RelTR: Relation Transformer for Scene Graph Generation
Different objects in the same scene are more or less related to each other, but only a limited number of these relationships are noteworthy. Inspired by Detection Transformer, which excels in object detection, we view scene graph generation as a set prediction problem. In this article, we propose an...
Saved in:
| Published in: | IEEE transactions on pattern analysis and machine intelligence Vol. 45; no. 9; pp. 11169 - 11183 |
|---|---|
| Main Authors: | , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
United States
IEEE
01.09.2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Subjects: | |
| ISSN: | 0162-8828, 1939-3539, 2160-9292, 1939-3539 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Different objects in the same scene are more or less related to each other, but only a limited number of these relationships are noteworthy. Inspired by Detection Transformer, which excels in object detection, we view scene graph generation as a set prediction problem. In this article, we propose an end-to-end scene graph generation model Relation Transformer (RelTR), which has an encoder-decoder architecture. The encoder reasons about the visual feature context while the decoder infers a fixed-size set of triplets subject-predicate-object using different types of attention mechanisms with coupled subject and object queries. We design a set prediction loss performing the matching between the ground truth and predicted triplets for the end-to-end training. In contrast to most existing scene graph generation methods, RelTR is a one-stage method that predicts sparse scene graphs directly only using visual appearance without combining entities and labeling all possible predicates. Extensive experiments on the Visual Genome, Open Images V6, and VRD datasets demonstrate the superior performance and fast inference of our model. |
|---|---|
| AbstractList | Different objects in the same scene are more or less related to each other, but only a limited number of these relationships are noteworthy. Inspired by Detection Transformer, which excels in object detection, we view scene graph generation as a set prediction problem. In this article, we propose an end-to-end scene graph generation model Relation Transformer (RelTR), which has an encoder-decoder architecture. The encoder reasons about the visual feature context while the decoder infers a fixed-size set of triplets subject-predicate-object using different types of attention mechanisms with coupled subject and object queries. We design a set prediction loss performing the matching between the ground truth and predicted triplets for the end-to-end training. In contrast to most existing scene graph generation methods, RelTR is a one-stage method that predicts sparse scene graphs directly only using visual appearance without combining entities and labeling all possible predicates. Extensive experiments on the Visual Genome, Open Images V6, and VRD datasets demonstrate the superior performance and fast inference of our model.Different objects in the same scene are more or less related to each other, but only a limited number of these relationships are noteworthy. Inspired by Detection Transformer, which excels in object detection, we view scene graph generation as a set prediction