Object-Level Scene Context Prediction
Contextual information plays an important role in solving various image and scene understanding tasks. Prior works have focused on the extraction of contextual information from an image and use it to infer the properties of some object(s) in the image or understand the scene behind the image, e.g.,...
Saved in:
| Published in | IEEE transactions on pattern analysis and machine intelligence Vol. 44; no. 9; pp. 5280 - 5292 |
|---|---|
| Main Authors | , , , |
| Format | Journal Article |
| Language | English |
| Published |
United States
IEEE
01.09.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Subjects | |
| Online Access | Get full text |
| ISSN | 0162-8828 1939-3539 2160-9292 1939-3539 |
| DOI | 10.1109/TPAMI.2021.3075676 |
Cover
| Abstract | Contextual information plays an important role in solving various image and scene understanding tasks. Prior works have focused on the extraction of contextual information from an image and use it to infer the properties of some object(s) in the image or understand the scene behind the image, e.g., context-based object detection, recognition and semantic segmentation. In this paper, we consider an inverse problem, i.e., how to hallucinate the missing contextual information from the properties of standalone objects. We refer to it as object-level scene context prediction. This problem is difficult, as it requires extensive knowledge of the complex and diverse relationships among objects in the scene. We propose a deep neural network, which takes as input the properties (i.e., category, shape, and position) of a few standalone objects to predict an object-level scene layout that compactly encodes the semantics and structure of the scene context where the given objects are. Quantitative experiments and user studies demonstrate that our model can generate more plausible scene contexts than the baselines. Our model also enables the synthesis of realistic scene images from partial scene layouts. Finally, we validate that our model internally learns useful features for scene recognition and fake scene detection. |
|---|---|
| AbstractList | Contextual information plays an important role in solving various image and scene understanding tasks. Prior works have focused on the extraction of contextual information from an image and use it to infer the properties of some object(s) in the image or understand the scene behind the image, e.g., context-based object detection, recognition and semantic segmentation. In this paper, we consider an inverse problem, i.e., how to hallucinate the missing contextual information from the properties of standalone objects. We refer to it as object-level scene context prediction. This problem is difficult, as it requires extensive knowledge of the complex and diverse relationships among objects in the scene. We propose a deep neural network, which takes as input the properties (i.e., category, shape, and position) of a few standalone objects to predict an object-level scene layout that compactly encodes the semantics and structure of the scene context where the given objects are. Quantitative experiments and user studies demonstrate that our model can generate more plausible scene contexts than the baselines. Our model also enables the synthesis of realistic scene images from partial scene layouts. Finally, we validate that our model internally learns useful features for scene recognition and fake scene detection. Contextual information plays an important role in solving various image and scene understanding tasks. Prior works have focused on the extraction of contextual information from an image and use it to infer the properties of some object(s) in the image or understand the scene behind the image, e.g., context-based object detection, recognition and semantic