{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T07:40:03Z","timestamp":1755848403098,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":26,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,3,10]],"date-time":"2023-03-10T00:00:00Z","timestamp":1678406400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,3,10]]},"DOI":"10.1145\/3589883.3589914","type":"proceedings-article","created":{"date-parts":[[2023,6,27]],"date-time":"2023-06-27T19:50:36Z","timestamp":1687895436000},"page":"201-207","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Are Attention blocks better than BiLSTM for text recognition?\u00a0"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-7251-0901","authenticated-orcid":false,"given":"Amine Mohamed","family":"Belhakimi","sequence":"first","affiliation":[{"name":"Idnow center of excellence, Idnow gmbh, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3665-4900","authenticated-orcid":false,"given":"Guillaume","family":"Chiron","sequence":"additional","affiliation":[{"name":"Idnow center of excellence, Idnow gmbh, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3777-374X","authenticated-orcid":false,"given":"Florian","family":"Arrestier","sequence":"additional","affiliation":[{"name":"Idnow center of excellence, Idnow gmbh, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0479-6312","authenticated-orcid":false,"given":"Ahmad Montaser","family":"Awal","sequence":"additional","affiliation":[{"name":"Idnow center of excellence, Idnow gmbh, France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,6,27]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"2304","volume-title":"TPAMI","volume":"39","author":"Shi Baoguang","unstructured":"Baoguang Shi, Xiang Bai, and Cong Yao. An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition. In TPAMI, volume 39, pages 2298\u20132304. IEEE, 2017. 1, 2, 4, 5, 10, 11, 12"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68763-2_49"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/BROADNETS.2004.8"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/358669.358692"},{"key":"e_1_3_2_1_5_1","first-page":"343","volume-title":"NIPS","author":"Wang Jianfeng","year":"2017","unstructured":"Jianfeng Wang and Xiaolin Hu. Gated recurrent convolution neural network for ocr. In NIPS, pages 334\u2013343, 2017. 1, 2, 4, 10, 11, 12"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDARW.2019.40083"},{"volume-title":"The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (June 2015)","author":"X.","key":"e_1_3_2_1_7_1","unstructured":"Liang, M., Hu, X.: Recurrent convolutional neural network for object recognition. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (June 2015)"},{"key":"e_1_3_2_1_8_1","first-page":"344","volume-title":"Hu","author":"J.","unstructured":"Wang, J., Hu, X.: Gated recurrent convolution neural network for ocr. In: Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., Garnett, R. (eds.) Advances in Neural Information Processing Systems 30, pp. 335\u2013344. Curran Associates, Inc. (2017)"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.245"},{"key":"e_1_3_2_1_10_1","first-page":"79","volume-title":"KDD","author":"Borisyuk Fedor","year":"2018","unstructured":"Fedor Borisyuk, Albert Gordo, and Viswanath Sivakumar. Rosetta: Large scale system for text detection and recognition in images. In KDD, pages 71\u201379, 2018. 1, 2, 4."},{"key":"e_1_3_2_1_11_1","volume-title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. CoRR, abs\/2010.11929. https:\/\/arxiv.org\/abs\/2010.11929","author":"N.","year":"2020","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., & Houlsby, N. (2020). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. CoRR, abs\/2010.11929. https:\/\/arxiv.org\/abs\/2010.11929"},{"key":"e_1_3_2_1_12_1","volume-title":"Mohammed","author":"Yousef Mohamed","year":"2018","unstructured":"Mohamed Yousef, Khaled F. Hussain, and Usama S. Mohammed. 