{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T01:40:06Z","timestamp":1792460406288,"version":"4.5.0"},"publisher-location":"Cham","reference-count":50,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031198144","type":"print"},{"value":"9783031198151","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-031-19815-1_28","type":"book-chapter","created":{"date-parts":[[2022,10,19]],"date-time":"2022-10-19T19:11:54Z","timestamp":1666206714000},"page":"481-497","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["Pure Transformer with\u00a0Integrated Experts for\u00a0Scene Text Recognition"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8117-105X","authenticated-orcid":false,"given":"Yew Lee","family":"Tan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9728-9511","authenticated-orcid":false,"given":"Adams Wai-Kin","family":"Kong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6024-0047","authenticated-orcid":false,"given":"Jung-Jae","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,10,20]]},"reference":[{"key":"28_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1007\/978-3-030-86549-8_21","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"R Atienza","year":"2021","unstructured":"Atienza, R.: Vision transformer for fast and efficient scene text recognition. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12821, pp. 319\u2013334. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86549-8_21"},{"key":"28_CR2","doi-asserted-by":"crossref","unstructured":"Baek, J., Matsui, Y., Aizawa, K.: What if we only use real datasets for scene text recognition? Toward scene text recognition with fewer labels. In: CVPR, pp. 3113\u20133122 (2021)","DOI":"10.1109\/CVPR46437.2021.00313"},{"key":"28_CR3","unstructured":"Bartz, C., Bethge, J., Yang, H., Meinel, C.: Kiss: keeping it simple for scene text recognition. arXiv preprint arXiv:1911.08400 (2019)"},{"key":"28_CR4","doi-asserted-by":"crossref","unstructured":"Cao, Y., Xu, J., Lin, S., Wei, F., Hu, H.: GCNet: non-local networks meet squeeze-excitation networks and beyond. In: ICCVW (2019)","DOI":"10.1109\/ICCVW.2019.00246"},{"issue":"2","key":"28_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3440756","volume":"54","author":"X Chen","year":"2021","unstructured":"Chen, X., Jin, L., Zhu, Y., Luo, C., Wang, T.: Text recognition in the wild: a survey. ACM Comput. Surv. 54(2), 1\u201335 (2021)","journal-title":"ACM Comput. Surv."},{"key":"28_CR6","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"28_CR7","doi-asserted-by":"crossref","unstructured":"Ezaki, N., Kiyota, K., Minh, B.T., Bulacu, M., Schomaker, L.: Improved text-detection methods for a camera-based text reading system for blind persons. In: ICDAR, pp. 257\u2013261 (2005)","DOI":"10.1109\/ICDAR.2005.137"},{"key":"28_CR8","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: CVPR, pp. 7098\u20137107 (2021)","DOI":"10.1109\/CVPR46437.2021.00702"},{"key":"28_CR9","doi-asserted-by":"crossref","unstructured":"Fu, Z., Xie, H., Jin, G., Guo, J.: Look back again: dual parallel attention network for accurate and robust scene text recognition. In: ICMR, pp. 638\u2013644 (2021)","DOI":"10.1145\/3460426.3463674"},{"key":"28_CR10","doi-asserted-by":"crossref","unstructured":"Gomez, R., et al.: ICDAR 2017 robust reading challenge on coco-text. In: ICDAR, vol. 1, pp. 1435\u20131443 (2017)","DOI":"10.1109\/ICDAR.2017.234"},{"key":"28_CR11","doi-asserted-by":"publisher","unstructured":"Gupta, A., Vedaldi, A., Zisserman, A.: Synthetic data for text localisation in natural images. In: CVPR, pp. 2315\u20132324 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.254","DOI":"10.1109\/CVPR.2016.254"},{"key":"28_CR12","doi-asserted-by":"crossref","unstructured":"Gurari, D., et al.: Vizwiz grand challenge: answering visual questions from blind people. In: CVPR, pp. 3608\u20133617 (2018)","DOI":"10.1109\/CVPR.2018.00380"},{"issue":"8","key":"28_CR13","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"28_CR14","doi-asserted-by":"crossref","unstructured":"Hu, W., Cai, X., Hou, J., Yi, S., Lin, Z.: GTC: guided training of CTC towards efficient and accurate scene text recognition. In: AAAI, vol. 34, pp. 11005\u201311012 (2020)","DOI":"10.1609\/aaai.v34i07.6735"},{"issue":"10","key":"28_CR15","doi-asserted-by":"publisher","first-page":"e0240592","DOI":"10.1371\/journal.pone.0240592","volume":"15","author":"D