problem. In this article, we propose an end-to-end scene graph generation model Relation Transformer (RelTR), which has an encoder-decoder architecture. The encoder reasons about the visual feature context while the decoder infers a fixed-size set of triplets subject-predicate-object using different types of attention mechanisms with coupled subject and object queries. We design a set prediction loss performing the matching between the ground truth and predicted triplets for the end-to-end training. In contrast to most existing scene graph generation methods, RelTR is a one-stage method that predicts sparse scene graphs directly only using visual appearance without combining entities and labeling all possible predicates. Extensive experiments on the Visual Genome, Open Images V6, and VRD datasets demonstrate the superior performance and fast inference of our model. Different objects in the same scene are more or less related to each other, but only a limited number of these relationships are noteworthy. Inspired by Detection Transformer, which excels in object detection, we view scene graph generation as a set prediction problem. In this article, we propose an end-to-end scene graph generation model Relation Transformer (RelTR), which has an encoder-decoder architecture. The encoder reasons about the visual feature context while the decoder infers a fixed-size set of triplets subject-predicate-object using different types of attention mechanisms with coupled subject and object queries. We design a set prediction loss performing the matching between the ground truth and predicted triplets for the end-to-end training. In contrast to most existing scene graph generation methods, RelTR is a one-stage method that predicts sparse scene graphs directly only using visual appearance without combining entities and labeling all possible predicates. Extensive experiments on the Visual Genome, Open Images V6, and VRD datasets demonstrate the superior performance and fast inference of our model. |
| Author | Rosenhahn, Bodo Cong, Yuren Yang, Michael Ying |
| Author_xml | – sequence: 1 givenname: Yuren orcidid: 0000-0001-7505-8563 surname: Cong fullname: Cong, Yuren email: cong@tnt.uni-hannover.de organization: Institute of Information Processing, Leibniz University Hannover, Hannover, Germany – sequence: 2 givenname: Michael Ying orcidid: 0000-0002-0649-9987 surname: Yang fullname: Yang, Michael Ying email: michael.yang@utwente.nl organization: Scene Understanding Group, Faculty of Geo-Information Science and Earth Observation (ITC), University of Twente, Enschede, NB, The Netherlands – sequence: 3 givenname: Bodo orcidid: 0000-0003-3861-1424 surname: Rosenhahn fullname: Rosenhahn, Bodo email: rosenhahn@tnt.uni-hannover.de organization: Institute of Information Processing, Leibniz University Hannover, Hannover, Germany |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/37074895$$D View this record in MEDLINE/PubMed |
| BookMark | eNp9kE1Lw0AQhhep2A_9AyIS8OIldXcn2ex6K0VroaLUel426QRT0qTuJgf_vdsvkB48vXN43mHm6ZNOVVdIyDWjQ8aoeli8j16nQ045DIELSYU4Iz3OBA0VV7xDepQJHkrJZZf0nVtRyqKYwgXpQkKTSKq4R8Qcy8X8MfBhmqKugoU1lctru0Yb-Ag-MqwwmFiz-QomfrQ77JKc56Z0eHXIAfl8flqMX8LZ22Q6Hs3CDGLehAkkucRIMcYzASJFwJTFcUxRYa7SKElzjJAxNFypXGQyQzDLZaoEWyrIYxiQ-_3eja2_W3SNXhcuw7I0Fdat01xSAPAywKN3J-iqbm3lr_NUlKg4AYg8dXug2nSNS72xxdrYH3004gG5BzJbO2cx11nR7H5urClKzajeytc7-XorXx_k-yo_qR63_1u62ZcKRPxTYNRrSuAXoteNrw |