2018. Accurate, Data-Efficient, Unconstrained Text Recognition with Convolutional Neural Networks. CoRR abs\/1812.11894, (2018). Retrieved from http:\/\/arxiv.org\/abs\/1812.11894"},{"key":"e_1_3_2_1_13_1","volume-title":"Highway networks","author":"Srivastava R. K.","year":"2015","unstructured":"R. K. Srivastava, K. Greff, and J. Schmidhuber, \u201cHighway networks,\u201d arXiv preprint arXiv:1505.00387, 2015."},{"key":"e_1_3_2_1_14_1","volume-title":"Highway and residual networks learn unrolled iterative estimation","author":"Greff K.","year":"2016","unstructured":"K. Greff, R. K. Srivastava, and J. Schmidhuber, \u201cHighway and residual networks learn unrolled iterative estimation,\u201d arXiv preprint arXiv:1612.07771, 2016."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10362"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86337-1"},{"key":"e_1_3_2_1_17_1","volume-title":"Workshop on Deep Learning, NIPS","author":"Jaderberg Max","year":"2014","unstructured":"Max Jaderberg, Karen Simonyan, Andrea Vedaldi, and Andrew Zisserman. Synthetic data and artificial neural networks for natural scene text recognition. In Workshop on Deep Learning, NIPS, 2014. 2"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.254"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.5244\/C.26.127"},{"key":"e_1_3_2_1_20_1","first-page":"1464","volume-title":"ICCV","author":"Wang Kai","year":"2011","unstructured":"Kai Wang, Boris Babenko, and Serge Belongie. End-to-end scene text recognition. In ICCV, pages 1457\u20131464, 2011. 3"},{"key":"e_1_3_2_1_21_1","first-page":"687","volume-title":"ICDAR","author":"Lucas Simon M","year":"2003","unstructured":"Simon M Lucas, Alex Panaretos, Luis Sosa, Anthony Tang, Shirley Wong, and Robert Young. Icdar 2003 robust reading competitions. In ICDAR, pages 682\u2013687, 2003. 3"},{"key":"e_1_3_2_1_22_1","first-page":"1493","volume-title":"ICDAR","author":"Karatzas Dimosthenis","year":"2013","unstructured":"Dimosthenis Karatzas, Faisal Shafait, Seiichi Uchida, Masakazu Iwamura, Lluis Gomez i Bigorda, Sergi Robles Mestre, Joan Mas, David Fernandez Mota, Jon Almazan Almazan, and Lluis Pere De Las Heras. Icdar 2013 robust reading competition. In ICDAR, pages 1484\u20131493, 2013. 3"},{"key":"e_1_3_2_1_23_1","first-page":"1160","volume-title":"ICDAR","author":"Karatzas Dimosthenis","year":"2015","unstructured":"Dimosthenis Karatzas, Lluis Gomez-Bigorda, Anguelos Nicolaou, Suman Ghosh, Andrew Bagdanov, Masakazu Iwamura, Jiri Matas, Lukas Neumann, Vijay Ramaseshan Chandrasekhar, Shijian Lu, Icdar 2015 competition on robust reading. In ICDAR, pages 1156\u20131160, 2015. 3"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.76"},{"key":"e_1_3_2_1_25_1","first-page":"8048","volume-title":"ESWA","volume":"41","author":"Risnumawan Anhar","unstructured":"Anhar Risnumawan, Palaiahankote Shivakumara, Chee Seng Chan, and Chew Lim Tan. A robust arbitrary text detection system for natural scene images. In ESWA, volume 41, pages 8027\u20138048. Elsevier, 2014. 3"},{"key":"e_1_3_2_1_26_1","unstructured":"Warp-ctc Baidu Research https:\/\/github.com\/baidu-research\/warp-ctc"}],"event":{"name":"ICMLT 2023: 2023 8th International Conference on Machine Learning Technologies","acronym":"ICMLT 2023","location":"Stockholm Sweden"},"container-title":["Proceedings of the 2023 8th International Conference on Machine Learning Technologies"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3589883.3589914","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3589883.3589914","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T07:04:00Z","timestamp":1755846240000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3589883.3589914"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,10]]},"references-count":26,"alternative-id":["10.1145\/3589883.3589914","10.1145\/3589883"],"URL":"https:\/\/doi.org\/10.1145\/3589883.3589914","relation":{},"subject":[],"published":{"date-parts":[[2023,3,10]]},"assertion":[{"value":"2023-06-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}