{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T12:42:30Z","timestamp":1780576950708,"version":"3.54.1"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001700","name":"Ministry of Education, Culture, Sports, Science and Technology (MEXT), Japan, through Grants-in-Aid for Scientific Research","doi-asserted-by":"publisher","award":["JP21H03519"],"award-info":[{"award-number":["JP21H03519"]}],"id":[{"id":"10.13039\/501100001700","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001700","name":"Ministry of Education, Culture, Sports, Science and Technology (MEXT), Japan, through Grants-in-Aid for Scientific Research","doi-asserted-by":"publisher","award":["JP23K16945"],"award-info":[{"award-number":["JP23K16945"]}],"id":[{"id":"10.13039\/501100001700","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3332098","type":"journal-article","created":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T19:28:08Z","timestamp":1699903688000},"page":"128245-128260","source":"Crossref","is-referenced-by-count":17,"title":["An Approach to Generate a Caption for an Image Collection Using Scene Graph Generation"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1295-777X","authenticated-orcid":false,"given":"Itthisak","family":"Phueaksri","sequence":"first","affiliation":[{"name":"Graduate School of Informatics, Nagoya University, Nagoya, Aichi, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9193-5973","authenticated-orcid":false,"given":"Marc A.","family":"Kastner","sequence":"additional","affiliation":[{"name":"Graduate School of Informatics, Kyoto University, Kyoto, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3799-4550","authenticated-orcid":false,"given":"Yasutomo","family":"Kawanishi","sequence":"additional","affiliation":[{"name":"Graduate School of Informatics, Nagoya University, Nagoya, Aichi, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3041-4330","authenticated-orcid":false,"given":"Takahiro","family":"Komamizu","sequence":"additional","affiliation":[{"name":"Graduate School of Informatics, Nagoya University, Nagoya, Aichi, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3942-9296","authenticated-orcid":false,"given":"Ichiro","family":"Ide","sequence":"additional","affiliation":[{"name":"Graduate School of Informatics, Nagoya University, Nagoya, Aichi, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.488"},{"key":"ref2","article-title":"BLIP-2: Bootstrapping languageimage pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"arXiv:2301.12597"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-016-3840-1"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cvi.2017.0568"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3229654"},{"key":"ref6","article-title":"Multi-image summarization: Textual summary from a set of cohesive images","author":"Trieu","year":"2020","journal-title":"arXiv:2006.08686"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00097"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3031111"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-27077-2_14"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00611"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0255127"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d18-1443"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.211"},{"key":"ref15","first-page":"11328","article-title":"PEGASUS: Pre-training with extracted gap-sentences for abstractive summarization","volume-title":"Proc. ICML","author":"Zhang"},{"key":"ref16","first-page":"1","article-title":"Are scene graphs good enough to improve image captioning?","volume-title":"Proc. ACL-IJCNLP","author":"Milewski"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11164"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1101"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018909"},{"key":"ref21","article-title":"Image scene graph generation (SGG) benchmark","author":"Han","year":"2021","journal-title":"arXiv:2107.12604"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00144"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_13"},{"key":"ref25","article-title":"Image as a foreign language: BEiT pretraining for all vision and vision-language tasks","author":"Wang","year":"2022","journal-title":"arXiv:2208.10442"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref27","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"28","author":"Ren"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1126\/science.298.5594.824"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2_4"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01180"},{"key":"ref31","article-title":"GRCNN: Graph recognition convolutional neural network for synthesizing programs from flow charts","author":"Cheng","year":"2020","journal-title":"arXiv:2011.05980"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00377"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3268066"},{"issue":"140","key":"ref34","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.124"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2018.12.011"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.413"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.socnet.2007.11.001"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511815478"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3115\/1118108.1118117"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref45","first-page":"1","article-title":"VSE++: Improving visual-semantic embeddings with hard negatives","volume-title":"Proc. BMVC","author":"Faghri"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1222"},{"key":"ref49","first-page":"1","article-title":"BERTScore: Evaluating text generation with BERT","volume-title":"Proc. ICLR","author":"Zhang"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d19-1053"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.3390\/info11020078"},{"key":"ref52","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. ICLR","author":"Kingma"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref55","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Proc. ACL","author":"Lin"},{"key":"ref56","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. ACL Conf. NAACL HLT","author":"Devlin"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1023\/A:1026543900054"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2016.10.017"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10315005.pdf?arnumber=10315005","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T00:16:49Z","timestamp":1710375409000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10315005\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3332098","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}