| CODEN | ITPIDJ |
| CitedBy_id | crossref_primary_10_1109_TIP_2025_3543114 crossref_primary_10_1109_TMC_2024_3438152 crossref_primary_10_1109_TPAMI_2024_3389030 crossref_primary_10_1016_j_isprsjprs_2025_01_012 crossref_primary_10_1109_LRA_2024_3412593 crossref_primary_10_1016_j_ins_2025_122668 crossref_primary_10_3390_info15120766 crossref_primary_10_1007_s40747_024_01746_z crossref_primary_10_1016_j_patrec_2025_04_005 crossref_primary_10_1007_s11263_025_02564_7 crossref_primary_10_1016_j_neucom_2023_127052 crossref_primary_10_1016_j_neucom_2025_131307 crossref_primary_10_1109_TIP_2025_3540296 crossref_primary_10_1016_j_neucom_2025_130130 crossref_primary_10_1016_j_patcog_2024_111039 crossref_primary_10_1109_TVT_2025_3529763 crossref_primary_10_1145_3659610 crossref_primary_10_1016_j_eswa_2025_129525 crossref_primary_10_1109_MWC_002_2400349 crossref_primary_10_1007_s10618_025_01121_7 crossref_primary_10_1109_TCSVT_2023_3349130 crossref_primary_10_1109_TPAMI_2023_3332246 crossref_primary_10_1016_j_rineng_2025_105397 crossref_primary_10_1109_LCOMM_2024_3496534 crossref_primary_10_3390_s24134329 crossref_primary_10_1007_s11263_025_02365_y crossref_primary_10_1016_j_patrec_2025_04_036 crossref_primary_10_3233_MGS_230132 crossref_primary_10_1016_j_patcog_2025_112183 crossref_primary_10_1109_TIE_2023_3323695 crossref_primary_10_1109_TPAMI_2025_3531452 crossref_primary_10_1109_JIOT_2024_3464646 crossref_primary_10_1145_3748318 crossref_primary_10_1109_TPAMI_2025_3559995 crossref_primary_10_1109_MNET_2023_3334285 crossref_primary_10_1016_j_patcog_2025_111641 crossref_primary_10_1016_j_compag_2025_110865 crossref_primary_10_1016_j_inffus_2025_103260 crossref_primary_10_1109_ACCESS_2024_3450908 crossref_primary_10_1038_s40494_025_01950_1 crossref_primary_10_1109_ACCESS_2025_3555230 crossref_primary_10_1109_TCSVT_2025_3548308 crossref_primary_10_1109_JSTARS_2025_3571939 crossref_primary_10_1109_ACCESS_2024_3360113 crossref_primary_10_1109_TVT_2025_3541019 crossref_primary_10_1016_j_image_2025_117273 crossref_primary_10_1109_MWC_001_2300014 crossref_primary_10_1109_ACCESS_2023_3332098 crossref_primary_10_1016_j_neunet_2024_107002 crossref_primary_10_1016_j_isci_2024_109571 crossref_primary_10_1109_TPAMI_2024_3508072 crossref_primary_10_1016_j_dsp_2024_104611 crossref_primary_10_1109_TPAMI_2024_3402143 crossref_primary_10_1038_s41598_023_48916_6 crossref_primary_10_1016_j_dcan_2025_04_010 crossref_primary_10_1016_j_patcog_2025_111992 crossref_primary_10_1016_j_engappai_2025_111984 crossref_primary_10_1109_TIP_2023_3345652 crossref_primary_10_1007_s44443_025_00063_w crossref_primary_10_1007_s11263_025_02499_z crossref_primary_10_1016_j_eswa_2025_127486 crossref_primary_10_1109_TMI_2024_3444279 |