segmentation. In this paper, we consider an inverse problem, i.e., how to hallucinate the missing contextual information from the properties of standalone objects. We refer to it as object-level scene context prediction. This problem is difficult, as it requires extensive knowledge of the complex and diverse relationships among objects in the scene. We propose a deep neural network, which takes as input the properties (i.e., category, shape, and position) of a few standalone objects to predict an object-level scene layout that compactly encodes the semantics and structure of the scene context where the given objects are. Quantitative experiments and user studies demonstrate that our model can generate more plausible scene contexts than the baselines. Our model also enables the synthesis of realistic scene images from partial scene layouts. Finally, we validate that our model internally learns useful features for scene recognition and fake scene detection.Contextual information plays an important role in solving various image and scene understanding tasks. Prior works have focused on the extraction of contextual information from an image and use it to infer the properties of some object(s) in the image or understand the scene behind the image, e.g., context-based object detection, recognition and semantic segmentation. In this paper, we consider an inverse problem, i.e., how to hallucinate the missing contextual information from the properties of standalone objects. We refer to it as object-level scene context prediction. This problem is difficult, as it requires extensive knowledge of the complex and diverse relationships among objects in the scene. We propose a deep neural network, which takes as input the properties (i.e., category, shape, and position) of a few standalone objects to predict an object-level scene layout that compactly encodes the semantics and structure of the scene context where the given objects are. Quantitative experiments and user studies demonstrate that our model can generate more plausible scene contexts than the baselines. Our model also enables the synthesis of realistic scene images from partial scene layouts. Finally, we validate that our model internally learns useful features for scene recognition and fake scene detection. |
| Author | Qiao, Xiaotian Lau, Rynson W.H. Zheng, Quanlong Cao, Ying |
| Author_xml | – sequence: 1 givenname: Xiaotian orcidid: 0000-0002-5351-8335 surname: Qiao fullname: Qiao, Xiaotian email: qiaoxt1992@gmail.com organization: Department of Computer Science, City University of Hong Kong, Hong Kong – sequence: 2 givenname: Quanlong orcidid: 0000-0001-5059-0078 surname: Zheng fullname: Zheng, Quanlong email: xiaolong921001@gmail.com organization: Department of Computer Science, City University of Hong Kong, Hong Kong – sequence: 3 givenname: Ying orcidid: 0000-0002-9288-3167 surname: Cao fullname: Cao, Ying email: caoying59@gmail.com organization: Department of Computer Science, City University of Hong Kong, Hong Kong – sequence: 4 givenname: Rynson W.H. orcidid: 0000-0002-8957-8129 surname: Lau fullname: Lau, Rynson W.H. email: rynson.lau@cityu.edu.hk organization: Department of Computer Science, City University of Hong Kong, Hong Kong |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/33905322$$D View this record in MEDLINE/PubMed |
| BookMark | eNp9kE1LAzEQQINU7If-AQUpiOBlaybZZJNjKX4UKi1YzyFNJrBlu1t3t6L_3l3bevDgaS7vDTOvTzp5kSMhl0BHAFTfLxfjl-mIUQYjThMhE3lCegwkjTTTrEN6FCSLlGKqS_pVtaYUYkH5GelyrqngjPXI7Xy1RldHM_zAbPjqMMfhpMhr_KyHixJ96uq0yM_JabBZhReHOSBvjw_LyXM0mz9NJ-NZ5LiAOpJBawAnvEyUQ-RJHFZBrDDxiRU-CYL72MU8UM-8be4OLLZgpQpKc2Fjzwfkbr93WxbvO6xqs0krh1lmcyx2lWECNAetpGzQmz_outiVeXOdYVK3T0OsG-r6QO1WG_RmW6YbW36ZY4AGUHvAlUVVlRiMS2vb_lyXNs0MUNO2Nj-tTdvaHFo3KvujHrf_K13tpRQRfwUdg1QA_BtTAodc |
| CODEN | ITPIDJ |
