{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T22:40:01Z","timestamp":1756852801691,"version":"3.44.0"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030861971"},{"type":"electronic","value":"9783030861988"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-86198-8_16","type":"book-chapter","created":{"date-parts":[[2021,9,3]],"date-time":"2021-09-03T20:33:19Z","timestamp":1630701199000},"page":"213-228","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CATALIST: CAmera TrAnsformations for Multi-LIngual Scene Text Recognition"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3543-1754","authenticated-orcid":false,"given":"Shivam","family":"Sood","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0773-3480","authenticated-orcid":false,"given":"Rohit","family":"Saluja","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4533-2490","authenticated-orcid":false,"given":"Ganesh","family":"Ramakrishnan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1706-5703","authenticated-orcid":false,"given":"Parag","family":"Chaudhuri","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,9,4]]},"reference":[{"key":"16_CR1","unstructured":"Abadi, M., et al.: Tensorflow: a system for large-scale machine learning. In: 12th $$\\{USENIX\\}$$ Symposium on Operating Systems Design and Implementation (OSDI 2016), pp. 265\u2013283 (2016)"},{"key":"16_CR2","unstructured":"Bartz, C., Yang, H., Meinel, C.: STN-OCR: a single neural network for text detection and text recognition. arXiv preprint arXiv:1707.08831 (2017)"},{"key":"16_CR3","doi-asserted-by":"crossref","unstructured":"Bu\u0161ta, M., Neumann, L., Matas, J.: Deep textspotter: an end-to-end trainable scene text localization and recognition framework. In: International Conference on Computer Vision (2017)","DOI":"10.1109\/ICCV.2017.242"},{"key":"16_CR4","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":"16_CR5","unstructured":"Duarte, K., Rawat, Y.S., Shah, M.: Videocapsulenet: a simplified network for action detection. arXiv preprint arXiv:1805.08162 (2018)"},{"key":"16_CR6","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":"16_CR7","volume-title":"Multiple View Geometry in Computer Vision","author":"R Hartley","year":"2003","unstructured":"Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision. Cambridge University Press, Cambridge (2003)"},{"key":"16_CR8","unstructured":"Hinton, G.E., Sabour, S., Frosst, N.: Matrix capsules with EM routing. In: International Conference on Learning Representations (2018)"},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et al.: 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":"16_CR10","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":"16_CR11","doi-asserted-by":"crossref","unstructured":"Liao, M., Shi, B., Bai, X., Wang, X., Liu, W.: Textboxes: a fast text detector with a single deep neural network. In: AAAI, pp. 4161\u20134167 (2017)","DOI":"10.1609\/aaai.v31i1.11196"},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"Milletari, F., Navab, N., Ahmadi, S.A.: V-net: fully convolutional neural networks for volumetric medical image segmentation. In: 2016 Fourth International Conference on 3D Vision (3DV), pp. 565\u2013571. IEEE (2016)","DOI":"10.1109\/3DV.2016.79"},{"key":"16_CR13","doi-asserted-by":"crossref","unstructured":"Liao, M., Shi, B., Bai, X.: TextBoxes++: a single-shot oriented scene text detector. CoRR abs\/1801.02765 (2018)","DOI":"10.1109\/TIP.2018.2825107"},{"key":"16_CR14","doi-asserted-by":"crossref","unstructured":"Reddy, S., Mathew, M., Gomez, L., Rusinol, M., Karatzas, D., Jawahar, C.: RoadText-1K: text detection & recognition dataset for driving videos. In: 2020 IEEE International Conference on Robotics and Automation (ICRA), pp. 11074\u201311080. IEEE (2020)","DOI":"10.1109\/ICRA40945.2020.9196577"},{"key":"16_CR15","doi-asserted-by":"crossref","unstructured":"Saluja, R., Maheshwari, A., Ramakrishnan, G., Chaudhuri, P., Carman, M.: Robust end-to-end systems for reading license plates and street signs. In: 2019 15th IAPR International Conference on Document Analysis and Recognition (ICDAR), pp. 154\u2013159. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00033"},{"issue":"11","key":"16_CR16","doi-asserted-by":"publisher","first-page":"2298","DOI":"10.1109\/TPAMI.2016.2646371","volume":"39","author":"B Shi","year":"2017","unstructured":"Shi, B., Bai, X., Yao, C.: An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition. IEEE Trans. Pattern Anal. Mach. Intell. 39(11), 2298\u20132304 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"16_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1007\/978-3-319-46604-0_30","volume-title":"Computer Vision \u2013 ECCV 2016 Workshops","author":"R Smith","year":"2016","unstructured":"Smith, R., et al.: End-to-end interpretation of the French street name signs dataset. In: Hua, G., J\u00e9gou, H. (eds.) ECCV 2016, Part I. LNCS, vol. 9913, pp. 411\u2013426. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46604-0_30"},{"key":"16_CR18","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132826 (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"16_CR19","doi-asserted-by":"crossref","unstructured":"Wojna, Z., et al.: Attention-based extraction of structured information from street view imagery. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 1, pp. 844\u2013850. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.143"},{"key":"16_CR20","unstructured":"Yu, F., et al.: BDD100K: a diverse driving video database with scalable annotation tooling. arXiv preprint arXiv:1805.04687, vol. 2, no. 5, p. 6 (2018)"},{"key":"16_CR21","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. 2017 (2017)"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition \u2013 ICDAR 2021 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-86198-8_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T22:13:52Z","timestamp":1756851232000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86198-8_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030861971","9783030861988"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86198-8_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"4 September 2021","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":"Lausanne","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Switzerland","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iapr.org\/icdar2021","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":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"340","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":"182","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":"54% - 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":"2.9","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":"4.9","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Additionally, 13 competition reports are included.","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)"}}]}}