{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:14:59Z","timestamp":1777655699815,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","funder":[{"name":"Ministry of Economic Development of the RF","award":["000000C313925P4G0002"],"award-info":[{"award-number":["000000C313925P4G0002"]}]},{"name":"Ivannikov Institute for System Programming of the Russian Academy of Sciences","award":["139-15-2025-011"],"award-info":[{"award-number":["139-15-2025-011"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754797","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:27:39Z","timestamp":1761377259000},"page":"5336-5344","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Evaluation of Egyptian Hieroglyph Classification Across Diverse Writing Styles"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0679-6981","authenticated-orcid":false,"given":"Maksim","family":"Golyadkin","sequence":"first","affiliation":[{"name":"Artificial Intelligence Research Institute, Moscow, Russian Federation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7628-078X","authenticated-orcid":false,"given":"Valeria","family":"Rubanova","sequence":"additional","affiliation":[{"name":"National Research University ITMO, Saint Petersburg, Russian Federation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2817-7337","authenticated-orcid":false,"given":"Aleksandr","family":"Utkov","sequence":"additional","affiliation":[{"name":"National Research University ITMO, Saint Petersburg, Russian Federation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2025-7997","authenticated-orcid":false,"given":"Dmitry","family":"Nikolotov","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Research Institute, Dolgoprudny, Russian Federation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3308-8825","authenticated-orcid":false,"given":"Ilya","family":"Makarov","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Research Institute, Moscow, Russian Federation, Ivannikov Institute for System Programming, Moscow, Russian Federation, and National Research University ITMO, Saint Petersburg, Russian Federation"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0299297"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/IC457434.2024.10486368"},{"key":"e_1_3_2_1_3_1","volume-title":"Restoring ancient text using deep learning: a case study on Greek epigraphy. arXiv preprint arXiv:1910.06262","author":"Assael Yannis","year":"2019","unstructured":"Yannis Assael, Thea Sommerschield, and Jonathan Prag. 2019. Restoring ancient text using deep learning: a case study on Greek epigraphy. arXiv preprint arXiv:1910.06262 (2019)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-022-04448-z"},{"key":"e_1_3_2_1_5_1","first-page":"67","volume-title":"Proceedings of the Second International Conference on Computing, Communication, Security and Intelligent Systems, Shahid Mumtaz, Danda B. Rawat, and Varun G. Menon (Eds.). Springer Nature Singapore","author":"Aswathy A.","unstructured":"A. Aswathy and P. Uma Maheswari. 2024. Synthetic Ancient Tamil Character Generation Using GAN. In Proceedings of the Second International Conference on Computing, Communication, Security and Intelligent Systems, Shahid Mumtaz, Danda B. Rawat, and Varun G. Menon (Eds.). Springer Nature Singapore, Singapore, 67-81."},{"key":"e_1_3_2_1_6_1","volume-title":"Synthetic data from diffusion models improves imagenet classification. arXiv preprint arXiv:2304.08466","author":"Azizi Shekoofeh","year":"2023","unstructured":"Shekoofeh Azizi, Simon Kornblith, Chitwan Saharia, Mohammad Norouzi, and David J Fleet. 2023. Synthetic data from diffusion models improves imagenet classification. arXiv preprint arXiv:2304.08466 (2023)."},{"key":"e_1_3_2_1_7_1","unstructured":"Andrea Barucci Michela Amendola Fabrizio Argenti Chiara Canfailla Costanza Cucci Massimiliano Franci Tommaso Guidi and Lorenzo Python. 2023. Discovering the Ancient Egyptian Hieroglyphs with Deep Learning. Consiglio Nazionale delle Richerche (CNR)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3110082"},{"key":"e_1_3_2_1_9_1","volume-title":"A theory of learning from different domains. Machine learning","author":"Ben-David Shai","year":"2010","unstructured":"Shai Ben-David, John Blitzer, Koby Crammer, Alex Kulesza, Fernando Pereira, and Jennifer Wortman Vaughan. 2010. A theory of learning from different domains. Machine learning, Vol. 79 (2010), 151-175."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40494-024-01182-9"},{"key":"e_1_3_2_1_11_1","first-page":"74","volume-title":"Tel Aviv","author":"Ding Mingyu","year":"2022","unstructured":"Mingyu Ding, Bin Xiao, Noel Codella, Ping Luo, Jingdong Wang, and Lu Yuan. 2022. Davit: Dual attention vision transformers. In Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XXIV. Springer, 74-92."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/SITIS.2018.00016"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2003794117"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502199"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651671.3651771"},{"key":"e_1_3_2_1_16_1","volume-title":"Egyptian grammar: being an introduction to the study of hieroglyphs","author":"Gardiner Alan Henderson","unstructured":"Alan Henderson Gardiner. 1927. Egyptian grammar: being an introduction to the study of hieroglyphs. Clarendon Press."