...
SourceID	proquest pubmed crossref ieee
SourceType	Aggregation Database Index Database Enrichment Source Publisher
StartPage	4237
SubjectTerms	Coders Collaboration content-dependent modeling Context Convolution Decoding Encoders-Decoders Feature extraction Head Image segmentation Modules Object detection Object recognition Roots Salience Salient object detection Task analysis Transformers
Title	Collaborative Content-Dependent Modeling: A Return to the Roots of Salient Object Detection
URI	https://ieeexplore.ieee.org/document/10183835 https://www.ncbi.nlm.nih.gov/pubmed/37440395 https://www.proquest.com/docview/2843142643 https://www.proquest.com/docview/2838255026
Volume	32
WOSCitedRecordID	wos001040104200003&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: 1941-0042 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014516 issn: 1057-7149 databaseCode: RIE dateStart: 19920101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1La9wwEB6akEN7yKtp4zYNCuSSg3dty15JvYU8aKGkIUnLQg9GlsdQCHbIevP7OyNrN3tJITeDx7bQjDyjGc33ARzrKjeprnWMBidcZkxi65osntSFsVluk9wn3H7_UFdXejo116FZ3ffCIKI_fIYjvvS1_Lpzc06VjRldinZUxRqsKTUZmrWWJQNmnPWlzULFiuL-RU0yMeO779cjpgkfSXJuqmCkUMnAeJJZJVbckedXeTnU9C7ncuuVg92GzRBbitPBGHbgDba7sBXiTBFW8WwX3q2AEL6HP2fPpvCEwsNVtX18Hthxe8F0ady0_lWcihskF9WKvhMUOIqbrutnomvELUXzLPqz4rSOOMfen_Bq9-DX5cXd2bc4UC7ETua6j_NC28bUzMdhbJNUFTl0ybyiGWrHXasV45ul9E_MdCNt6pSSWVVraxAVylp-gPW2a3EfRE4WgBNZ56l2OTZ1ZRPEypFTzmiuZBrBeDHzpQt45EyLcV_6fUliSlJbyWorg9oiOFk-8TBgcfxHdo9VsiI3aCOCg4V2y7BaZyW5aJlyaCgjOFrepnXGxRPbYjdnGUmb6YK2rBF8HKxi-fKFMX164aOf4S2PbcjcHMB6_zjHL7Dhnvq_s8dDMuapPvTG_A_afe1u
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3fT9swED4NhgR74GdhYd1mpL3wkDaJk8bmDcEqEF1BrCAkHiLHuUhIKJloyt8_n-OWvjBpb5FySSzfOXe-830fwA-RxzIUhfBR4oDKjIGvdBn5gyKRKopVENuE2_0oHY_Fw4O8cc3qthcGEe3hM-zRpa3lF7WeUaqsT-hSZkeVrMBHos5y7VqLogFxztriZpL6qYn851XJQPYnlzc9IgrvcePe0oSwQjlB43HilVhySJZh5f1g0zqd4dZ_DncbNl10yU5bc9iBD1jtwpaLNJlbx9Nd-LQEQ7gHj2dvxvCKzAJWVY1_7vhxG0aEadS2fsJO2S0aJ1WxpmYmdGS3dd1MWV2y3yaeJ9HrnBI77Bwbe8ar6sDd8Ofk7MJ3pAu-5rFo_DgRqpQFMXJIVQZ5blw6J2bRCIWmvtWcEM5C81eMRMlVqNOUR3khlERMkRd8H1arusLPwGJjAzjgRRwKHWNZ5CpAzLVxy5GZKx560J_PfKYdIjkRYzxndmcSyMyoLSO1ZU5tHhwvnvjTonH8Q7ZDKlmSa7XhQXeu3cyt12lmnDQPKTjkHhwtbpuVRuUTVWE9IxluttOJ2bR6cNBaxeLlc2M6fOej32H9YvJrlI0ux1dfYIPG2eZxurDavMzwK6zp1-Zp-vLNmvRfxnnvzw
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=Collaborative+Content-Dependent+Modeling%3A+A+Return+to+the+Roots+of+Salient+Object+Detection&rft.jtitle=IEEE+transactions+on+image+processing&rft.au=Jiao%2C+Siyu&rft.au=Goel%2C+Vidit&rft.au=Navasardyan%2C+Shant&rft.au=Yang%2C+Zongxin&rft.date=2023&rft.pub=IEEE&rft.issn=1057-7149&rft.volume=32&rft.spage=4237&rft.epage=4246&rft_id=info:doi/10.1109%2FTIP.2023.3293759&rft_id=info%3Apmid%2F37440395&rft.externalDocID=10183835
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1057-7149&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1057-7149&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1057-7149&client=summon