| Cites_doi | 10.1109/CVPR46437.2021.00863 10.1109/ICCV48922.2021.00144 10.1007/s11263-020-01316-z 10.1109/CVPR.2018.00611 10.1109/CVPR.2017.331 10.1109/CVPR46437.2021.01096 10.1109/CVPR.2008.4587799 10.1007/978-3-030-01219-9_20 10.1007/978-3-030-58565-5_38 10.1109/GC46384.2019.00015 10.1109/CVPR46437.2021.01138 10.1609/aaai.v33i01.33013159 10.1109/CVPR42600.2020.00377 10.1109/CVPR.2017.330 10.1109/CVPR.2019.00408 10.1109/CVPR46437.2021.01372 10.1109/ICCV48922.2021.01560 10.1109/ICCV.2017.142 10.1109/CVPR46437.2021.00014 10.1109/CVPR52688.2022.01890 10.1007/978-3-030-58592-1_36 10.1109/ICCV.2019.00972 10.1109/ICCV48922.2021.01512 10.1109/CVPR.2019.00857 10.1109/ICIP.2019.8803182 10.1007/978-3-319-46448-0_51 10.1109/CVPR42600.2020.01025 10.1007/s11263-008-0140-x 10.1109/CVPR42600.2020.00380 10.1109/CVPR46437.2021.01165 10.1109/CVPR.2019.00527 10.1109/CVPR.2019.00550 10.1109/CVPR.2019.01094 10.1109/ICCV.2017.121 10.1109/ICCV.2017.325 10.1109/CVPR.2017.469 10.1145/3240508.3240668 10.1109/ICCV48922.2021.01563 10.1109/ICCV48922.2021.01607 10.1109/CVPR.2019.00075 10.1109/CVPR.2019.00838 10.1109/CVPR.2019.00207 10.1109/TPAMI.2016.2577031 10.1007/978-3-030-01246-5_21 10.1109/CVPR52688.2022.01883 10.1109/CVPR.2019.01180 10.1109/ICCV48922.2021.01343 10.1109/CVPR.2015.7298990 10.1145/3474085.3475297 10.1109/ICCV.2019.00471 10.1109/ICCV48922.2021.01606 10.1109/CVPRW53098.2021.00244 10.1109/ICCVW.2019.00218 10.1109/CVPR.2019.00632 10.1007/978-3-030-01246-5_41 10.1145/3195106.3195114 10.1109/ICCV.2019.01042 10.1109/ICCV48922.2021.01608 10.1109/ICCV.2019.00466 10.1109/CVPR.2018.00133 10.1109/CVPR.2016.255 10.1145/3394171.3413722 10.1109/CVPR.2019.00678 10.1109/CVPR.2017.352 10.1109/CVPR.2009.5206848 10.1109/CVPR52688.2022.01888 10.1007/s11263-016-0981-7 |
| 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/TPAMI.2023.3268066 |
| DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005–Present 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 | MEDLINE - Academic Technology Research Database PubMed |
| 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 | Engineering Computer Science |
| EISSN | 2160-9292 1939-3539 |
| EndPage | 11183 |
| ExternalDocumentID | 37074895 10_1109_TPAMI_2023_3268066 10105507 |
| Genre | orig-research Journal Article |
| GrantInformation_xml | – fundername: Bundesministerium für Bildung und Forschung; Federal Ministry of Education and Research grantid: 01DD20003 funderid: 10.13039/501100002347 – fundername: Deutsche Forschungsgemeinschaft funderid: 10.13039/501100001659 – fundername: Center for Digital Innovations |
| 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 AAYXX CITATION 5VS 9M8 AAYOK ABFSI ADRHT AETEA AETIX AGSQL AI. AIBXA ALLEH FA8 H~9 IBMZZ ICLAB IFJZH NPM RIG RNI RZB VH1 XJT 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8 |
| ID | FETCH-LOGICAL-c352t-737f8e49112c636be3eb15550e9ef9b47bfe4e11ea299f6c8ce3addb961d93f53 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 104 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001045832200037&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0162-8828 1939-3539 |
| IngestDate | Sun Sep 28 01:39:45 EDT 2025 Mon Jun 30 06:34:03 EDT 2025 Thu Apr 03 07:04:19 EDT 2025 Sat Nov 29 02:58:23 EST 2025 Tue Nov 18 22:33:42 EST 2025 Wed Aug 27 02:46:14 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 9 |
| 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-c352t-737f8e49112c636be3eb15550e9ef9b47bfe4e11ea299f6c8ce3addb961d93f53 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 |
| ORCID | 0000-0003-3861-1424 0000-0002-0649-9987 0000-0001-7505-8563 |
| PMID | 37074895 |
| PQID | 2847957334 |
| PQPubID | 85458 |
| PageCount | 15 |
| ParticipantIDs | crossref_citationtrail_10_1109_TPAMI_2023_3268066 pubmed_primary_37074895 proquest_miscellaneous_2803331093 ieee_primary_10105507 proquest_journals_2847957334 crossref_primary_10_1109_TPAMI_2023_3268066 |
