{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T00:04:41Z","timestamp":1767312281519,"version":"3.48.0"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032093707","type":"print"},{"value":"9783032093714","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-09371-4_4","type":"book-chapter","created":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T00:00:14Z","timestamp":1767312014000},"page":"50-66","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["AnnoPage Dataset: Dataset of\u00a0Non-textual Elements in\u00a0Documents with\u00a0Fine-Grained Categorization"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6853-0508","authenticated-orcid":false,"given":"Martin","family":"Ki\u0161\u0161","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6364-129X","authenticated-orcid":false,"given":"Michal","family":"Hradi\u0161","sequence":"additional","affiliation":[]},{"given":"Martina","family":"Dvo\u0159\u00e1kov\u00e1","sequence":"additional","affiliation":[]},{"given":"V\u00e1clav","family":"Jirou\u0161ek","sequence":"additional","affiliation":[]},{"given":"Filip","family":"Kersch","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,2]]},"reference":[{"key":"4_CR1","doi-asserted-by":"crossref","unstructured":"Antonacopoulos, A., Bridson, D., Papadopoulos, C., Pletschacher, S.: A realistic dataset for performance evaluation of document layout analysis. In: 2009 10th International Conference on Document Analysis and Recognition pp. 296\u2013300 (2009). ISSN 2379-2140","DOI":"10.1109\/ICDAR.2009.271"},{"key":"4_CR2","doi-asserted-by":"crossref","unstructured":"Auer, C., Nassar, A., Lysak, M., Dolfi, M., Livathinos, N., Staar, P.: ICDAR 2023 competition on robust layout segmentation in corporate documents. In: Fink, G.A., Jain, R., Kise, K., Zanibbi, R. (eds.) Document Analysis and Recognition - ICDAR 2023. Springer, Cham (2023)","DOI":"10.1007\/978-3-031-41679-8_27"},{"key":"4_CR3","doi-asserted-by":"crossref","unstructured":"Boillet, M., Bonhomme, M.L., Stutzmann, D., Kermorvant, C.: HORAE: an annotated dataset of books of hours. In: Proceedings of the 5th International Workshop on Historical Document Imaging and Processing, HIP 2019, pp. 7\u201312. Association for Computing Machinery (2019)","DOI":"10.1145\/3352631.3352633"},{"key":"4_CR4","doi-asserted-by":"crossref","unstructured":"B\u00fcttner, J., Martinetz, J., El-Hajj, H., Valleriani, M.: CorDeep and the Sacrobosco dataset: detection of visual elements in historical documents. J. Imaging 8(10), 285 (2022)","DOI":"10.3390\/jimaging8100285"},{"key":"4_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"4_CR6","doi-asserted-by":"crossref","unstructured":"Cheng, H., et al.: M6Doc: a large-scale multi-format, multi-type, multi-layout, multi-language, multi-annotation category dataset for modern document layout analysis, pp. 15138\u201315147","DOI":"10.1109\/CVPR52729.2023.01453"},{"key":"4_CR7","doi-asserted-by":"crossref","unstructured":"Clausner, C., Antonacopoulos, A., Pletschacher, S.: ICDAR2019 competition on recognition of documents with complex layouts - RDCL2019. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1521\u20131526 (2019). ISSN 2379-2140","DOI":"10.1109\/ICDAR.2019.00245"},{"key":"4_CR8","doi-asserted-by":"crossref","unstructured":"Clausner, C., Papadopoulos, C., Pletschacher, S., Antonacopoulos, A.: The ENP image and ground truth dataset of historical newspapers. In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR), pp. 931\u2013935 (2015)","DOI":"10.1109\/ICDAR.2015.7333898"},{"key":"4_CR9","doi-asserted-by":"crossref","unstructured":"Diem, M., Kleber, F., Sablatnig, R., Gatos, B.: cBAD: ICDAR2019 competition on baseline detection. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1494\u20131498 (2019). ISSN 2379-2140","DOI":"10.1109\/ICDAR.2019.00240"},{"key":"4_CR10","unstructured":"Dubey, A., et\u00a0al.: The Llama 3 Herd of models. arXiv preprint arXiv:2407.21783 (2024)"},{"key":"4_CR11","doi-asserted-by":"crossref","unstructured":"Gao, L., et al.: ICDAR 2019 competition on table detection and recognition (cTDaR). In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1510\u20131515 (2019). ISSN 2379-2140","DOI":"10.1109\/ICDAR.2019.00243"},{"key":"4_CR12","doi-asserted-by":"crossref","unstructured":"Jaume, G., Ekenel, H.K., Thiran, J.P.: FUNSD: a dataset for form understanding in noisy scanned documents. In: 2019 International Conference on Document Analysis and Recognition Workshops (ICDARW), vol.