{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T15:57:16Z","timestamp":1776182236330,"version":"3.50.1"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031416781","type":"print"},{"value":"9783031416798","type":"electronic"}],"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\/978-3-031-41679-8_22","type":"book-chapter","created":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T07:02:59Z","timestamp":1692342179000},"page":"384-401","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":37,"title":["WordStylist: Styled Verbatim Handwritten Text Generation with\u00a0Latent Diffusion Models"],"prefix":"10.1007","author":[{"given":"Konstantina","family":"Nikolaidou","sequence":"first","affiliation":[]},{"given":"George","family":"Retsinas","sequence":"additional","affiliation":[]},{"given":"Vincent","family":"Christlein","sequence":"additional","affiliation":[]},{"given":"Mathias","family":"Seuret","sequence":"additional","affiliation":[]},{"given":"Giorgos","family":"Sfikas","sequence":"additional","affiliation":[]},{"given":"Elisa Barney","family":"Smith","sequence":"additional","affiliation":[]},{"given":"Hamam","family":"Mokayed","sequence":"additional","affiliation":[]},{"given":"Marcus","family":"Liwicki","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,8,19]]},"reference":[{"key":"22_CR1","doi-asserted-by":"crossref","unstructured":"Arandjelovi\u0107, R., Zisserman, A.: Three things everyone should know to improve object retrieval. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2911\u20132918. Providence, June 2012","DOI":"10.1109\/CVPR.2012.6248018"},{"key":"22_CR2","doi-asserted-by":"crossref","unstructured":"Bhunia, A.K., Khan, S., Cholakkal, H., Anwer, R.M., Khan, F.S., Shah, M.: Handwriting transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 1086\u20131094, October 2021","DOI":"10.1109\/ICCV48922.2021.00112"},{"key":"22_CR3","doi-asserted-by":"crossref","unstructured":"Christlein, V., Bernecker, D., Angelopoulou, E.: Writer identification using vlad encoded contour-zernike moments. In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR), pp. 906\u2013910. Nancy, August 2015","DOI":"10.1109\/ICDAR.2015.7333893"},{"key":"22_CR4","doi-asserted-by":"publisher","first-page":"258","DOI":"10.1016\/j.patcog.2016.10.005","volume":"63","author":"V Christlein","year":"2017","unstructured":"Christlein, V., Bernecker, D., H\u00f6nig, F., Maier, A., Angelopoulou, E.: Writer identification using GMM supervectors and exemplar-svms. Pattern Recogn. 63, 258\u2013267 (2017)","journal-title":"Pattern Recogn."},{"key":"22_CR5","doi-asserted-by":"crossref","unstructured":"Christlein, V., Gropp, M., Fiel, S., Maier, A.: Unsupervised feature learning for writer identification and writer retrieval. In: 2017 14th International Conference on Document Analysis and Recognition, vol. 01, pp. 991\u2013997. Kyoto (2017)","DOI":"10.1109\/ICDAR.2017.165"},{"key":"22_CR6","doi-asserted-by":"crossref","unstructured":"Christlein, V., Maier, A.: Encoding CNN activations for writer recognition. In: 13th IAPR International Workshop on Document Analysis Systems, pp. 169\u2013174. Vienna (2018)","DOI":"10.1109\/DAS.2018.9"},{"key":"22_CR7","doi-asserted-by":"publisher","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255 (2009). https:\/\/doi.org\/10.1109\/CVPR.2009.5206848","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"3","key":"22_CR8","doi-asserted-by":"publisher","first-page":"450","DOI":"10.1016\/0047-259X(82)90077-X","volume":"12","author":"D Dowson","year":"1982","unstructured":"Dowson, D., Landau, B.: The Fr\u00e9chet distance between multivariate normal distributions. J. Multivar. Anal. 12(3), 450\u2013455 (1982)","journal-title":"J. Multivar. Anal."},{"key":"22_CR9","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1016\/j.neunet.2021.07.019","volume":"144","author":"S Frolov","year":"2021","unstructured":"Frolov, S., Hinz, T., Raue, F., Hees, J., Dengel, A.: Adversarial text-to-image synthesis: a review. Neural Netw. 144, 187\u2013209 (2021)","journal-title":"Neural Netw."},{"key":"22_CR10","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N., Weinberger, K. (eds.) Advances in Neural Information Processing Systems, vol. 27. Curran Associates, Inc. (2014). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2014\/file\/5ca3e9b122f61f8f06494c97b1afccf3-Paper.pdf"},{"issue":"5","key":"22_CR11","doi-asserted-by":"publisher","first-page":"855","DOI":"10.1109\/TPAMI.2008.137","volume":"31","author":"A Graves","year":"2008","unstructured":"Graves, A., Liwicki, M., Fern\u00e1ndez, S., Bertolami, R., Bunke, H., Schmidhuber, J.: A novel connectionist system for unconstrained handwriting recognition. IEEE Trans. Pattern Anal. Mach. Intell. 31(5), 855\u2013868 (2008)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"22_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"22_CR13","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"22_CR14","doi-asserted-by":"crossref","unstructured":"Kang, L., Riba, P., Rusinol, M., Forn\u00e9s, A., Villegas, M.: Content and style aware generation of text-line images for handwriting recognition. IEEE Trans. Pattern Anal. Mach. Intell. 44(12), 8846\u20138860 (2021)","DOI":"10.1109\/TPAMI.2021.3122572"},{"key":"22_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1007\/978-3-030-58592-1_17","volume-title":"Computer Vision \u2013 ECCV 2020","author":"L Kang","year":"2020","unstructured":"Kang, L., Riba, P., Wang, Y., Rusi\u00f1ol, M., Forn\u00e9s, A., Villegas, M.: GANwriting: content-conditioned generation of styled handwritten word images. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12368, pp. 273\u2013289. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58592-1_17"},{"key":"22_CR16","first-page":"21696","volume":"34","author":"D Kingma","year":"2021","unstructured":"Kingma, D., Salimans, T., Poole, B., Ho, J.: Variational diffusion models. Adv. Neural Inf. Process. Syst. 34, 21696\u201321707 (2021)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"22_CR17","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. In: Bengio, Y., LeCun, Y. (eds.) 2nd International Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, 14\u201316 April 2014, Conference Track Proceedings (2014)"},{"key":"22_CR18","unstructured":"Kingma, D.P., Dhariwal, P.: Glow: generative flow with invertible 1x1 convolutions. Adv. Neural Inf. Process. Syst. 31 (2018)"},{"key":"22_CR19","unstructured":"Kong, Z., Ping, W., Huang, J., Zhao, K., Catanzaro, B.: DiffWave: a versatile diffusion model for audio synthesis. In: International Conference on Learning Representations (2020)"},{"key":"22_CR20","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., et al.: Microsoft COCO: common objects in context. In: European Conference on Computer Vision (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"issue":"10","key":"22_CR21","doi-asserted-by":"publisher","first-page":"110","DOI":"10.3390\/jimaging6100110","volume":"6","author":"F Lombardi","year":"2020","unstructured":"Lombardi, F., Marinai, S.: Deep learning for historical document analysis and recognition-a survey. J. Imaging 6(10), 110 (2020)","journal-title":"J. Imaging"},{"key":"22_CR22","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (2017)"},{"issue":"2","key":"22_CR23","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91\u2013110 (2004)","journal-title":"Int. J. Comput. Vis."},{"key":"22_CR24","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1007\/s100320200071","volume":"5","author":"UV Marti","year":"2002","unstructured":"Marti, U.V., Bunke, H.: The IAM-database: an English sentence database for offline handwriting recognition. Int. J. Doc. Anal. Recogn. 5, 39\u201346 (2002)","journal-title":"Int. J. Doc. Anal. Recogn."},{"key":"22_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"268","DOI":"10.1007\/978-3-030-86549-8_18","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"A Mattick","year":"2021","unstructured":"Mattick, A., Mayr, M., Seuret, M., Maier, A., Christlein, V.: SmartPatch: improving handwritten word imitation with patch discriminators. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12821, pp. 268\u2013283. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86549-8_18"},{"key":"22_CR26","unstructured":"Mirza, M., Osindero, S.: Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784 (2014)"},{"key":"22_CR27","unstructured":"Mittal, G., Engel, J.H., Hawthorne, C., Simon, I.: Symbolic music generation with diffusion models. In: Proceedings of the 22nd International Society for Music Information Retrieval Conference, ISMIR 2021, 7\u201312 November 2021, pp. 468\u2013475 (2021). https:\/\/archives.ismir.net\/ismir2021\/paper\/000058.pdf"},{"key":"22_CR28","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1007\/s10032-022-00405-8","volume":"25","author":"K Nikolaidou","year":"2022","unstructured":"Nikolaidou, K., Seuret, M., Mokayed, H., Liwicki, M.: