{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,25]],"date-time":"2025-11-25T20:42:31Z","timestamp":1764103351342,"version":"3.40.3"},"publisher-location":"Cham","reference-count":57,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031200731"},{"type":"electronic","value":"9783031200748"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20074-8_13","type":"book-chapter","created":{"date-parts":[[2022,11,11]],"date-time":"2022-11-11T20:23:11Z","timestamp":1668198191000},"page":"219-236","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["StyleBabel: Artistic Style Tagging and\u00a0Captioning"],"prefix":"10.1007","author":[{"given":"Dan","family":"Ruta","sequence":"first","affiliation":[]},{"given":"Andrew","family":"Gilbert","sequence":"additional","affiliation":[]},{"given":"Pranav","family":"Aggarwal","sequence":"additional","affiliation":[]},{"given":"Naveen","family":"Marri","sequence":"additional","affiliation":[]},{"given":"Ajinkya","family":"Kale","sequence":"additional","affiliation":[]},{"given":"Jo","family":"Briggs","sequence":"additional","affiliation":[]},{"given":"Chris","family":"Speed","sequence":"additional","affiliation":[]},{"given":"Hailin","family":"Jin","sequence":"additional","affiliation":[]},{"given":"Baldo","family":"Faieta","sequence":"additional","affiliation":[]},{"given":"Alex","family":"Filipkowski","sequence":"additional","affiliation":[]},{"given":"Zhe","family":"Lin","sequence":"additional","affiliation":[]},{"given":"John","family":"Collomosse","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,11,12]]},"reference":[{"key":"13_CR1","doi-asserted-by":"crossref","unstructured":"von Ahn, L., Dabbish, L.A.: ESP: labeling images with a computer game, pp. 91\u201398 (2005)","DOI":"10.1145\/985692.985733"},{"key":"13_CR2","doi-asserted-by":"crossref","unstructured":"Achlioptas, P., Ovsjanikov, M., Haydarov, K., Elhoseiny, M., Guibas, L.: Artemis: affective language for visual art. In: Proceedings of CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01140"},{"key":"13_CR3","doi-asserted-by":"crossref","unstructured":"Bai, Z., Nakashima, Y., Garcia, N.: Explain me the painting: multi-topic knowledgeable art description generation. CoRR, arXiv:2109.05743 (2021)","DOI":"10.1109\/ICCV48922.2021.00537"},{"key":"13_CR4","doi-asserted-by":"crossref","unstructured":"Bell, S., Bala, K.: Learning visual similarity for product design with convolutional neural networks. In: Proceedings of ACM SIGGRAPH (2015)","DOI":"10.1145\/2766959"},{"key":"13_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1007\/978-3-319-48680-2_11","volume-title":"Advanced Concepts for Intelligent Vision Systems","author":"S Bianco","year":"2016","unstructured":"Bianco, S., Celona, L., Napoletano, P., Schettini, R.: Predicting image aesthetics with deep learning. In: Blanc-Talon, J., Distante, C., Philips, W., Popescu, D., Scheunders, P. (eds.) ACIVS 2016. LNCS, vol. 10016, pp. 117\u2013125. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-48680-2_11"},{"key":"13_CR6","volume-title":"Constructing Grounded Theory: A Practical Guide through Qualitative Analysis","author":"C Kathy","year":"2006","unstructured":"Kathy, C.: Constructing Grounded Theory: A Practical Guide through Qualitative Analysis. Sage, London (2006)"},{"key":"13_CR7","unstructured":"Cetinic, E., Grgic, S.: Automated painter recognition based on image feature extraction. In: Proceedings of ELMAR (2013)"},{"key":"13_CR8","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. arXiv preprint arXiv:2002.05709 (2020)"},{"key":"13_CR9","doi-asserted-by":"crossref","unstructured":"Collomosse, J., Bui, T., Wilber, M., Fang, C., Jin, H.: Sketching with style: visual search with sketches and aesthetic context. In: Proceedings of ICCV (2017)","DOI":"10.1109\/ICCV.2017.290"},{"key":"13_CR10","doi-asserted-by":"crossref","unstructured":"Cornia, M., Stefanini, M., Baraldi, L., Cucchiara, R.: Meshed-memory transformer for image captioning. arXiv preprint arXiv:1912.08226 (2020)","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"13_CR11","doi-asserted-by":"crossref","unstructured":"Desai, K., Johnson, J.: Virtex: learning visual representations from textual annotations. CoRR, arXiv:2006.06666 (2020)","DOI":"10.1109\/CVPR46437.2021.01101"},{"key":"13_CR12","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"13_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1007\/978-3-642-15561-1_2","volume-title":"Computer Vision \u2013 ECCV 2010","author":"A Farhadi","year":"2010","unstructured":"Farhadi, A., et al.: Every picture tells a story: generating sentences from images. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6314, pp. 15\u201329. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-15561-1_2"},{"key":"13_CR14","volume-title":"Art History and its Methods: A Critical Anthology","author":"F Eric","year":"1995","unstructured":"Eric, F.: Art History and its Methods: A Critical Anthology. Phaidon, London (1995)"},{"key":"13_CR15","doi-asserted-by":"crossref","unstructured":"Fellbaum, C.: WordNet: An Electronic Lexical Database. Bradford Books (1998)","DOI":"10.7551\/mitpress\/7287.001.0001"},{"key":"13_CR16","doi-asserted-by":"crossref","unstructured":"Garcia, N., Vogiatzis, G.: How to read paintings: semantic art understanding with multi-modal retrieval. CoRR, arXiv:1810.09617 (2018)","DOI":"10.1007\/978-3-030-11012-3_52"},{"key":"13_CR17","doi-asserted-by":"crossref","unstructured":"Gatys, L.A., Ecker, A.S., Bethge, M.: A neural algorithm of artistic style. arXiv preprint arXiv:1508.06576 (2015)","DOI":"10.1167\/16.12.326"},{"key":"13_CR18","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., Lee, H., Kudlur, M., Dumoulin, V., Shlens, J.: Exploring the structure of a real-time, arbitrary neural artistic stylization network. arXiv preprint arXiv:1705.06830 (2017)","DOI":"10.5244\/C.31.114"},{"key":"13_CR19","doi-asserted-by":"crossref","unstructured":"Ghosal, K., Rana, A., Smolic, A.: Aesthetic image captioning from weakly-labelled photographs. CoRR, arXiv:1908.11310 (2019)","DOI":"10.1109\/ICCVW.2019.00556"},{"key":"13_CR20","doi-asserted-by":"crossref","unstructured":"Huang, L., Wang, W., Chen, J., Wei, X.: Attention on attention for image captioning. CoRR, arXiv:1908.06954 (2019)","DOI":"10.1109\/ICCV.2019.00473"},{"key":"13_CR21","doi-asserted-by":"crossref","unstructured":"Huang, X., Belongie, S.: Arbitrary style transfer in real-time with adaptive instance normalization. In: Proceedings of ICCV (2017)","DOI":"10.1109\/ICCV.2017.167"},{"key":"13_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1007\/978-3-030-01219-9_11","volume-title":"Computer Vision \u2013 ECCV 2018","author":"X Huang","year":"2018","unstructured":"Huang, X., Liu, M.-Y., Belongie, S., Kautz, J.: Multimodal unsupervised image-to-image translation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 179\u2013196. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01219-9_11"},{"key":"13_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"694","DOI":"10.1007\/978-3-319-46475-6_43","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J Johnson","year":"2016","unstructured":"Johnson, J., Alahi, A., Fei-Fei, L.: Perceptual losses for real-time style transfer and super-resolution. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 694\u2013711. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_43"},{"key":"13_CR24","doi-asserted-by":"crossref","unstructured":"Karayev, S., et al.: Recognizing image style. In: Proceedings of BMVC (2014)","DOI":"10.5244\/C.28.122"},{"issue":"12","key":"13_CR25","doi-asserted-by":"publisher","first-page":"2891","DOI":"10.1109\/TPAMI.2012.162","volume":"35","author":"G Kulkarni","year":"2013","unstructured":"Kulkarni, G., et al.: Babytalk: understanding and generating simple image descriptions. IEEE Trans. Pattern Anal. Mach. Intell. 