{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:48:27Z","timestamp":1775580507894,"version":"3.50.1"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030306441","type":"print"},{"value":"9783030306458","type":"electronic"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"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":[[2019]]},"DOI":"10.1007\/978-3-030-30645-8_66","type":"book-chapter","created":{"date-parts":[[2019,9,4]],"date-time":"2019-09-04T08:06:57Z","timestamp":1567584417000},"page":"729-740","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":35,"title":["Artpedia: A New Visual-Semantic Dataset with Visual and Contextual Sentences in the Artistic Domain"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6153-926X","authenticated-orcid":false,"given":"Matteo","family":"Stefanini","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9640-9385","authenticated-orcid":false,"given":"Marcella","family":"Cornia","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5125-4957","authenticated-orcid":false,"given":"Lorenzo","family":"Baraldi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0543-1638","authenticated-orcid":false,"given":"Massimiliano","family":"Corsini","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2239-283X","authenticated-orcid":false,"given":"Rita","family":"Cucchiara","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,9,2]]},"reference":[{"key":"66_CR1","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"66_CR2","doi-asserted-by":"crossref","unstructured":"Baraldi, L., Cornia, M., Grana, C., Cucchiara, R.: Aligning text and document illustrations: towards visually explainable digital humanities. In: ICPR (2018)","DOI":"10.1109\/ICPR.2018.8545064"},{"key":"66_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"625","DOI":"10.1007\/978-3-030-11024-6_47","volume-title":"Computer Vision \u2013 ECCV 2018 Workshops","author":"A Carraggi","year":"2019","unstructured":"Carraggi, A., Cornia, M., Baraldi, L., Cucchiara, R.: Visual-semantic alignment across domains using a semi-supervised approach. In: Leal-Taix\u00e9, L., Roth, S. (eds.) ECCV 2018. LNCS, vol. 11134, pp. 625\u2013640. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-11024-6_47"},{"key":"66_CR4","unstructured":"Chorowski, J.K., Bahdanau, D., Serdyuk, D., Cho, K., Bengio, Y.: Attention-based models for speech recognition. In: NeurIPS (2015)"},{"key":"66_CR5","doi-asserted-by":"crossref","unstructured":"Cornia, M., Baraldi, L., Cucchiara, R.: Show, control and tell: a framework for generating controllable and grounded captions. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00850"},{"key":"66_CR6","doi-asserted-by":"crossref","unstructured":"Engilberge, M., Chevallier, L., P\u00e9rez, P., Cord, M.: Finding beans in burgers: deep semantic-visual embedding with localization. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00419"},{"key":"66_CR7","unstructured":"Faghri, F., Fleet, D.J., Kiros, J.R., Fidler, S.: VSE++: improving visual-semantic embeddings with hard negatives. In: BMVC (2018)"},{"key":"66_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"676","DOI":"10.1007\/978-3-030-11012-3_52","volume-title":"Computer Vision \u2013 ECCV 2018 Workshops","author":"N Garcia","year":"2019","unstructured":"Garcia, N., Vogiatzis, G.: How to read paintings: semantic art understanding with multi-modal retrieval. In: Leal-Taix\u00e9, L., Roth, S. (eds.) ECCV 2018. LNCS, vol. 11130, pp. 676\u2013691. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-11012-3_52"},{"key":"66_CR9","doi-asserted-by":"crossref","unstructured":"Gatys, L.A., Ecker, A.S., Bethge, M.: Image style transfer using convolutional neural networks. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.265"},{"key":"66_CR10","doi-asserted-by":"crossref","unstructured":"Gu, J., Cai, J., Joty, S.R., Niu, L., Wang, G.: Look, imagine and match: improving textual-visual cross-modal retrieval with generative models. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00750"},{"key":"66_CR11","doi-asserted-by":"crossref","unstructured":"Huang, Y., Wu, Q., Song, C., Wang, L.: Learning semantic concepts and order for image and sentence matching. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00645"},{"key":"66_CR12","doi-asserted-by":"crossref","unstructured":"Karayev, S., et al.: Recognizing image style. In: BMVC (2014)","DOI":"10.5244\/C.28.122"},{"key":"66_CR13","unstructured":"Kiros, R., Salakhutdinov, R., Zemel, R.S.: Unifying visual-semantic embeddings with multimodal neural language models. In: NeurIPS Workshops (2014)"},{"issue":"1","key":"66_CR14","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. Vision 123(1), 32\u201373 (2017)","journal-title":"Int. J. Comput. Vision"},{"key":"66_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1007\/978-3-030-01225-0_13","volume-title":"Computer Vision \u2013 ECCV 2018","author":"K-H Lee","year":"2018","unstructured":"Lee, K.-H., Chen, X., Hua, G., Hu, H., He, X.: Stacked cross attention for image-text matching. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 212\u2013228. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01225-0_13"},{"key":"66_CR16","doi-asserted-by":"crossref","unstructured":"Lu, J., Yang, J., Batra, D., Parikh, D.: Neural baby talk. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00754"},{"issue":"Nov","key":"66_CR17","first-page":"2579","volume":"9","author":"L Van der Maaten","year":"2008","unstructured":"Van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(Nov), 2579\u20132605 (2008)","journal-title":"J. Mach. Learn. Res."},{"key":"66_CR18","doi-asserted-by":"crossref","unstructured":"Mao, H., Cheung, M., She, J.: DeepArt: learning joint representations of visual arts. In: ACM Multimedia (2017)","DOI":"10.1145\/3123266.3123405"},{"key":"66_CR19","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.: Glove: global vectors for word representation. In: EMNLP (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"66_CR20","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NeurIPS (2015)"},{"key":"66_CR21","doi-asserted-by":"crossref","unstructured":"Shen, X., Efros, A.A., Mathieu, A.: Discovering visual patterns in art collections with spatially-consistent feature learning. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00950"},{"key":"66_CR22","unstructured":"Tolias, G., Sicre, R., J\u00e9gou, H.: Particular object retrieval with integral max-pooling of CNN activations. In: ICLR (2016)"},{"key":"66_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"601","DOI":"10.1007\/978-3-030-11012-3_46","volume-title":"Computer Vision \u2013 ECCV 2018 Workshops","author":"M Tomei","year":"2019","unstructured":"Tomei, M., Baraldi, L., Cornia, M., Cucchiara, R.: What was Monet seeing while painting? Translating artworks to photo-realistic images. In: Leal-Taix\u00e9, L., Roth, S. (eds.) ECCV 2018. LNCS, vol. 11130, pp. 601\u2013616. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-11012-3_46"},{"key":"66_CR24","doi-asserted-by":"crossref","unstructured":"Tomei, M., Cornia, M., Baraldi, L., Cucchiara, R.: Art2Real: unfolding the reality of artworks via semantically-aware image-to-image translation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00600"},{"key":"66_CR25","doi-asserted-by":"crossref","unstructured":"Xu, T., et al.: AttnGAN: fine-grained text to image generation with attentional generative adversarial networks. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00143"}],"container-title":["Lecture Notes in Computer Science","Image Analysis and Processing \u2013 ICIAP 2019"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-30645-8_66","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T00:09:28Z","timestamp":1693786168000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-30645-8_66"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030306441","9783030306458"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-30645-8_66","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"2 September 2019","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":"Trento","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":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 September 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 September 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iciap2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/event.unitn.it\/iciap2019\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-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":"207","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":"117","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":"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":"2.6","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)"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}