A survey of historical document image datasets. Int. J. Doc. Anal. Recogn. (IJDAR) 25, 305\u2013338 (2022)","journal-title":"Int. J. Doc. Anal. Recogn. (IJDAR)"},{"key":"22_CR29","doi-asserted-by":"publisher","unstructured":"Pondenkandath, V., Alberti, M., Diatta, M., Ingold, R., Liwicki, M.: Historical document synthesis with generative adversarial networks. In: 2019 International Conference on Document Analysis and Recognition Workshops (ICDARW), vol. 5, pp. 146\u2013151 (2019). https:\/\/doi.org\/10.1109\/ICDARW.2019.40096","DOI":"10.1109\/ICDARW.2019.40096"},{"key":"22_CR30","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with CLIP Latents. ArXiv abs\/2204.06125 (2022)"},{"key":"22_CR31","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1007\/978-3-031-06555-2_17","volume-title":"Document Analysis Systems","author":"G Retsinas","year":"2022","unstructured":"Retsinas, G., Sfikas, G., Gatos, B., Nikou, C.: Best practices for a handwritten text recognition system. In: Uchida, S., Barney, E., Eglin, V. (eds.) Document Analysis Systems, pp. 247\u2013259. Springer International Publishing, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-06555-2_17"},{"key":"22_CR32","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"22_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"22_CR34","first-page":"36479","volume":"35","author":"C Saharia","year":"2022","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. Adv. Neural Inf. Process. Syst. 35, 36479\u201336494 (2022)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"22_CR35","doi-asserted-by":"crossref","unstructured":"Fogel, S., Averbuch-Elor, H., Cohen, S., Mazor, S., Litman, R.: ScrabbleGAN: semi-supervised varying length handwritten text generation. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4323\u20134332 (2020)","DOI":"10.1109\/CVPR42600.2020.00438"},{"key":"22_CR36","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: International Conference on Machine Learning, pp. 2256\u20132265. PMLR (2015)"},{"key":"22_CR37","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2818\u20132826 (2015)","DOI":"10.1109\/CVPR.2016.308"},{"key":"22_CR38","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"22_CR39","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"610","DOI":"10.1007\/978-3-030-86334-0_40","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"L V\u00f6gtlin","year":"2021","unstructured":"V\u00f6gtlin, L., Drazyk, M., Pondenkandath, V., Alberti, M., Ingold, R.: Generating synthetic handwritten historical documents with OCR constrained GANs. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12823, pp. 610\u2013625. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86334-0_40"},{"key":"22_CR40","doi-asserted-by":"crossref","unstructured":"Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2223\u20132232 (2017)","DOI":"10.1109\/ICCV.2017.244"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition - ICDAR 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-41679-8_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T07:27:40Z","timestamp":1692343660000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-41679-8_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031416781","9783031416798"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-41679-8_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"19 August 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICDAR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Document Analysis and Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"San Jos\u00e9, CA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","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":"21 August 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 August 2023","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":"icdar2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icdar2023.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":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"316","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":"154","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":"49% - 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":"2.89","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":"1.50","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":"Number and type of other papers accepted : IJDAR track papers","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)"}}]}}