\u00a02, pp.\u00a01\u20136. IEEE (2019)","DOI":"10.1109\/ICDARW.2019.10029"},{"key":"4_CR13","unstructured":"Jirou\u0161ek, V., et al.: Metodika zpracov\u00e1n\u00ed obrazov\u00fdch dokument\u016f. http:\/\/www.nusl.cz\/ntk\/nusl-668880. Publisher: Knihovna AV \u010cR, N\u00e1rodn\u00ed 3, 115 22 Praha 1. http:\/\/www.lib.cas.cz\/"},{"key":"4_CR14","unstructured":"Jocher, G., Qiu, J.: Ultralytics YOLO11 (2024). https:\/\/github.com\/ultralytics\/ultralytics"},{"key":"4_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"492","DOI":"10.1007\/978-3-030-86331-9_32","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"O Kodym","year":"2021","unstructured":"Kodym, O., Hradi\u0161, M.: Page layout analysis system for\u00a0unconstrained historic documents. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12822, pp. 492\u2013506. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86331-9_32"},{"key":"4_CR16","doi-asserted-by":"crossref","unstructured":"Li, F., et al.: Mask DINO: towards a unified transformer-based framework for object detection and segmentation. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3041\u20133050 (2023). ISSN 2575-7075","DOI":"10.1109\/CVPR52729.2023.00297"},{"key":"4_CR17","unstructured":"Li, M., Cui, L., Huang, S., Wei, F., Zhou, M., Li, Z.: TableBank: table benchmark for image-based table detection and recognition. In: Calzolari, N., et al. (eds.) Proceedings of the Twelfth Language Resources and Evaluation Conference, pp. 1918\u20131925. European Language Resources Association (2020)"},{"key":"4_CR18","doi-asserted-by":"crossref","unstructured":"Li, M., et al.: DocBank: a benchmark dataset for document layout analysis. In: Scott, D., Bel, N., Zong, C. (eds.) Proceedings of the 28th International Conference on Computational Linguistics, pp. 949\u2013960. International Committee on Computational Linguistics (2020)","DOI":"10.18653\/v1\/2020.coling-main.82"},{"key":"4_CR19","doi-asserted-by":"crossref","unstructured":"Ma, J., Du, J., Hu, P., Zhang, Z., Zhang, J., Zhu, H., Liu, C.: HRDoc: dataset and baseline method toward hierarchical reconstruction of document structures. In: Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence and Thirty-Fifth Conference on Innovative Applications of Artificial Intelligence and Thirteenth Symposium on Educational Advances in Artificial Intelligence, AAAI 2023\/IAAI 2023\/EAAI 2023, vol.\u00a037, pp. 1870\u20131877. AAAI Press (2023)","DOI":"10.1609\/aaai.v37i2.25277"},{"key":"4_CR20","doi-asserted-by":"crossref","unstructured":"Mehri, M., H\u00e9roux, P., Mullot, R., Moreux, J.P., Co\u00fcasnon, B., Barrett, B.: HBA 1.0: a pixel-based annotated dataset for historical book analysis. In: Proceedings of the 4th International Workshop on Historical Document Imaging and Processing, HIP 2017, pp. 107\u2013112. Association for Computing Machinery (2017)","DOI":"10.1145\/3151509.3151528"},{"key":"4_CR21","doi-asserted-by":"crossref","unstructured":"Monnier, T., Aubry, M.: docExtractor: an off-the-shelf historical document element extraction. In: 2020 17th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 91\u201396 (2020)","DOI":"10.1109\/ICFHR2020.2020.00027"},{"key":"4_CR22","unstructured":"Oquab, M., et\u00a0al.: DINOv2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"4_CR23","doi-asserted-by":"crossref","unstructured":"Pfitzmann, B., Auer, C., Dolfi, M., Nassar, A.S., Staar, P.: DocLayNet: a large human-annotated dataset for document-layout segmentation. In: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2022, pp. 3743\u20133751. Association for Computing Machinery (2022)","DOI":"10.1145\/3534678.3539043"},{"key":"4_CR24","unstructured":"Radford, A., Kim, J.W., Xu, T., Brockman, G., McLeavey, C., Sutskever, I.: Robust speech