{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T07:19:44Z","timestamp":1760080784198,"version":"3.40.3"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031250682"},{"type":"electronic","value":"9783031250699"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-25069-9_20","type":"book-chapter","created":{"date-parts":[[2023,2,14]],"date-time":"2023-02-14T00:15:46Z","timestamp":1676333746000},"page":"297-313","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Task Grouping for\u00a0Multilingual Text Recognition"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3488-3641","authenticated-orcid":false,"given":"Jing","family":"Huang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0221-9108","authenticated-orcid":false,"given":"Kevin J.","family":"Liang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3707-1983","authenticated-orcid":false,"given":"Rama","family":"Kovvuri","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2275-1406","authenticated-orcid":false,"given":"Tal","family":"Hassner","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,2,14]]},"reference":[{"key":"20_CR1","doi-asserted-by":"crossref","unstructured":"Aldous, D.J.: Exchangeability and related topics. In: \u00c9cole d\u2019\u00c9t\u00e9 de Probabilit\u00e9s de Saint-Flour XIII \u2014 1983 (1985)","DOI":"10.1007\/BFb0099420"},{"key":"20_CR2","doi-asserted-by":"crossref","unstructured":"Baek, Y., Lee, B., Han, D., Yun, S., Lee, H.: Character region awareness for text detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 9365\u20139374 (2019)","DOI":"10.1109\/CVPR.2019.00959"},{"key":"20_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1007\/978-3-030-58526-6_30","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Baek","year":"2020","unstructured":"Baek, Y., et al.: Character region attention for text spotting. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12374, pp. 504\u2013521. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58526-6_30"},{"key":"20_CR4","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)"},{"key":"20_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1007\/978-3-030-21074-8_11","volume-title":"Computer Vision \u2013 ACCV 2018 Workshops","author":"M Bu\u0161ta","year":"2019","unstructured":"Bu\u0161ta, M., Patel, Y., Matas, J.: E2E-MLT - an unconstrained end-to-end method for multi-language scene text. In: Carneiro, G., You, S. (eds.) ACCV 2018. LNCS, vol. 11367, pp. 127\u2013143. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-21074-8_11"},{"key":"20_CR6","doi-asserted-by":"crossref","unstructured":"Caruana, R.: Multitask learning. Machine Learn. 28(1), 41\u201375 (1997)","DOI":"10.1023\/A:1007379606734"},{"key":"20_CR7","doi-asserted-by":"crossref","unstructured":"Ch\u2019ng, C.K., Chan, C.S.: Total-text: a comprehensive dataset for scene text detection and recognition. In: International Conference on Document Analysis and Recognition, vol. 1, pp. 935\u2013942. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.157"},{"key":"20_CR8","doi-asserted-by":"crossref","unstructured":"Chng, C.K., et al.: ICDAR 2019 robust reading challenge on arbitrary-shaped text-RRC-ArT. In: International Conference on Document Analysis and Recognition, pp. 1571\u20131576. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00252"},{"key":"20_CR9","doi-asserted-by":"crossref","unstructured":"Evgeniou, T., Pontil, M.: Regularized multi-task learning. In: Proceedings of the International Conference on Knowledge Discovery and Data Mining, pp. 109\u2013117 (2004)","DOI":"10.1145\/1014052.1014067"},{"key":"20_CR10","unstructured":"Ghahramani, Z., Griffiths, T.L.: Infinite latent feature models and the indian buffet process. In: Neural Information Processing Systems (2006)"},{"key":"20_CR11","doi-asserted-by":"crossref","unstructured":"Graves, A., Fern\u00e1ndez, S., Gomez, F., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: International Conference on Machine Learning, pp. 369\u2013376 (2006)","DOI":"10.1145\/1143844.1143891"},{"key":"20_CR12","doi-asserted-by":"crossref","unstructured":"He, P., Huang, W., Qiao, Y., Loy, C.C., Tang, X.: Reading scene text in deep convolutional sequences. In: AAAI, pp. 3501\u20133508 (2016)","DOI":"10.1609\/aaai.v30i1.10465"},{"key":"20_CR13","doi-asserted-by":"crossref","unstructured":"Huang, J., et al.: A multiplexed network for end-to-end, multilingual OCR. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 4547\u20134557 (2021)","DOI":"10.1109\/CVPR46437.2021.00452"},{"key":"20_CR14","unstructured":"Inkawhich, N., Liang, K., Carin, L., Chen, Y.: Transferable perturbations of deep feature distributions. In: International Conference on Learning Representations (2020)"},{"key":"20_CR15","unstructured":"Jang, E., Gu, S., Poole, B.: Categorical reparameterization with gumbel-softmax. arXiv preprint arXiv:1611.01144 (2016)"},{"key":"20_CR16","unstructured":"Jiang, Y., et al.: R2CNN: rotational region CNN for orientation robust scene text detection. arXiv preprint arXiv:1706.09579 (2017)"},{"key":"20_CR17","unstructured":"Kang, Z., Grauman, K., Sha, F.: Learning with whom to share in multi-task feature learning. In: International Conference on Machine Learning, pp. 521\u2013528 (2011)"},{"key":"20_CR18","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et al.: ICDAR 2015 competition on robust reading. In: International Conference on Document Analysis and Recognition, pp. 1156\u20131160. IEEE (2015)","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"20_CR19","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et al.: ICDAR 2013 robust reading competition. In: International Conference on Document Analysis and Recognition, pp. 1484\u20131493. IEEE (2013)","DOI":"10.1109\/ICDAR.2013.221"},{"key":"20_CR20","unstructured":"Kumar, A., Daum\u00e9 III, H.: Learning task grouping and overlap in multi-task learning. In: International Conference on Machine Learning, pp. 1723\u20131730 (2012)"},{"key":"20_CR21","unstructured":"LeCun, Y.: The MNIST database of handwritten digits. http:\/\/yann.lecun.com\/exdb\/mnist\/ (1998)"},{"key":"20_CR22","doi-asserted-by":"crossref","unstructured":"Lee, C.Y., Osindero, S.: Recursive recurrent nets with attention modeling for OCR in the wild. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2231\u20132239 (2016)","DOI":"10.1109\/CVPR.2016.245"},{"issue":"2","key":"20_CR23","doi-asserted-by":"publisher","first-page":"532","DOI":"10.1109\/TPAMI.2019.2937086","volume":"43","author":"M Liao","year":"2021","unstructured":"Liao, M., Lyu, P., He, M., Yao, C., Wu, W., Bai, X.: Mask textspotter: an end-to-end trainable neural network for spotting text with arbitrary shapes. IEEE Trans. Pattern Anal. Mach. Intell. 43(2), 532\u2013548 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"20_CR24","doi-asserted-by":"crossref","unstructured":"Liao, M., Pang, G., Huang, J., Hassner, T., Bai, X.: Mask textspotter v3: segmentation proposal network for robust scene text spotting. arXiv preprint arXiv:2007.09482 (2020)","DOI":"10.1007\/978-3-030-58621-8_41"},{"key":"20_CR25","doi-asserted-by":"crossref","unstructured":"Liu, X., Liang, D., Yan, S., Chen, D., Qiao, Y., Yan, J.: FOTS: fast oriented text spotting with a unified network. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 5676\u20135685 (2018)","DOI":"10.1109\/CVPR.2018.00595"},{"issue":"1","key":"20_CR26","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1007\/s11263-020-01369-0","volume":"129","author":"S Long","year":"2020","unstructured":"Long, S., He, X., Yao, C.: Scene text detection and recognition: the deep learning era. Int. J. Comput. Vis. 129(1), 161\u2013184 (2020). https:\/\/doi.org\/10.1007\/s11263-020-01369-0","journal-title":"Int. J. Comput. Vis."},{"issue":"11","key":"20_CR27","doi-asserted-by":"publisher","first-page":"3111","DOI":"10.1109\/TMM.2018.2818020","volume":"20","author":"J Ma","year":"2018","unstructured":"Ma, J., et al.: Arbitrary-oriented scene text detection via rotation proposals. IEEE Trans. Multimedia 20(11), 3111\u20133122 (2018)","journal-title":"IEEE Trans. Multimedia"},{"key":"20_CR28","unstructured":"Mehta, N., Liang, K., Verma, V.K., Carin, L.: Continual learning using a Bayesian nonparametric dictionary of weight factors. In: International Conference on Artificial Intelligence and Statistics (2021)"},{"key":"20_CR29","doi-asserted-by":"crossref","unstructured":"Nayef, N., et al.: ICDAR 2019 robust reading challenge on multi-lingual scene text detection and recognition-RRC-MLT-2019. In: International Conference on Document Analysis and Recognition, pp. 1582\u20131587. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00254"},{"key":"20_CR30","doi-asserted-by":"crossref","unstructured":"Nayef, N., et al.: ICDAR 2017 robust reading challenge on multi-lingual scene text detection and script identification-RRC-MLT. In: International Conference on Document Analysis and Recognition, vol. 1, pp. 1454\u20131459. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.237"},{"key":"20_CR31","doi-asserted-by":"crossref","unstructured":"Parisi, G.I., Kemker, R., Part, J.L., Kanan, C., Wermter, S.: Continual Lifelong Learning with Neural Networks: a Review. Neural Netw. 113, 54\u201371 (2019)","DOI":"10.1016\/j.neunet.2019.01.012"},{"key":"20_CR32","doi-asserted-by":"crossref","unstructured":"Qin, S., Bissacco, A., Raptis, M., Fujii, Y., Xiao, Y.: Towards unconstrained end-to-end text spotting. In: International Conference on Computer Vision, pp. 4704\u20134714 (2019)","DOI":"10.1109\/ICCV.2019.00480"},{"key":"20_CR33","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91\u201399 (2015)"},{"key":"20_CR34","doi-asserted-by":"crossref","unstructured":"Shi, B., Wang, X., Lyu, P., Yao, C., Bai, X.: Robust scene text recognition with automatic rectification. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 4168\u20134176 (2016)","DOI":"10.1109\/CVPR.2016.452"},{"key":"20_CR35","doi-asserted-by":"crossref","unstructured":"Shi, B., et al.: ICDAR 2017 competition on reading Chinese text in the wild (RCTW-17). In: International Conference on Document Analysis and Recognition (2017)","DOI":"10.1109\/ICDAR.2017.233"},{"key":"20_CR36","doi-asserted-by":"crossref","unstructured":"Strezoski, G., van Noord, N., Marcel, W.: Learning task relatedness in multi-task learning for images in context. In: Proceedings of the International Conference on Multimedia Retrieval, pp. 78\u201386 (2019)","DOI":"10.1145\/3323873.3325009"},{"key":"20_CR37","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1007\/978-3-319-16865-4_3","volume-title":"Computer Vision \u2013 ACCV 2014","author":"B Su","year":"2015","unstructured":"Su, B., Lu, S.: Accurate scene text recognition based on recurrent neural network. In: Cremers, D., Reid, I., Saito, H., Yang, M.-H. (eds.) ACCV 2014. LNCS, vol. 9003, pp. 35\u201348. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-16865-4_3"},{"key":"20_CR38","doi-asserted-by":"crossref","unstructured":"Sun, Y., et al.: ICDAR 2019 competition on large-scale street view text with partial labeling - RRC-LSVT. In: International Conference on Document Analysis and Recognition (2019)","DOI":"10.1109\/ICDAR.2019.00250"},{"key":"20_CR39","doi-asserted-by":"crossref","unstructured":"Xing, L., Tian, Z., Huang, W., Scott, M.R.: Convolutional character networks. In: International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00922"},{"key":"20_CR40","unstructured":"Yuliang, L., Lianwen, J., Shuaitao, Z., Sheng, Z.: Detecting curve text in the wild: new dataset and new solution. arXiv preprint arXiv:1712.02170 (2017)"},{"key":"20_CR41","doi-asserted-by":"crossref","unstructured":"Zamir, A.R., Sax, A., Shen, W., Guibas, L.J., Malik, J., Savarese, S.: Taskonomy: disentangling task transfer learning. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3712\u20133722 (2018)","DOI":"10.1109\/CVPR.2018.00391"},{"key":"20_CR42","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"818","DOI":"10.1007\/978-3-319-10590-1_53","volume-title":"Computer Vision \u2013 ECCV 2014","author":"MD Zeiler","year":"2014","unstructured":"Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 818\u2013833. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10590-1_53"},{"key":"20_CR43","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1016\/j.neucom.2015.12.092","volume":"189","author":"S Zhong","year":"2016","unstructured":"Zhong, S., Pu, J., Jiang, Y.G., Feng, R., Xue, X.: Flexible multi-task learning with latent task grouping. Neurocomputing 189, 179\u2013188 (2016)","journal-title":"Neurocomputing"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-25069-9_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T17:19:19Z","timestamp":1709831959000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-25069-9_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031250682","9783031250699"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-25069-9_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"14 February 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"From the workshops, 367 reviewed full papers have been selected for publication","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}