{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T20:22:17Z","timestamp":1743106937517,"version":"3.40.3"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031510250"},{"type":"electronic","value":"9783031510267"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-51026-7_27","type":"book-chapter","created":{"date-parts":[[2024,1,20]],"date-time":"2024-01-20T14:02:08Z","timestamp":1705759328000},"page":"309-321","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Exploring the\u00a0Synergy Between Vision-Language Pretraining and\u00a0ChatGPT for\u00a0Artwork Captioning: A Preliminary Study"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6489-8628","authenticated-orcid":false,"given":"Giovanna","family":"Castellano","sequence":"first","affiliation":[]},{"given":"Nicola","family":"Fanelli","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7512-7661","authenticated-orcid":false,"given":"Raffaele","family":"Scaringi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0883-2691","authenticated-orcid":false,"given":"Gennaro","family":"Vessio","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,1,21]]},"reference":[{"key":"27_CR1","doi-asserted-by":"publisher","unstructured":"Aslan, S., Castellano, G., Digeno, V., Migailo, G., Scaringi, R., Vessio, G.: Recognizing the emotions evoked by artworks through visual features and knowledge graph-embeddings. In: Mazzeo, P.L., Frontoni, E., Sclaroff, S., Distante, C. (eds.) Image Analysis and Processing. ICIAP 2022. LNCS, vol. 13373, pp. 129\u2013140. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-13321-3_12","DOI":"10.1007\/978-3-031-13321-3_12"},{"key":"27_CR2","doi-asserted-by":"crossref","unstructured":"Bai, Z., Nakashima, Y., Garcia, N.: Explain me the painting: multi-topic knowledgeable art description generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5422\u20135432 (2021)","DOI":"10.1109\/ICCV48922.2021.00537"},{"key":"27_CR3","doi-asserted-by":"crossref","unstructured":"Becattini, F., et al.: VISCOUNTH: a large-scale multilingual visual question answering dataset for cultural heritage. ACM Trans. Multim. Comput. Commun. Appl. (2023). Just Accepted","DOI":"10.1145\/3590773"},{"key":"27_CR4","doi-asserted-by":"publisher","unstructured":"Bongini, P., Becattini, F., Del Bimbo, A.: Is GPT-3 all you need for visual question answering in cultural heritage? In: Karlinsky, L., Michaeli, T., Nishino, K. (eds.) ECCV 2022. LNCS, vol. 13801, pp. 268\u2013281. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-25056-9_18","DOI":"10.1007\/978-3-031-25056-9_18"},{"key":"27_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108859","volume":"248","author":"G Castellano","year":"2022","unstructured":"Castellano, G., Digeno, V., Sansaro, G., Vessio, G.: Leveraging knowledge graphs and deep learning for automatic art analysis. Knowl.-Based Syst. 248, 108859 (2022)","journal-title":"Knowl.-Based Syst."},{"issue":"19","key":"27_CR6","doi-asserted-by":"publisher","first-page":"12263","DOI":"10.1007\/s00521-021-05893-z","volume":"33","author":"G Castellano","year":"2021","unstructured":"Castellano, G., Vessio, G.: Deep learning approaches to pattern extraction and recognition in paintings and drawings: an overview. Neural Comput. Appl. 33(19), 12263\u201312282 (2021)","journal-title":"Neural Comput. Appl."},{"issue":"8","key":"27_CR7","doi-asserted-by":"publisher","first-page":"123","DOI":"10.3390\/jimaging7080123","volume":"7","author":"E Cetinic","year":"2021","unstructured":"Cetinic, E.: Towards generating and evaluating iconographic image captions of artworks. J. Imaging 7(8), 123 (2021)","journal-title":"J. Imaging"},{"key":"27_CR8","doi-asserted-by":"crossref","unstructured":"Chen, D., Fisch, A., Weston, J., Bordes, A.: Reading Wikipedia to answer open-domain questions. arXiv preprint arXiv:1704.00051 (2017)","DOI":"10.18653\/v1\/P17-1171"},{"key":"27_CR9","doi-asserted-by":"crossref","unstructured":"Cornia, M., Stefanini, M., Baraldi, L., Cucchiara, R.: Meshed-memory transformer for image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10578\u201310587 (2020)","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"27_CR10","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"27_CR11","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"27_CR12","doi-asserted-by":"crossref","unstructured":"Fang, Z., et al.: Injecting semantic concepts into end-to-end image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18009\u201318019 (2022)","DOI":"10.1109\/CVPR52688.2022.01748"},{"key":"27_CR13","doi-asserted-by":"crossref","unstructured":"Garcia, N., Vogiatzis, G.: How to read paintings: semantic art understanding with multi-modal retrieval. In: Proceedings of the European Conference on Computer Vision (ECCV) Workshops (2018)","DOI":"10.1007\/978-3-030-11012-3_52"},{"key":"27_CR14","unstructured":"Herdade, S., Kappeler, A., Boakye, K., Soares, J.: Image captioning: transforming objects into words. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"27_CR15","doi-asserted-by":"crossref","unstructured":"Hessel, J., Holtzman, A., Forbes, M., Bras, R.L., Choi, Y.: CLIPScore: a reference-free evaluation metric for image captioning. arXiv preprint arXiv:2104.08718 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"27_CR16","doi-asserted-by":"publisher","first-page":"24527","DOI":"10.1109\/ACCESS.2023.3255887","volume":"11","author":"S Ishikawa","year":"2023","unstructured":"Ishikawa, S., Sugiura, K.: Affective image captioning for visual artworks using emotion-based cross-attention mechanisms. IEEE Access 11, 24527\u201324534 (2023)","journal-title":"IEEE Access"},{"key":"27_CR17","doi-asserted-by":"crossref","unstructured":"Kendall, A., Gal, Y., Cipolla, R.: Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7482\u20137491 (2018)","DOI":"10.1109\/CVPR.2018.00781"},{"key":"27_CR18","doi-asserted-by":"crossref","unstructured":"Lita, L.V., Ittycheriah, A., Roukos, S., Kambhatla, N.: tRuEcasIng. In: Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics, pp. 152\u2013159. Association for Computational Linguistics, Sapporo (2003)","DOI":"10.3115\/1075096.1075116"},{"key":"27_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.101811","volume":"97","author":"F Liu","year":"2023","unstructured":"Liu, F., Zhang, M., Zheng, B., Cui, S., Ma, W., Liu, Z.: Feature fusion via multi-target learning for ancient artwork captioning. Inf. Fusion 97, 101811 (2023)","journal-title":"Inf. Fusion"},{"key":"27_CR20","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1016\/j.neucom.2022.01.068","volume":"490","author":"Y Lu","year":"2022","unstructured":"Lu, Y., Guo, C., Dai, X., Wang, F.Y.: Data-efficient image captioning of fine art paintings via virtual-real semantic alignment training. Neurocomputing 490, 163\u2013180 (2022)","journal-title":"Neurocomputing"},{"key":"27_CR21","unstructured":"OpenAI: ChatGPT (2023). https:\/\/openai.com, version 3.5"},{"key":"27_CR22","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"27_CR23","doi-asserted-by":"publisher","unstructured":"Ruta, D., et al.: StyleBabel: artistic style tagging and captioning. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13668, pp. 219\u2013236. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20074-8_13","DOI":"10.1007\/978-3-031-20074-8_13"},{"key":"27_CR24","unstructured":"Schuhmann, C., et al.: LAION-400M: open dataset of CLIP-filtered 400 million image-text pairs. arXiv preprint arXiv:2111.02114 (2021)"},{"key":"27_CR25","doi-asserted-by":"crossref","unstructured":"Sheng, S., Moens, M.F.: Generating captions for images of ancient artworks. In: Proceedings of the 27th ACM International Conference on Multimedia (MM 2019), pp. 2478\u20132486. Association for Computing Machinery, New York (2019)","DOI":"10.1145\/3343031.3350972"},{"issue":"1","key":"27_CR26","doi-asserted-by":"publisher","first-page":"2104333","DOI":"10.1080\/23311916.2022.2104333","volume":"9","author":"U Sirisha","year":"2022","unstructured":"Sirisha, U., Chandana, B.S.: Semantic interdisciplinary evaluation of image captioning models. Cogent Eng. 9(1), 2104333 (2022)","journal-title":"Cogent Eng."},{"key":"27_CR27","doi-asserted-by":"publisher","unstructured":"Stefanini, M., Cornia, M., Baraldi, L., Corsini, M., Cucchiara, R.: Artpedia: a new visual-semantic dataset with visual and contextual sentences in the artistic domain. In: Ricci, E., Rota Bul\u00f2, S., Snoek, C., Lanz, O., Messelodi, S., Sebe, N. (eds.) Image Analysis and Processing - ICIAP 2019. LNCS, vol. 11752, pp. 729\u2013740. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-30645-8_66","DOI":"10.1007\/978-3-030-30645-8_66"},{"key":"27_CR28","unstructured":"Tiedemann, J., Thottingal, S.: OPUS-MT - building open translation services for the world. In: Proceedings of the 22nd Annual Conferenec of the European Association for Machine Translation (EAMT), Lisbon (2020)"},{"key":"27_CR29","doi-asserted-by":"crossref","unstructured":"Turkerud, I.R., Mengshoel, O.J.: Image captioning using deep learning: text augmentation by paraphrasing via backtranslation. In: 2021 IEEE Symposium Series on Computational Intelligence (SSCI), pp. 01\u201310 (2021)","DOI":"10.1109\/SSCI50451.2021.9659834"},{"key":"27_CR30","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"27_CR31","unstructured":"Wang, J., et al.: GIT: a generative image-to-text transformer for vision and language. arXiv preprint arXiv:2205.14100 (2022)"}],"container-title":["Lecture Notes in Computer Science","Image Analysis and Processing - ICIAP 2023 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-51026-7_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,8]],"date-time":"2024-11-08T18:07:48Z","timestamp":1731089268000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-51026-7_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031510250","9783031510267"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-51026-7_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"21 January 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIAP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Image Analysis and Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Udine","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"11 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iciap2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.iciap2023.org\/","order":11,"name":"conference_url","label":"Conference URL","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"144","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":"82","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":"13","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":"57% - 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":"3","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"https:\/\/iciap2023.org\/satellite-event\/workshops\/","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}