| PublicationCentury | 2000 |
| PublicationDate | 2023-09-01 |
| PublicationDateYYYYMMDD | 2023-09-01 |
| PublicationDate_xml | – month: 09 year: 2023 text: 2023-09-01 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 | 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 | ref13 ref57 ref12 lee (ref23) 2019 ref15 ref59 ref58 liu (ref68) 2021 ref53 ref11 ref55 ref10 zhu (ref70) 2021 ref19 ref51 ref50 newell (ref81) 2017 ref46 ref45 ref48 ref47 law (ref14) 2018 ref42 ref86 ref85 ref44 ref88 ref43 lin (ref78) 2014 herzig (ref52) 2018 ref49 zhou (ref16) 2019 ref8 ref7 zeng (ref69) 2021 ref9 ref4 ref3 lu (ref41) 2021 ref6 ref5 ref40 ref84 ref83 ref80 ref35 ref79 ref34 ref37 carion (ref18) 2020 ref36 ref31 ref75 ref30 ref74 ref33 ref77 ref32 yao (ref71) 2021 menon (ref87) 2021 ref2 ref1 ref39 sun (ref17) 2021 ref38 vaswani (ref54) 2017 loshchilov (ref76) 2019 ref73 ref72 ref24 ref67 yuan (ref65) 2022 ref25 ref20 ref64 ref63 ref22 ref66 ref21 li (ref82) 2017 ref28 ref27 ref29 koner (ref56) 2020 li (ref26) 2019 yu (ref60) 2020 ref62 ref61 |
| References_xml | – ident: ref67 doi: 10.1109/CVPR46437.2021.00863 – ident: ref3 doi: 10.1109/ICCV48922.2021.00144 – start-page: 734 year: 2018 ident: ref14 article-title: Cornernet: Detecting objects as paired keypoints publication-title: Proc Eur Conf Comput Vis – ident: ref20 doi: 10.1007/s11263-020-01316-z – ident: ref9 doi: 10.1109/CVPR.2018.00611 – ident: ref80 doi: 10.1109/CVPR.2017.331 – ident: ref50 doi: 10.1109/CVPR46437.2021.01096 – ident: ref28 doi: 10.1109/CVPR.2008.4587799 – ident: ref85 doi: 10.1007/978-3-030-01219-9_20 – ident: ref30 doi: 10.1007/978-3-030-58565-5_38 – ident: ref25 doi: 10.1109/GC46384.2019.00015 – ident: ref63 doi: 10.1109/CVPR46437.2021.01138 – ident: ref79 doi: 10.1609/aaai.v33i01.33013159 – ident: ref75 doi: 10.1109/CVPR42600.2020.00377 – ident: ref46 doi: 10.1109/CVPR.2017.330 – year: 2021 ident: ref71 article-title: Efficient DETR: Improving end-to-end object detector with dense prior – ident: ref53 doi: 10.1109/CVPR.2019.00408 – ident: ref42 doi: 10.1109/CVPR46437.2021.01372 – ident: ref33 doi: 10.1109/ICCV48922.2021.01560 – year: 2022 ident: ref65 article-title: RLIP: Relational language-image pre-training for human-object interaction detection – ident: ref47 doi: 10.1109/ICCV.2017.142 – start-page: 3948 year: 2019 ident: ref26 article-title: PasteGAN: A semi-parametric method to generate image from scene graph publication-title: Proc Adv Neural Inf Process Syst – ident: ref66 doi: 10.1109/CVPR46437.2021.00014 – start-page: 2171 year: 2017 ident: ref81 article-title: Pixels to graphs by associative embedding publication-title: Proc Adv Neural Inf Process Syst – ident: ref57 doi: 10.1109/CVPR52688.2022.01890 – year: 2021 ident: ref68 article-title: CPTR: Full transformer network for image captioning – year: 2021 ident: ref87 article-title: Long-tail learning via logit adjustment publication-title: Proc Int Conf Learn Representations – year: 2019 ident: ref23 article-title: Learning visual relation priors for image-text matching and image captioning with neural scene graph generators – ident: ref12 doi: 10.1007/978-3-030-58592-1_36 – ident: ref15 doi: 10.1109/ICCV.2019.00972 – year: 2019 ident: ref76 article-title: Decoupled weight decay regularization publication-title: Proc Int Conf Learn Representations – ident: ref45 doi: 10.1109/ICCV48922.2021.01512 – ident: ref24 doi: 10.1109/CVPR.2019.00857 – ident: ref27 doi: 10.1109/ICIP.2019.8803182 – ident: ref2 doi: 10.1007/978-3-319-46448-0_51 – ident: ref38 doi: 10.1109/CVPR42600.2020.01025 – ident: ref29 doi: 10.1007/s11263-008-0140-x – start-page: 5998 year: 2017 ident: ref54 article-title: Attention is all you need publication-title: Proc Adv Neural Inf Process Syst – ident: ref51 doi: 10.1109/CVPR42600.2020.00380 – ident: ref72 doi: 10.1109/CVPR46437.2021.01165 – ident: ref84 doi: 10.1109/CVPR.2019.00527 – start-page: 7211 year: 2018 ident: ref52 article-title: Mapping images to scene graphs with permutation-invariant structured prediction publication-title: Proc Adv Neural Inf Process Syst – ident: ref86 doi: 10.1109/CVPR.2019.00550 – ident: ref21 doi: 10.1109/CVPR.2019.01094 – ident: ref11 doi: 10.1109/ICCV.2017.121 – ident: ref5 doi: 10.1109/ICCV.2017.325 – ident: ref83 doi: 10.1109/CVPR.2017.469 – ident: ref59 doi: 10.1145/3240508.3240668 – ident: ref34 doi: 10.1109/ICCV48922.2021.01563 – ident: ref44 doi: 10.1109/ICCV48922.2021.01607 – ident: ref74 doi: 10.1109/CVPR.2019.00075 – ident: ref31 doi: 10.1109/CVPR.2019.00838 – ident: ref13 doi: 10.1109/CVPR.2019.00207 – ident: ref8 doi: 10.1109/TPAMI.2016.2577031 – ident: ref49 doi: 10.1007/978-3-030-01246-5_21 – ident: ref88 doi: 10.1109/CVPR52688.2022.01883 – ident: ref61 doi: 10.1109/CVPR.2019.01180 – start-page: 740 year: 2014 ident: ref78 article-title: Microsoft COCO: Common objects in context publication-title: Proc Eur Conf Comput Vis – ident: ref40 doi: 10.1109/ICCV48922.2021.01343 – start-page: 213 year: 2020 ident: ref18 article-title: End-to-end object detection with transformers publication-title: Proc Eur Conf Comput Vis – ident: ref1 doi: 10.1109/CVPR.2015.7298990 – year: 2020 ident: ref56 article-title: Relation transformer network – year: 2017 ident: ref82 article-title: ViP-CNN: A visual phrase reasoning convolutional neural network for visual relationsip detection – ident: ref37 doi: 10.1145/3474085.3475297 – ident: ref36 doi: 10.1109/ICCV.2019.00471 – ident: ref39 doi: 10.1109/ICCV48922.2021.01606 – ident: ref55 doi: 10.1109/CVPRW53098.2021.00244 – start-page: 9934 year: 2021 ident: ref17 article-title: What makes for end-to-end object detection? publication-title: Proc Int Conf Mach Learn – ident: ref58 doi: 10.1109/ICCVW.2019.00218 – ident: ref10 doi: 10.1109/CVPR.2019.00632 – ident: ref48 doi: 10.1007/978-3-030-01246-5_41 – ident: ref4 doi: 10.1145/3195106.3195114 – ident: ref22 doi: 10.1109/ICCV.2019.01042 – year: 2020 ident: ref60 article-title: Cogtree: Cognition tree loss for unbiased scene graph generation – ident: ref32 doi: 10.1109/ICCV48922.2021.01608 – ident: ref6 doi: 10.1109/ICCV.2019.00466 – ident: ref7 doi: 10.1109/CVPR.2018.00133 – year: 2021 ident: ref70 article-title: Deformable DETR: Deformable transformers for end-to-end object detection publication-title: Proc Int Conf Learn Representations – ident: ref73 doi: 10.1109/CVPR.2016.255 – ident: ref43 doi: 10.1145/3394171.3413722 – ident: ref35 doi: 10.1109/CVPR.2019.00678 – year: 2019 ident: ref16 article-title: Objects as points – start-page: 1 year: 2021 ident: ref41 article-title: Multi-view scene graph generation in videos publication-title: Proc Int Challenge Activity Recognit Workshop – year: 2021 ident: ref69 article-title: MOTR: End-to-end multiple-object tracking with transformer – ident: ref62 doi: 10.1109/CVPR.2017.352 – ident: ref77 doi: 10.1109/CVPR.2009.5206848 – ident: ref64 doi: 10.1109/CVPR52688.2022.01888 – ident: ref19 doi: 10.1007/s11263-016-0981-7 |