| CitedBy_id | crossref_primary_10_1109_TIM_2024_3441019 |
| Cites_doi | 10.1109/CVPR.2018.00730 10.1109/CVPR.2017.632 10.1109/CVPR.2018.00917 10.1007/978-3-642-15549-9_1 10.1109/CVPR.2017.359 10.1109/CVPR.2018.00833 10.1109/CVPR.2019.00152 10.1145/3130800.3130805 10.1109/ICCV.2015.164 10.1109/TPAMI.2009.154 10.1109/CVPR.2014.37 10.1109/CVPR.2018.00133 10.1109/ICCV.2013.51 10.1109/CVPR.2017.660 10.1109/CVPR.2018.00378 10.1111/cgf.12976 10.1109/CVPR.2010.5539970 10.1109/ICCV.2017.168 10.1016/j.patrec.2011.12.004 10.1007/s11263-011-0439-x 10.1109/ICCVW.2017.30 10.1109/CVPR.2018.00618 10.1038/nrn1476 10.1109/CVPR.2016.174 10.1006/cogp.1998.0681 10.1109/CVPR.2018.00068 10.1109/CVPR.2018.00981 10.1007/978-3-319-10602-1_48 10.1109/CVPR.2018.00918 10.1109/CVPR.2009.5206532 10.1145/3197517.3201362 10.1109/CVPR.2016.91 10.1109/ICCV.2017.304 10.1007/978-3-030-01219-9_31 10.1109/TGRS.2019.2899955 10.1109/CVPR.2016.278 10.1023/A:1023052124951 10.1109/CVPR.2017.330 10.1109/CVPR.2014.119 10.1109/WACV.2018.00170 10.1145/1666420.1666446 10.1109/CVPR.2019.00244 10.1109/TPAMI.2019.2963663 10.1007/978-3-030-01258-8_23 10.1109/ICCV.2015.167 10.1145/2661229.2661243 10.1109/TPAMI.2011.119 10.1109/CVPR.2016.18 10.1109/ICCV.2015.169 10.1109/CVPR.2018.00132 10.1109/ICCV.2019.00999 10.1109/TPAMI.2009.186 10.1109/CVPR.2019.00274 10.1145/3065386 |
| ContentType | Journal Article |
| Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022 |
| Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022 |
| DBID | 97E RIA RIE AAYXX CITATION NPM 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8 |
| DOI | 10.1109/TPAMI.2021.3075676 |
| DatabaseName | IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Xplore 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: https://proxy.k.utb.cz/login?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://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering Computer Science |
| EISSN | 2160-9292 1939-3539 |
| EndPage | 5292 |
| ExternalDocumentID | 33905322 10_1109_TPAMI_2021_3075676 9416811 |
| Genre | orig-research Journal Article |
| GrantInformation_xml | – fundername: Research Grants Council of Hong Kong grantid: 11205620 |
| GroupedDBID | --- -DZ -~X .DC 0R~ 29I 4.4 53G 5GY 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK ACNCT AENEX AGQYO AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 E.L EBS EJD F5P HZ~ IEDLZ IFIPE IPLJI JAVBF LAI M43 MS~ O9- OCL P2P PQQKQ RIA RIE RNS RXW TAE TN5 UHB ~02 5VS 9M8 AAYOK AAYXX ABFSI ADRHT AETEA AETIX AGSQL AI. AIBXA ALLEH CITATION FA8 H~9 IBMZZ ICLAB IFJZH RIG RNI RZB VH1 XJT NPM 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8 |
| ID | FETCH-LOGICAL-c351t-6f9911c5d678cee374fbf5be7d7a5d7f53d4c43f0d2da202f24a1a68f8935a4d3 |
| IEDL.DBID | RIE |
| ISSN | 0162-8828 1939-3539 |
| IngestDate | Thu Jul 10 23:11:29 EDT 2025 Mon Jun 30 06:22:41 EDT 2025 Thu Apr 03 07:06:53 EDT 2025 Thu Apr 24 23:06:46 EDT 2025 Tue Jul 01 03:18:26 EDT 2025 Wed Aug 27 02:29:16 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 9 |
| Language | English |
| License | https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c351t-6f9911c5d678cee374fbf5be7d7a5d7f53d4c43f0d2da202f24a1a68f8935a4d3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 |
| ORCID | 0000-0002-5351-8335 0000-0002-9288-3167 0000-0002-8957-8129 0000-0001-5059-0078 |
| PMID | 33905322 |
| PQID | 2698828149 |
| PQPubID | 85458 |
| PageCount | 13 |
| ParticipantIDs | crossref_citationtrail_10_1109_TPAMI_2021_3075676 ieee_primary_9416811 proquest_miscellaneous_2519319866 pubmed_primary_33905322 crossref_primary_10_1109_TPAMI_2021_3075676 proquest_journals_2698828149 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2022-09-01 |
| PublicationDateYYYYMMDD | 2022-09-01 |
| PublicationDate_xml | – month: 09 year: 2022 text: 2022-09-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States – name: New York |
