{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,15]],"date-time":"2025-06-15T14:40:04Z","timestamp":1749998404260,"version":"3.41.0"},"publisher-location":"Cham","reference-count":13,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031705519"},{"type":"electronic","value":"9783031705526"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-70552-6_25","type":"book-chapter","created":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T04:02:14Z","timestamp":1725940934000},"page":"410-425","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ICDAR 2024 Competition on\u00a0Reading Documents Through Aria Glasses"],"prefix":"10.1007","author":[{"given":"Soumya Shamarao","family":"Jahagirdar","sequence":"first","affiliation":[]},{"given":"Ajoy","family":"Mondal","sequence":"additional","affiliation":[]},{"given":"Yuheng","family":"Ren","sequence":"additional","affiliation":[]},{"given":"Omkar M.","family":"Parkhi","sequence":"additional","affiliation":[]},{"given":"C. V.","family":"Jawahar","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,9,11]]},"reference":[{"key":"25_CR1","unstructured":"Tesseract OCR (2021). https:\/\/github.com\/tesseract-ocr\/tesseract"},{"key":"25_CR2","doi-asserted-by":"crossref","unstructured":"Baek, Y., Lee, B., Han, D., Yun, S., Lee, H.: Character region awareness for text detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9365\u20139374 (2019)","DOI":"10.1109\/CVPR.2019.00959"},{"key":"25_CR3","doi-asserted-by":"publisher","unstructured":"Bautista, D., Atienza, R.: Scene text recognition with permuted autoregressive sequence models. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) European Conference on Computer Vision, vol. 13688, pp. 178\u2013196. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19815-1_11","DOI":"10.1007\/978-3-031-19815-1_11"},{"key":"25_CR4","unstructured":"Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: YOLOv4: optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020)"},{"key":"25_CR5","doi-asserted-by":"crossref","unstructured":"Du, Y., et al.: SVTR: scene text recognition with a single visual model. arXiv preprint arXiv:2205.00159 (2022)","DOI":"10.24963\/ijcai.2022\/124"},{"key":"25_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"444","DOI":"10.1007\/978-3-030-86337-1_30","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"S Gongidi","year":"2021","unstructured":"Gongidi, S., Jawahar, C.V.: IIIT-INDIC-HW-Words: a dataset for indic handwritten text recognition. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12824, pp. 444\u2013459. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86337-1_30"},{"key":"25_CR7","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"25_CR8","doi-asserted-by":"crossref","unstructured":"Huang, Y., Lv, T., Cui, L., Lu, Y., Wei, F.: LayoutLMv3: pre-training for document AI with unified text and image masking. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 4083\u20134091 (2022)","DOI":"10.1145\/3503161.3548112"},{"key":"25_CR9","unstructured":"Mindee: docTR: document text recognition (2021). https:\/\/github.com\/mindee\/doctr"},{"key":"25_CR10","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 of the Association for Computational Linguistics, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"25_CR11","doi-asserted-by":"crossref","unstructured":"Wang, Z., Xu, Y., Cui, L., Shang, J., Wei, F.: LayoutReader: pre-training of text and layout for reading order detection. arXiv preprint arXiv:2108.11591 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.389"},{"key":"25_CR12","doi-asserted-by":"crossref","unstructured":"Wang, Z., Xie, H., Wang, Y., Xu, J., Zhang, B., Zhang, Y.: Symmetrical linguistic feature distillation with clip for scene text recognition. In: Proceedings of the 31st ACM International Conference on Multimedia. pp. 509\u2013518 (2023)","DOI":"10.1145\/3581783.3611769"},{"key":"25_CR13","doi-asserted-by":"crossref","unstructured":"Zhao, S., Quan, R., Zhu, L., Yang, Y.: CLIP4STR: a simple baseline for scene text recognition with pre-trained vision-language model. arXiv preprint arXiv:2305.14014 (2023)","DOI":"10.1109\/TIP.2024.3512354"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition - ICDAR 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-70552-6_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,15]],"date-time":"2025-06-15T14:07:49Z","timestamp":1749996469000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70552-6_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031705519","9783031705526"],"references-count":13,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70552-6_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"11 September 2024","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":"Athens","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icdar2024.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}