35(12), 2891\u20132903 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"13_CR26","doi-asserted-by":"crossref","unstructured":"Lavie, A., Agarwal, A.: Meteor: an automatic metric for MT evaluation with high levels of correlation with human judgments, pp. 228\u2013231 (2007)","DOI":"10.3115\/1626355.1626389"},{"key":"13_CR27","unstructured":"Xu, L., Mero\u00f1o-Pe\u00f1uela, A., Huang, Z., Harmelen, F.V.: An ontology model for narrative image annotation in the field of cultural heritage. In: WHiSe@ISWC (2017)"},{"key":"13_CR28","doi-asserted-by":"crossref","unstructured":"Li, X., et al.: Oscar: object-semantics aligned pre-training for vision-language tasks. arXiv preprint arXiv:2004.06165 (2020)","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"13_CR29","unstructured":"Li, Y., Fang, C., Yang, J., Wang, Z., Lu, X., Yang, M.: Universal style transfer via feature transforms. In: Proceedings of NIPS (2017)"},{"key":"13_CR30","unstructured":"Lin, C.-Y.: Rouge: a package for automatic evaluation of summaries, p. 10 (2004)"},{"key":"13_CR31","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. CoRR, arXiv:1405.0312 (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"13_CR32","doi-asserted-by":"crossref","unstructured":"Pang, K., Yang, Y., Hospedales, T.M., Xiang, T., Song, Y.: Solving mixed-modal jigsaw puzzle for fine-grained sketch-based image retrieval. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Los Alamitos, CA, USA, pp. 10344\u201310352. IEEE Computer Society (2020)","DOI":"10.1109\/CVPR42600.2020.01036"},{"key":"13_CR33","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.-J.: Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, USA, ACL 2002, pp. 311\u2013318. Association for Computational Linguistics (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"13_CR34","unstructured":"Park, T., et al.: Swapping autoencoder for deep image manipulation. In: Proceedings of ECCV (2020)"},{"key":"13_CR35","doi-asserted-by":"crossref","unstructured":"Pinotti, A.: Formalism and the History of Style, pp. 75\u201390. Brill, Leiden (2012)","DOI":"10.1163\/9789004231702_007"},{"key":"13_CR36","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. arXiv preprint arXiv:2103.00020 (2021)"},{"key":"13_CR37","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generatio. arXiv preprint arXiv:2102.12092 (2021)"},{"key":"13_CR38","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. arXiv preprint arXiv:2102.12092 (2021)"},{"key":"13_CR39","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. CoRR, arXiv:1506.01497 (2015)"},{"key":"13_CR40","doi-asserted-by":"crossref","unstructured":"Ruder, M., Dosovitskiy, A., Brox, T.: Artistic style transfer for videos. In: Proceedings of GCPR (2016)","DOI":"10.1007\/978-3-319-45886-1_3"},{"key":"13_CR41","doi-asserted-by":"crossref","unstructured":"Ruta, D., et al.: Aladin: all layer adaptive instance normalization for fine-grained style similarity. arXiv preprint arXiv:2103.09776 (2021)","DOI":"10.1109\/ICCV48922.2021.01171"},{"key":"13_CR42","unstructured":"Saleh, B., Elgammal, A.: Large-scale classification of fine-art paintings: learning the right metric on the right feature (2015)"},{"key":"13_CR43","doi-asserted-by":"crossref","unstructured":"Shamir, L., Macura, T., Orlov, N., Eckley, D.: Impressionism, expressionism, surrealism: automated recognition of painters and schools of art. IEEE Trans. Appl. Percept. (2010)","DOI":"10.1145\/1670671.1670672"},{"key":"13_CR44","volume-title":"Routledge International Handbook of Participatory Design","author":"J Simondsen","year":"2013","unstructured":"Simondsen, J., Roberton, T.: Routledge International Handbook of Participatory Design. Routledge, London (2013)"},{"key":"13_CR45","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"13_CR46","doi-asserted-by":"crossref","unstructured":"Srinivas, A., Lin, T.