| PublicationTitle | IEEE transactions on pattern analysis and machine intelligence |
| PublicationTitleAbbrev | TPAMI |
| PublicationTitleAlternate | IEEE Trans Pattern Anal Mach Intell |
| PublicationYear | 2022 |
| 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 | ref13 ref57 ref12 ref15 Goodfellow (ref40); 2 ref59 ref14 ref58 ref53 ref52 ref11 ref55 ref10 ref54 Zhu (ref46) ref17 ref16 ref19 ref18 Zhou (ref56) Aneja (ref61) 2021 ref50 ref45 ref48 ref47 ref42 ref41 ref43 ref49 ref8 Torralba (ref5) 2003; 53 ref7 ref9 ref4 ref3 ref6 Kingma (ref44) 2014 Heusel (ref51) Wu (ref63) ref35 ref34 ref37 ref36 ref31 ref30 ref33 ref32 Jaderberg (ref38) ref2 ref1 ref39 ref24 ref23 ref26 ref25 ref20 ref22 ref21 ref27 Mikolov (ref28) ref29 ref60 ref62 |
| References_xml | – ident: ref2 doi: 10.1109/CVPR.2018.00730 – start-page: 3111 volume-title: Proc. 26th Int. Conf. Neural Inf. Process. Syst. ident: ref28 article-title: Distributed representations of words and phrases and their compositionality, – start-page: 487 volume-title: Proc. 27th Int. Conf. Neural Inf. Process. Syst ident: ref56 article-title: Learning deep features for scene recognition using places database, – ident: ref8 doi: 10.1109/CVPR.2017.632 – ident: ref33 doi: 10.1109/CVPR.2018.00917 – ident: ref48 doi: 10.1007/978-3-642-15549-9_1 – ident: ref21 doi: 10.1109/CVPR.2017.359 – ident: ref34 doi: 10.1109/CVPR.2018.00833 – ident: ref42 doi: 10.1109/CVPR.2019.00152 – year: 2021 ident: ref61 article-title: Catching out-of-context misinformation with self-supervised learning, – ident: ref23 doi: 10.1145/3130800.3130805 – ident: ref53 doi: 10.1109/ICCV.2015.164 – ident: ref58 doi: 10.1109/TPAMI.2009.154 – start-page: 82 volume-title: Proc. 30th Int. Conf. Neural Inf. Process. Syst. ident: ref63 article-title: Learning a probabilistic latent space of object shapes via 3D generative-adversarial modeling, – ident: ref19 doi: 10.1109/CVPR.2014.37 – ident: ref35 doi: 10.1109/CVPR.2018.00133 – ident: ref17 doi: 10.1109/ICCV.2013.51 – ident: ref59 doi: 10.1109/CVPR.2017.660 – ident: ref1 doi: 10.1109/CVPR.2018.00378 – ident: ref22 doi: 10.1111/cgf.12976 – ident: ref57 doi: 10.1109/CVPR.2010.5539970 – start-page: 2017 volume-title: Proc. 28th Int. Conf. Neural Inf. Process. Syst. ident: ref38 article-title: Spatial transformer networks, – ident: ref39 doi: 10.1109/ICCV.2017.168 – ident: ref18 doi: 10.1016/j.patrec.2011.12.004 – ident: ref16 doi: 10.1007/s11263-011-0439-x – ident: ref20 doi: 10.1109/ICCVW.2017.30 – volume: 2 start-page: 2672 volume-title: Proc. 27th Int. Conf. Neural Inf. Process. Syst. ident: ref40 article-title: Generative adversarial nets, – ident: ref24 doi: 10.1109/CVPR.2018.00618 – ident: ref12 doi: 10.1038/nrn1476 – ident: ref60 doi: 10.1109/CVPR.2016.174 – ident: ref13 doi: 10.1006/cogp.1998.0681 – ident: ref50 doi: 10.1109/CVPR.2018.00068 – ident: ref54 doi: 10.1109/CVPR.2018.00981 – year: 2014 ident: ref44 article-title: Adam: A method for stochastic optimization, – ident: ref47 doi: 10.1007/978-3-319-10602-1_48 – ident: ref52 doi: 10.1109/CVPR.2018.00918 – ident: ref3 doi: 10.1109/CVPR.2009.5206532 – ident: ref25 doi: 10.1145/3197517.3201362 – ident: ref43 doi: 10.1109/CVPR.2016.91 – ident: ref41 doi: 10.1109/ICCV.2017.304 – ident: ref32 doi: 10.1007/978-3-030-01219-9_31 – ident: ref37 doi: 10.1109/TGRS.2019.2899955 – ident: ref7 doi: 10.1109/CVPR.2016.278 – volume: 53 start-page: 169 issue: 2 year: 2003 ident: ref5 article-title: Contextual priming for object detection, publication-title: Int. J. Comput. Vis. doi: 10.1023/A:1023052124951 – ident: ref9 doi: 10.1109/CVPR.2017.330 – ident: ref4 doi: 10.1109/CVPR.2014.119 – ident: ref31 doi: 10.1109/WACV.2018.00170 – ident: ref15 doi: 10.1145/1666420.1666446 – ident: ref45 doi: 10.1109/CVPR.2019.00244 – ident: ref26 doi: 10.1109/TPAMI.2019.2963663 – ident: ref14 doi: 10.1007/978-3-030-01258-8_23 – ident: ref29 doi: 10.1109/ICCV.2015.167 – ident: ref49 doi: 10.1145/2661229.2661243 – ident: ref62 doi: 10.1109/TPAMI.2011.119 – ident: ref30 doi: 10.1109/CVPR.2016.18 – ident: ref36 doi: 10.1109/ICCV.2015.169 – start-page: 465 volume-title: Proc. 31st Int. Conf. Neural Inf. Process. Syst. ident: ref46 article-title: Toward multimodal image-to-image translation, – ident: ref10 doi: 10.1109/CVPR.2018.00132 – start-page: 6629 volume-title: Proc. 31st Int. Conf. Neural Inf. Process. Syst. ident: ref51 article-title: GANs trained by a two time-scale update rule converge to a local Nash equilibrium, – ident: ref27 doi: 10.1109/ICCV.2019.00999 – ident: ref6 doi: 10.1109/TPAMI.2009.186 – ident: ref11 doi: 10.1109/CVPR.2019.00274 – ident: ref55 doi: 10.1145/3065386 |
| SSID | ssj0014503 |
| Score | 2.4172857 |
| Snippet | Contextual information plays an important role in solving various image and scene understanding tasks. Prior works have focused on the extraction of contextual... |
| SourceID | proquest pubmed crossref ieee |
| SourceType | Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 5280 |
| SubjectTerms | Artificial neural networks Context Context modeling Feature recognition Generators Image segmentation Inverse problems Layout Layouts object inference object properties Object recognition Scene analysis Scene context scene understanding Semantics Shape Task analysis Visualization |
| Title | Object-Level Scene Context Prediction |
| URI | https://ieeexplore.ieee.org/document/9416811 https://www.ncbi.nlm.nih.gov/pubmed/33905322 https://www.proquest.com/docview/2698828149 https://www.proquest.com/docview/2519319866 |
| Volume | 44 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1JT9tQEB4Bp3KAkrCkBeRK9AQOsd-Wd0QVKFQNzQEkbpbfdmmVoNSRKn49M8-LSgWImyWPt1k837w3C8CJCVJzdEOpDkaknOp8dOZsalypUGekY3Hy3PRGTu7493txvwZnXS2M9z4mn_khHca9fLewK1oqO9eIHsZUyLuOalbXanU7BlzEKciIYNDCMYxoC2RG-vx2djG9xlAwz4ao0UIqmlvEMNgXLM-f-aM4YOV1rBl9ztU2TNu3rVNNfg1XlRnax_8aOb73cz7CVgM-k4taW3Zgzc97sN0OdkgaO-_B5j9dCvvw9aehxZr0B-UXIRH-HZPY1OpvlcyWtNFDwt2Fu6vL22-TtJmukFomsiqVAaFhZoVDd4WekikeTBDGK6dK4VQQzHHLWRi53JXIvJDzMivlOCDCESV3bA825ou5P4AkU4Q6xoHrYLlS0ggrmWKqZFx5btkAspbHhW1aj9MEjN9FDEFGuogiKkhERSOiAZx21zzUjTfepO4TfzvKhrUDOGxFWTS2-afIpSYFwdBwAF-602hVtFVSzv1ihTQEbDM9lnjn_VoFunu3mvPp5Wd-hg85lUjEPLRD2KiWK3-EwKUyx1FjnwCXauOm |
| linkProvider | IEEE |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1JT9tQEB4hOAAHKFAgLK0rtafiEPtteUeEikKbUA5B4mb5bRdQgqgjVf31nXleRBFF3Cx5vM3i-ea9WQA-myA1RzeU6mBEyqnOR2fOpsaVCnVGOhYnz02u5OiGf78Vt0tw0tXCeO9j8pnv02Hcy3dzu6ClslON6GFIhbwr6Pe5qKu1uj0DLuIcZMQwaOMYSLQlMgN9Or0-m1xiMJhnfdRpIRVNLmIY7guW5_94pDhi5f9oM3qdi02YtO9bJ5vc9ReV6ds_z1o5vvWD3sFGAz-Ts1pftmDJz7Zhsx3tkDSWvg3rT_oU7sCXn4aWa9IxZRghEf4fk9jW6neVXD_SVg-J9z3cXHybno_SZr5CapnIqlQGBIeZFQ4dFvpKpngwQRivnCqFU0Ewxy1nYeByVyLzQs7LrJTDgBhHlNyxXViezWd-H5JMEe4YBq6D5UpJI6xkiqmSceW5ZT3IWh4Xtmk-TjMw7osYhAx0EUVUkIiKRkQ9-Npd81C33niVeof421E2rO3BUSvKorHOX0UuNSkIBoc9-NSdRruizZJy5ucLpCFom-mhxDvv1SrQ3bvVnIOXn_kRVkfTybgYX179OIS1nAomYlbaESxXjwt_jDCmMh-i9v4Fr_fm8w |
| 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=Object-Level+Scene+Context+Prediction&rft.jtitle=IEEE+transactions+on+pattern+analysis+and+machine+intelligence&rft.au=Qiao%2C+Xiaotian&rft.au=Zheng%2C+Quanlong&rft.au=Cao%2C+Ying&rft.au=Rynson+WH+Lau&rft.date=2022-09-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.issn=0162-8828&rft.eissn=1939-3539&rft.volume=44&rft.issue=9&rft.spage=5280&rft_id=info:doi/10.1109%2FTPAMI.2021.3075676&rft.externalDBID=NO_FULL_TEXT |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0162-8828&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0162-8828&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0162-8828&client=summon |