{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T23:21:29Z","timestamp":1742944889340,"version":"3.40.3"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031270765"},{"type":"electronic","value":"9783031270772"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-27077-2_14","type":"book-chapter","created":{"date-parts":[[2023,3,28]],"date-time":"2023-03-28T05:03:10Z","timestamp":1679979790000},"page":"178-190","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Towards Captioning an\u00a0Image Collection from\u00a0a\u00a0Combined Scene Graph Representation Approach"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1295-777X","authenticated-orcid":false,"given":"Itthisak","family":"Phueaksri","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9193-5973","authenticated-orcid":false,"given":"Marc A.","family":"Kastner","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3799-4550","authenticated-orcid":false,"given":"Yasutomo","family":"Kawanishi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3041-4330","authenticated-orcid":false,"given":"Takahiro","family":"Komamizu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3942-9296","authenticated-orcid":false,"given":"Ichiro","family":"Ide","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,3,29]]},"reference":[{"issue":"7","key":"14_CR1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0255127","volume":"16","author":"H Alrasheed","year":"2021","unstructured":"Alrasheed, H.: Word synonym relationships for text analysis: a graph-based approach. PLoS ONE 16(7), e0255127 (2021)","journal-title":"PLoS ONE"},{"key":"14_CR2","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition, pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"Deng, J., et al.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"14_CR4","unstructured":"Faghri, F., et al.: VSE++: improving visual-semantic embeddings with hard negatives. In: 29th British Machine Vision Conference (2018)"},{"key":"14_CR5","doi-asserted-by":"crossref","unstructured":"Gao, Y., et al.: SUPERT: Towards new frontiers in unsupervised evaluation metrics for multi-document summarization. In: 58th Annual Meeting of the Association for Computational Linguistics, pp. 1347\u20131354 (2020)","DOI":"10.18653\/v1\/2020.acl-main.124"},{"key":"14_CR6","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: 16th IEEE International Conference on Computer Vision, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"14_CR7","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1016\/j.eswa.2018.12.011","volume":"121","author":"S Gupta","year":"2019","unstructured":"Gupta, S., et al.: Abstractive summarization: an overview of the state of the art. Expert Syst. Appl. 121, 49\u201365 (2019)","journal-title":"Expert Syst. Appl."},{"issue":"2","key":"14_CR8","doi-asserted-by":"publisher","first-page":"78","DOI":"10.3390\/info11020078","volume":"11","author":"TT Hailu","year":"2020","unstructured":"Hailu, T.T., et al.: A framework for word embedding based automatic text summarization and evaluation. Information 11(2), 78\u2013100 (2020)","journal-title":"Information"},{"key":"14_CR9","unstructured":"Han, X., et al.: Image scene graph generation (SGG) benchmark. Comput. Res. Reposit. arXiv preprint arXiv:2107.12604 (2021)"},{"key":"14_CR10","doi-asserted-by":"crossref","unstructured":"Hasan, T., et al.: XL-Sum: large-scale multilingual abstractive summarization for 44 languages. In: Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pp. 4693\u20134703 (2021)","DOI":"10.18653\/v1\/2021.findings-acl.413"},{"key":"14_CR11","doi-asserted-by":"crossref","unstructured":"He, K., et al.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"6","key":"14_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3295748","volume":"51","author":"MZ Hossain","year":"2019","unstructured":"Hossain, M.Z., et al.: A comprehensive survey of deep learning for image captioning. ACM Comput. Survey 51(6), 1\u201336 (2019)","journal-title":"ACM Comput. Survey"},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"Karpathy, A., et al.: Deep visual-semantic alignments for generating image descriptions. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3128\u20133137 (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"14_CR14","unstructured":"Kingma, D.P., et al.: Adam: a method for stochastic optimization. In: 3rd International Conference on Learning Representations (2014)"},{"issue":"1","key":"14_CR15","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vis. 123(1), 32\u201373 (2017)","journal-title":"Int. J. Comput. Vis."},{"key":"14_CR16","unstructured":"Lin, C.Y.: ROUGE: a package for automatic evaluation of summaries. In: ACL-04 Workshop on Text Summarization Branches Out, pp. 74\u201381 (2004)"},{"key":"14_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"14_CR18","doi-asserted-by":"crossref","unstructured":"Loper, E., et al.: NLTK: the natural language toolkit. In: 42nd Annual Meeting of the Association for Computational Linguistics, vol. 1, pp. 63\u201370 (2002)","DOI":"10.3115\/1118108.1118117"},{"key":"14_CR19","unstructured":"Milewski, V., et al.: Are scene graphs good enough to improve image captioning? In: Joint Conference 59th Annual Meeting of the Association for Computational Linguistics and 11th International Conference on Natural Language Processing (2020)"},{"key":"14_CR20","doi-asserted-by":"crossref","unstructured":"Pennington, J., et al.: GloVe: global vectors for word representation. In: 2014 Conference on Empirical Methods in Natural Language Processing, pp. 