{"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":1749998404049,"version":"3.41.0"},"publisher-location":"Cham","reference-count":30,"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_18","type":"book-chapter","created":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T04:02:14Z","timestamp":1725940934000},"page":"301-314","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ICDAR 2024 Competition on\u00a0Artistic Text Recognition"],"prefix":"10.1007","author":[{"given":"Xudong","family":"Xie","sequence":"first","affiliation":[]},{"given":"Linger","family":"Deng","sequence":"additional","affiliation":[]},{"given":"Zhifei","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Zhaowen","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Yuliang","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,9,11]]},"reference":[{"key":"18_CR1","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.) Computer Vision - ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, 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":"18_CR2","doi-asserted-by":"crossref","unstructured":"Bhunia, A.K., Ghose, S., Kumar, A., Chowdhury, P.N., Sain, A., Song, Y.Z.: MetaHTR: towards writer-adaptive handwritten text recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15830\u201315839 (2021)","DOI":"10.1109\/CVPR46437.2021.01557"},{"key":"18_CR3","unstructured":"Cheng, X., et al.: VIPTR: a vision permutable extractor for fast and efficient scene text recognition. arXiv preprint arXiv:2401.10110 (2024)"},{"key":"18_CR4","doi-asserted-by":"crossref","unstructured":"Chng, C.K., et\u00a0al.: Icdar2019 robust reading challenge on arbitrary-shaped text-rrc-art. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1571\u20131576. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00252"},{"key":"18_CR5","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2020)"},{"key":"18_CR6","doi-asserted-by":"crossref","unstructured":"Fang, S., Xie, H., Wang, Y., Mao, Z., Zhang, Y.: Read like humans: autonomous, bidirectional and iterative language modeling for scene text recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7098\u20137107 (2021)","DOI":"10.1109\/CVPR46437.2021.00702"},{"key":"18_CR7","doi-asserted-by":"crossref","unstructured":"Guan, T., Shen, W., Yang, X., Feng, Q., Jiang, Z., Yang, X.: Self-supervised character-to-character distillation for text recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 19473\u201319484 (2023)","DOI":"10.1109\/ICCV51070.2023.01784"},{"key":"18_CR8","doi-asserted-by":"crossref","unstructured":"Gupta, A., Vedaldi, A., Zisserman, A.: Synthetic data for text localisation in natural images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2315\u20132324 (2016)","DOI":"10.1109\/CVPR.2016.254"},{"key":"18_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"18_CR10","unstructured":"Jaderberg, M., Simonyan, K., Vedaldi, A., Zisserman, A.: Synthetic data and artificial neural networks for natural scene text recognition. Eprint Arxiv (2014)"},{"issue":"1","key":"18_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11263-015-0823-z","volume":"116","author":"M Jaderberg","year":"2016","unstructured":"Jaderberg, M., Simonyan, K., Vedaldi, A., Zisserman, A.: Reading text in the wild with convolutional neural networks. Int. J. Comput. Vision 116(1), 1\u201320 (2016)","journal-title":"Int. J. Comput. Vision"},{"key":"18_CR12","doi-asserted-by":"crossref","unstructured":"Jiang, Q., Wang, J., Peng, D., Liu, C., Jin, L.: Revisiting scene text recognition: a data perspective. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 20543\u201320554 (2023)","DOI":"10.1109\/ICCV51070.2023.01878"},{"key":"18_CR13","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et\u00a0al.: ICDAR 2015 competition on robust reading. In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR), pp. 1156\u20131160. IEEE (2015)","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et al.: ICDAR 2013 robust reading competition. In: 2013 12th International Conference on Document Analysis and Recognition, pp. 1484\u20131493. IEEE (2013)","DOI":"10.1109\/ICDAR.2013.221"},{"key":"18_CR15","doi-asserted-by":"crossref","unstructured":"Lee, J., Park, S., Baek, J., Oh, S.J., Kim, S., Lee, H.: On recognizing texts of arbitrary shapes with 2d self-attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 546\u2013547 (2020)","DOI":"10.1109\/CVPRW50498.2020.00281"},{"key":"18_CR16","doi-asserted-by":"crossref","unstructured":"Liu, Y., Matsoukas, C., Strand, F., Azizpour, H., Smith, K.: Patchdropout: economizing vision transformers using patch dropout. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 3953\u20133962 (2023)","DOI":"10.1109\/WACV56688.2023.00394"},{"key":"18_CR17","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1016\/j.patcog.2019.02.002","volume":"90","author":"Y Liu","year":"2019","unstructured":"Liu, Y., Jin, L., Zhang, S., Luo, C., Zhang, S.: Curved scene text detection via transverse and longitudinal sequence connection. Pattern Recogn. 90, 337\u2013345 (2019)","journal-title":"Pattern Recogn."},{"key":"18_CR18","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/j.patcog.2019.01.020","volume":"90","author":"C Luo","year":"2019","unstructured":"Luo, C., Jin, L., Sun, Z.: Moran: a multi-object rectified attention network for scene text recognition. Pattern Recogn. 90, 109\u2013118 (2019)","journal-title":"Pattern Recogn."},{"key":"18_CR19","doi-asserted-by":"crossref","unstructured":"Mishra, A., Alahari, K., Jawahar, C.: Scene text recognition using higher order language priors. In: BMVC-British machine vision conference. BMVA (2012)","DOI":"10.5244\/C.26.127"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Phan, T.Q., Shivakumara, P., Tian, S., Tan, C.L.: Recognizing text with perspective distortion in natural scenes. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 569\u2013576 (2013)","DOI":"10.1109\/ICCV.2013.76"},{"issue":"18","key":"18_CR21","doi-asserted-by":"publisher","first-page":"8027","DOI":"10.1016\/j.eswa.2014.07.008","volume":"41","author":"A Risnumawan","year":"2014","unstructured":"Risnumawan, A., Shivakumara, P., Chan, C.S., Tan, C.L.: A robust arbitrary text detection system for natural scene images. Expert Syst. Appl. 41(18), 8027\u20138048 (2014)","journal-title":"Expert Syst. Appl."},{"key":"18_CR22","doi-asserted-by":"crossref","unstructured":"Sun, Y., et\u00a0al.: ICDAR 2019 competition on large-scale street view text with partial labeling-RRC-LSVT. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1557\u20131562. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00250"},{"key":"18_CR23","unstructured":"Tarvainen, A., Valpola, H.: Mean teachers are better role models: weight-averaged consistency targets improve semi-supervised deep learning results. In: Advances in Neural Information Processing Systems vol. 30 (2017)"},{"key":"18_CR24","unstructured":"Veit, A., Matera, T., Neumann, L., Matas, J., Belongie, S.: Coco-text: dataset and benchmark for text detection and recognition in natural images. arXiv preprint arXiv:1601.07140 (2016)"},{"key":"18_CR25","unstructured":"Wang, K., Babenko, B., Belongie, S.: End-to-end scene text recognition. In: 2011 International Conference on Computer Vision, pp. 1457\u20131464. IEEE (2011)"},{"key":"18_CR26","doi-asserted-by":"publisher","unstructured":"Wang, P., Da, C., Yao, C.: Multi-granularity prediction for scene text recognition. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision - ECCV 2022, ECCV 2022, LNCS, vol. 13688, pp. 339\u2013355. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19815-1_20","DOI":"10.1007\/978-3-031-19815-1_20"},{"key":"18_CR27","doi-asserted-by":"publisher","unstructured":"Xie, X., Fu, L., Zhang, Z., Wang, Z., Bai, X.: Toward understanding wordart: corner-guided transformer for scene text recognition. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision - ECCV 2022, ECCV 2022, LNCS, vol 13688, pp. 303\u2013321. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19815-1_18","DOI":"10.1007\/978-3-031-19815-1_18"},{"key":"18_CR28","doi-asserted-by":"crossref","unstructured":"Xu, X., Zhang, Z., Wang, Z., Price, B., Wang, Z., Shi, H.: Rethinking text segmentation: a novel dataset and a text-specific refinement approach. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12045\u201312055 (2021)","DOI":"10.1109\/CVPR46437.2021.01187"},{"key":"18_CR29","doi-asserted-by":"crossref","unstructured":"Zhang, B., Xie, H., Wang, Y., Xu, J., Zhang, Y.: Linguistic more: taking a further step toward efficient and accurate scene text recognition. In: Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, pp. 1704\u20131712 (2023)","DOI":"10.24963\/ijcai.2023\/189"},{"key":"18_CR30","unstructured":"Zhang, Y., Gueguen, L., Zharkov, I., Zhang, P., Seifert, K., Kadlec, B.: Uber-text: a large-scale dataset for optical character recognition from street-level imagery. In: SUNw: Scene Understanding Workshop-CVPR, vol.\u00a02017, p.\u00a05 (2017)"}],"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_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,15]],"date-time":"2025-06-15T14:07:44Z","timestamp":1749996464000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70552-6_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031705519","9783031705526"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70552-6_18","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"}}]}}