recognition via large-scale weak supervision. In: International Conference on Machine Learning, pp. 28492\u201328518. PMLR (2023)"},{"key":"4_CR25","doi-asserted-by":"crossref","unstructured":"Shahab, A., Shafait, F., Kieninger, T., Dengel, A.: An open approach towards the benchmarking of table structure recognition systems. In: Proceedings of the 9th IAPR International Workshop on Document Analysis Systems, DAS 2010, pp. 113\u2013120. Association for Computing Machinery (2010)","DOI":"10.1145\/1815330.1815345"},{"key":"4_CR26","doi-asserted-by":"crossref","unstructured":"Simistira, F., Seuret, M., Eichenberger, N., Garz, A., Liwicki, M., Ingold, R.: DIVA-HisDB: a precisely annotated large dataset of challenging medieval manuscripts. In: 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 471\u2013476. ISSN 2167-6445","DOI":"10.1109\/ICFHR.2016.0093"},{"key":"4_CR27","doi-asserted-by":"crossref","unstructured":"Smock, B., Pesala, R., Abraham, R.: PubTables-1m: towards comprehensive table extraction from unstructured documents. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4624\u20134632. IEEE (2022)","DOI":"10.1109\/CVPR52688.2022.00459"},{"key":"4_CR28","unstructured":"Soboroff, I.: Complex document information processing (CDIP) dataset. National Institute of Standards and Technology (2022)"},{"key":"4_CR29","doi-asserted-by":"crossref","unstructured":"Tom, G., Mathew, M., Garcia-Bordils, S., Karatzas, D., Jawahar, C.: ICDAR 2023 competition on RoadText video text detection, tracking and recognition. In: Fink, G.A., Jain, R., Kise, K., Zanibbi, R. (eds.) Document Analysis and Recognition - ICDAR 2023, pp. 577\u2013586. Springer, Cham (2023)","DOI":"10.1007\/978-3-031-41679-8_35"},{"key":"4_CR30","doi-asserted-by":"crossref","unstructured":"Tschirschwitz, D., Klemstein, F., Stein, B., Rodehorst, V.: A dataset for analysing complex document layouts in the digital humanities and its evaluation with Krippendorff\u2019s alpha. In: Andres, B., Bernard, F., Cremers, D., Frintrop, S., Goldl\u00fccke, B., Ihrke, I. (eds.) Pattern Recognition, pp. 354\u2013374. Springer (2022)","DOI":"10.1007\/978-3-031-16788-1_22"},{"key":"4_CR31","unstructured":"Zhang, H., et al.: DINO: DETR with improved DeNoising anchor boxes for end-to-end object detection (2022)"},{"key":"4_CR32","unstructured":"Zhao, Z., Kang, H., Wang, B., He, C.: DocLayout-YOLO: enhancing document layout analysis through diverse synthetic data and global-to-local adaptive perception (2024)"},{"key":"4_CR33","doi-asserted-by":"crossref","unstructured":"Zhong, X., Tang, J., Jimeno\u00a0Yepes, A.: PubLayNet: largest dataset ever for document layout analysis. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1015\u20131022 (2019). ISSN 2379-2140","DOI":"10.1109\/ICDAR.2019.00166"},{"key":"4_CR34","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection (2021)"},{"issue":"20","key":"4_CR35","doi-asserted-by":"publisher","first-page":"11777","DOI":"10.1007\/s00521-023-09356-5","volume":"36","author":"S Zottin","year":"2024","unstructured":"Zottin, S., De Nardin, A., Colombi, E., Piciarelli, C., Pavan, F., Foresti, G.L.: U-DIADS-bib: a full and few-shot pixel-precise dataset for document layout analysis of ancient manuscripts. Neural Comput. Appl. 36(20), 11777\u201311789 (2024)","journal-title":"Neural Comput. Appl."}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition \u2013 ICDAR 2025 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-09371-4_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T00:00:20Z","timestamp":1767312020000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-09371-4_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032093707","9783032093714"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-09371-4_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"2 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that\u00a0are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"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":"Wuhan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iapr.org\/icdar2025","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}