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"},{"issue":"140","key":"14_CR21","first-page":"1","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(140), 1\u201367 (2020)","journal-title":"J. Mach. Learn. Res."},{"issue":"9","key":"14_CR22","doi-asserted-by":"publisher","first-page":"11917","DOI":"10.1007\/s11042-016-3840-1","volume":"76","author":"ZR Samani","year":"2017","unstructured":"Samani, Z.R., et al.: A knowledge-based semantic approach for image collection summarization. Multimed. Tools Appl. 76(9), 11917\u201311939 (2017)","journal-title":"Multimed. Tools Appl."},{"key":"14_CR23","doi-asserted-by":"crossref","unstructured":"Speer, R., et al.: ConceptNet 5.5: an open multilingual graph of general knowledge. In: 31st AAAI Conference on Artificial Intelligence, pp. 4444\u20134451 (2017)","DOI":"10.1609\/aaai.v31i1.11164"},{"key":"14_CR24","unstructured":"Trieu, N., et al.: Multi-image summarization: textual summary from a set of cohesive images. Comput. Res. Reposit. arXiv preprint arXiv:2006.08686 (2020)"},{"key":"14_CR25","doi-asserted-by":"crossref","unstructured":"Vedantam, R., et al.: CIDEr: consensus-based image description evaluation. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition, pp. 4566\u20134575 (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"14_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"370","DOI":"10.1007\/978-3-030-58452-8_22","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Wang","year":"2020","unstructured":"Wang, J., Xu, W., Wang, Q., Chan, A.B.: Compare and reweight: distinctive image captioning using similar images sets. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 370\u2013386. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_22"},{"key":"14_CR27","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Image as a foreign language: BEiT pretraining for all vision and vision-language tasks. Compt. Res. Reposit. arXiv preprint arXiv:2208.10442 (2022)","DOI":"10.1109\/CVPR52729.2023.01838"},{"key":"14_CR28","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511815478","volume-title":"Social Network Analysis: Methods and Applications","author":"S Wasserman","year":"1994","unstructured":"Wasserman, S., et al.: Social Network Analysis: Methods and Applications, vol. 8. Cambridge University Press, Cambridge (1994)"},{"key":"14_CR29","doi-asserted-by":"crossref","unstructured":"Zellers, R., et al.: Neural motifs: scene graph parsing with global context. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition, pp. 5831\u20135840 (2018)","DOI":"10.1109\/CVPR.2018.00611"},{"key":"14_CR30","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: Graphical contrastive losses for scene graph parsing. In: 2019 IEEE Conference on Computer Vision and Pattern Recognition, pp. 11535\u201311543 (2019)","DOI":"10.1109\/CVPR.2019.01180"},{"key":"14_CR31","unstructured":"Zhang, T., et al.: BERTScore: evaluating text generation with BERT. In: 9th International Conference on Learning Representations (2020)"},{"issue":"2","key":"14_CR32","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1049\/iet-cvi.2017.0568","volume":"13","author":"W Zhang","year":"2019","unstructured":"Zhang, W., et al.: Joint optimisation convex-negative matrix factorisation for multi-modal image collection summarisation based on images and tags. IET Comput. Vis. 13(2), 125\u2013130 (2019)","journal-title":"IET Comput. Vis."},{"key":"14_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/978-3-030-58568-6_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Zhong","year":"2020","unstructured":"Zhong, Y., Wang, L., Chen, J., Yu, D., Li, Y.: Comprehensive image captioning via scene graph decomposition. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 211\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58568-6_13"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-27077-2_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,9]],"date-time":"2023-12-09T19:17:47Z","timestamp":1702149467000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-27077-2_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031270765","9783031270772"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-27077-2_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"29 March 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bergen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Norway","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 January 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 January 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Conftool Pro","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"267","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"86","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"32% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}