| SSID | ssj0014503 |
| Score | 2.7020633 |
| Snippet | Different objects in the same scene are more or less related to each other, but only a limited number of these relationships are noteworthy. Inspired by... |
| SourceID | proquest pubmed crossref ieee |
| SourceType | Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 11169 |
| SubjectTerms | Coders Decoding Encoders-Decoders Object detection Object recognition One-stage Predictions Predictive models Proposals scene graph generation scene understanding Task analysis Transformers visual relationship detection Visualization |
| Title | RelTR: Relation Transformer for Scene Graph Generation |
| URI | https://ieeexplore.ieee.org/document/10105507 https://www.ncbi.nlm.nih.gov/pubmed/37074895 https://www.proquest.com/docview/2847957334 https://www.proquest.com/docview/2803331093 |
| Volume | 45 |
| WOSCitedRecordID | wos001045832200037&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: 2160-9292 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014503 issn: 0162-8828 databaseCode: RIE dateStart: 19790101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8NAEB60iNSD1fqKLyJ4k9Q0m-xmvYn4AhUpVXoLyWYCQmmlD3-_M5uk6KGCpwQymww7z83uzAdwTuaDMpbGy7UvPIpQkRdHWnrKGBVgnEpl4d7en9TLSzwY6NeqWN3WwiCiPXyGHb61e_n52Mz5VxlZOMM5cu34qlKqLNZabBmEkYVBphSGTJzWEXWFjK8v-6_Xz48dBgrvULYSU5RtwrpQPndeiX4FJIuwsjzZtEHnrvVPdrdgs8ou3etSHbZhBUdtaNXIDW5lyG3Y-NGGcAdkD4f93pVbH4xz-3U2S2PoQuPII7r33NvaLftUM9kuvN3d9m8evApPwTOUZs08JVQRY0juLTBSyAwFOeqIOESNhc5ClRUYIgkvpRhVSBMbFOT-Mi27uRZFJPagMRqP8ADc1E8xyKVIuyoPsyhIVernpqDFEwbGR-FAt57UxFTNxhnzYpjYRYevEyuThGWSVDJx4GIx5rNstfEn9S7P-A_KcrIdOK6Fl1TmOE04Bmvu_Bg6cLZ4TIbEuyPpCMdzpvGF4D6pxPx-KfTFy2tdOVzy0SNoMm_l2bNjaMwmczyBNfM1-5hOTklbB_Gp1dZvNd7gzQ |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3fS8MwED5EReeDP6dOp1bwTTq7pk0a30ScinOIVPGttOkVhLGJbv793qXt0AcFn1ropT1yudylyX0fwAm5D8pIGjfXnnApQoVuFGrpKmOUj1EqlaV7e-6rwSB6edEPVbG6rYVBRHv4DDt8a_fy87GZ8q8y8nCmc-Ta8YUwCPxuWa412zQIQkuETEkMOTmtJOoaGU-fxQ8X97cdpgrvUL4SUZxtwJJQHmOvhD9CkuVY-T3dtGGnt_ZPhddhtcovnYtyQGzAHI42Ya3mbnAqV96ElW9AhFsgH3EYP5479dE4J67zWWpDF2pHc6JzzejWTolUzWJNeOpdxZc3bsWo4BpKtCauEqqIMKAJzjdSyAwFTdUhaYgaC50FKiswQDJfSlGqkCYyKGgCzLTs5loUodiG-dF4hLvgpF6Kfi5F2lV5kIV-qlIvNwUtn9A3HooWdOtOTUwFN86sF8PELjs8nVibJGyTpLJJC05nbd5KsI0_pZvc498ky85uQbs2XlI55EfCUVgz9mPQguPZY3Il3h9JRziesownBCOlkvI7pdFnL6_Hyt4vHz2C5Zv4vp_0bwd3-9BgPcuTaG2Yn7xP8QAWzefk9eP90I7ZL8N54yw |
| 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=RelTR%3A+Relation+Transformer+for+Scene+Graph+Generation&rft.jtitle=IEEE+transactions+on+pattern+analysis+and+machine+intelligence&rft.au=Cong%2C+Yuren&rft.au=Yang%2C+Michael+Ying&rft.au=Rosenhahn%2C+Bodo&rft.date=2023-09-01&rft.pub=IEEE&rft.issn=0162-8828&rft.volume=45&rft.issue=9&rft.spage=11169&rft.epage=11183&rft_id=info:doi/10.1109%2FTPAMI.2023.3268066&rft_id=info%3Apmid%2F37074895&rft.externalDocID=10105507 |
| 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 |