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.265"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.3390\/a16020079"},{"key":"e_1_3_2_1_19_1","volume-title":"Classification and Detection of Symbols in Ancient Papyri","author":"Haliassos Alexandros","unstructured":"Alexandros Haliassos, Panagiotis Barmpoutis, Tania Stathaki, Stephen Quirke, and Anthony Constantinides. 2020. Classification and Detection of Symbols in Ancient Papyri. Springer International Publishing, Cham, 121-140."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_21_1","volume-title":"Advances in Neural Information Processing Systems","author":"Heusel Martin","year":"2017","unstructured":"Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. 2017. GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium. In Advances in Neural Information Processing Systems, I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.), Vol. 30. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/file\/8a1d694707eb0fefe65871369074926d-Paper.pdf"},{"key":"e_1_3_2_1_22_1","volume-title":"LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=nZeVKeeFYf9","author":"Hu Edward J","year":"2022","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=nZeVKeeFYf9"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_28"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.3103\/S0146411618040089"},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 139), Marina Meila and Tong Zhang (Eds.). PMLR, 8748-8763."},{"key":"e_1_3_2_1_28_1","unstructured":"Tonio Sebastian Richter Daniel A. Werning on behalf of the Berlin-Brandenburgische Akademie der Wissenschaften Hans-Werner Fischer-Elfert and Peter Dils on behalf of the S\u00e4chsische Akademie der Wissenschaften zu Leipzig. [n.d.]. Thesaurus Linguae Aegyptiae. Corpus issue 19 Web app version 2.2.0 11\/5\/2024 Available at: https:\/\/thesaurus-linguae-aegyptiae.de(accessed: 10.11.2024)."},{"key":"e_1_3_2_1_29_1","volume-title":"Synthetic data generation for Indic handwritten text recognition. arXiv preprint arXiv:1804.06254","author":"Roy Partha Pratim","year":"2018","unstructured":"Partha Pratim Roy, Akash Mohta, and Bidyut B Chaudhuri. 2018. Synthetic data generation for Indic handwritten text recognition. arXiv preprint arXiv:1804.06254 (2018)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00392"},{"key":"e_1_3_2_1_31_1","volume-title":"Investigation of the Zipf-plot of the extinct Meroitic language. arXiv preprint arXiv:0808.2904","author":"Smith Reginald D","year":"2008","unstructured":"Reginald D Smith. 2008. Investigation of the Zipf-plot of the extinct Meroitic language. arXiv preprint arXiv:0808.2904 (2008)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3267981"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00481"},{"key":"e_1_3_2_1_34_1","volume-title":"Proceedings of the 36th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"6114","author":"Tan Mingxing","year":"2019","unstructured":"Mingxing Tan and Quoc Le. 2019. EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. In Proceedings of the 36th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 97), Kamalika Chaudhuri and Ruslan Salakhutdinov (Eds.). PMLR, 6105-6114."},{"key":"e_1_3_2_1_35_1","volume-title":"Proceedings of the 39th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"23340","author":"Wang Peng","year":"2022","unstructured":"Peng Wang, An Yang, Rui Men, Junyang Lin, Shuai Bai, Zhikang Li, Jianxin Ma, Chang Zhou, Jingren Zhou, and Hongxia Yang. 2022. OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework. In Proceedings of the 39th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 162), Kamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesvari, Gang Niu, and Sivan Sabato (Eds.). PMLR, 23318-23340."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","unstructured":"Ross Wightman. 2019. PyTorch Image Models. https:\/\/github.com\/rwightman\/pytorch-image-models. doi:10.5281\/zenodo.4414861","DOI":"10.5281\/zenodo.4414861"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0009506"},{"key":"e_1_3_2_1_38_1","unstructured":"Hu Ye Jun Zhang Sibo Liu Xiao Han and Wei Yang. 2023. IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models. (2023)."},{"key":"e_1_3_2_1_39_1","volume-title":"Coca: Contrastive captioners are image-text foundation models. arXiv preprint arXiv:2205.01917","author":"Yu Jiahui","year":"2022","unstructured":"Jiahui Yu, Zirui Wang, Vijay Vasudevan, Legg Yeung, Mojtaba Seyedhosseini, and Yonghui Wu. 2022. Coca: Contrastive captioners are image-text foundation models. arXiv preprint arXiv:2205.01917 (2022)."},{"key":"e_1_3_2_1_40_1","volume-title":"Proceedings of the IEEE International Conference on Computer Vision (ICCV).","author":"Zhu Jun-Yan","unstructured":"Jun-Yan Zhu, Taesung Park, Phillip Isola, and Alexei A. Efros. 2017. Unpaired Image-To-Image Translation Using Cycle-Consistent Adversarial Networks. In Proceedings of the IEEE International Conference on Computer Vision (ICCV)."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3754797","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:56:28Z","timestamp":1765342588000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754797"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":40,"alternative-id":["10.1145\/3746027.3754797","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754797","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}