-Y., Parmar, N., Shlens, J., Abbeel, P., Vaswani, A.: Bottleneck transformers for visual recognition. arXiv preprint arXiv:2101.11605 (2021)","DOI":"10.1109\/CVPR46437.2021.01625"},{"key":"13_CR47","unstructured":"Ulyanov, D., Lebedev, V., Vedaldi, A., Lempitsky, V.: Texture networks: feed-forward synthesis of textures and stylized images. In: Proceedings of ICML (2016)"},{"key":"13_CR48","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence Zitnick, C., Parikh, D.: Cider: consensus-based image description evaluation. CoRR, arXiv:1411.5726 (2014)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"13_CR49","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. arXiv preprint arXiv:1411.4555 (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"13_CR50","doi-asserted-by":"crossref","unstructured":"Wang, X., Oxholm, G., Zhang, D., Wang, Y.-F.: Multimodal transfer: a hierarchical deep convolutional neural network for fast artistic style transfer. In: Proceedings of CVPR (2017)","DOI":"10.1109\/CVPR.2017.759"},{"key":"13_CR51","doi-asserted-by":"crossref","unstructured":"Wei, X.-S., Luo, J.-H., Wu, J., Zhou, Z.-H.: Selective convolutional descriptor aggregation for fine-grained image retrieval. arXiv preprint arXiv:1604.04994 (2017)","DOI":"10.1109\/TIP.2017.2688133"},{"key":"13_CR52","doi-asserted-by":"crossref","unstructured":"Wilber, M.J., Fang, C., Jin, H., Hertzmann, A., Collomosse, J., Belongie, S.: Bam! the behance artistic media dataset for recognition beyond photography. arXiv preprint arXiv:1704.08614 (2017)","DOI":"10.1109\/ICCV.2017.136"},{"key":"13_CR53","doi-asserted-by":"crossref","unstructured":"Xu, L., Wang, X.: Semantic description of cultural digital images: using a hierarchical model and controlled vocabulary. D Lib Mag. 21(5\/6) (2015)","DOI":"10.1045\/may2015-xu"},{"key":"13_CR54","doi-asserted-by":"crossref","unstructured":"Yao, B., Khosla, A., Fei-Fei, L.: Combining randomization and discrimination for fine-grained image categorization. In: CVPR 2011, pp. 1577\u20131584 (2011)","DOI":"10.1109\/CVPR.2011.5995368"},{"key":"13_CR55","doi-asserted-by":"crossref","unstructured":"Zhang, P., et al.: Vinvl: revisiting visual representations in vision-language models. arXiv preprint arXiv:2101.00529 (2021)","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"13_CR56","doi-asserted-by":"crossref","unstructured":"Zhou, L., Palangi, H., Zhang, L., Hu, H., Corso, J.J., Gao, J.: Unified vision-language pre-training for image captioning and VQA. arXiv preprint arXiv:1909.11059 (2019)","DOI":"10.1609\/aaai.v34i07.7005"},{"key":"13_CR57","doi-asserted-by":"crossref","unstructured":"Zujovic, J., Gandy, L., Friedman, S., Pardo, B., Pappas, T.N.: Classifying paintings by artistic genre: an analysis of features and classifiers. In: Proceedings of IEEE Workshop on Multimedia Signal Processing (MMSP) (2009)","DOI":"10.1109\/MMSP.2009.5293271"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20074-8_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,11]],"date-time":"2023-03-11T21:49:45Z","timestamp":1678571385000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20074-8_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200731","9783031200748"],"references-count":57,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20074-8_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"12 November 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","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":"5804","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":"1645","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":"28% - 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":"3.21","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":"3.91","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)"}}]}}