Huang","year":"2020","unstructured":"Huang, D., Lang, Y., Liu, T.: Evolving population distribution in China\u2019s border regions: spatial differences, driving forces and policy implications. PLoS ONE 15(10), e0240592 (2020)","journal-title":"PLoS ONE"},{"key":"28_CR16","unstructured":"Jaderberg, M., Simonyan, K., Vedaldi, A., Zisserman, A.: Synthetic data and artificial neural networks for natural scene text recognition. arXiv preprint arXiv:1406.2227 (2014)"},{"key":"28_CR17","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et al.: ICDAR 2015 competition on robust reading. In: ICDAR, pp. 1156\u20131160 (2015)","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"28_CR18","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et al.: ICDAR 2013 robust reading competition. In: ICDAR, pp. 1484\u20131493 (2013)","DOI":"10.1109\/ICDAR.2013.221"},{"key":"28_CR19","unstructured":"Ke, G., He, D., Liu, T.Y.: Rethinking positional encoding in language pre-training. In: ICLR (2020)"},{"key":"28_CR20","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: CVPRW, pp. 546\u2013547 (2020)","DOI":"10.1109\/CVPRW50498.2020.00281"},{"key":"28_CR21","doi-asserted-by":"crossref","unstructured":"Li, H., Wang, P., Shen, C., Zhang, G.: Show, attend and read: a simple and strong baseline for irregular text recognition. In: AAAI, vol. 33, pp. 8610\u20138617, July 2019","DOI":"10.1609\/aaai.v33i01.33018610"},{"issue":"1","key":"28_CR22","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1007\/s11263-020-01369-0","volume":"129","author":"S Long","year":"2021","unstructured":"Long, S., He, X., Yao, C.: Scene text detection and recognition: The deep learning era. IJCV 129(1), 161\u2013184 (2021)","journal-title":"IJCV"},{"key":"28_CR23","doi-asserted-by":"crossref","unstructured":"Lu, N., et al.: Master: multi-aspect non-local network for scene text recognition. PR 117, 107980 (2021)","DOI":"10.1016\/j.patcog.2021.107980"},{"key":"28_CR24","doi-asserted-by":"crossref","unstructured":"Luo, C., Jin, L., Sun, Z.: Moran: a multi-object rectified attention network for scene text recognition. PR 90, 109\u2013118 (2019)","DOI":"10.1016\/j.patcog.2019.01.020"},{"issue":"4","key":"28_CR25","doi-asserted-by":"publisher","first-page":"960","DOI":"10.1007\/s11263-020-01411-1","volume":"129","author":"C Luo","year":"2021","unstructured":"Luo, C., Lin, Q., Liu, Y., Jin, L., Shen, C.: Separating content from style using adversarial learning for recognizing text in the wild. IJCV 129(4), 960\u2013976 (2021)","journal-title":"IJCV"},{"key":"28_CR26","doi-asserted-by":"crossref","unstructured":"Mishra, A., Alahari, K., Jawahar, C.: Scene text recognition using higher order language priors. In: BMVC (2012)","DOI":"10.5244\/C.26.127"},{"key":"28_CR27","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: ICDAR, pp. 1582\u20131587. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00254"},{"key":"28_CR28","doi-asserted-by":"publisher","unstructured":"Phan, T.Q., Shivakumara, P., Tian, S., Tan, C.L.: Recognizing text with perspective distortion in natural scenes. In: ICCV, pp. 569\u2013576 (2013). https:\/\/doi.org\/10.1109\/ICCV.2013.76","DOI":"10.1109\/ICCV.2013.76"},{"key":"28_CR29","doi-asserted-by":"crossref","unstructured":"Qiao, Z., et al.: Pimnet: a parallel, iterative and mimicking network for scene text recognition. In: ACMMM, pp. 2046\u20132055 (2021)","DOI":"10.1145\/3474085.3475238"},{"key":"28_CR30","doi-asserted-by":"crossref","unstructured":"Qiao, Z., Zhou, Y., Yang, D., Zhou, Y., Wang, W.: Seed: semantics enhanced encoder-decoder framework for scene text recognition. In: CVPR, June 2020","DOI":"10.1109\/CVPR42600.2020.01354"},{"key":"28_CR31","doi-asserted-by":"crossref","unstructured":"Raisi, Z., Naiel, M.A., Younes, G., Wardell, S., Zelek, J.: 2LSPE: 2D learnable sinusoidal positional encoding using transformer for scene text recognition. In: CRV, pp. 119\u2013126 (2021)","DOI":"10.1109\/CRV52889.2021.00024"},{"key":"28_CR32","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.1016\/j.eswa.2014.07.008. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0957417414004060","DOI":"10.1016\/j.eswa.2014.07.008"},{"key":"28_CR33","doi-asserted-by":"crossref","unstructured":"Schulz, R., et al.: Robot navigation using human cues: a robot navigation system for symbolic goal-directed exploration. In: ICRA, pp. 1100\u20131105 (2015)","DOI":"10.1109\/ICRA.2015.7139313"},{"issue":"11","key":"28_CR34","doi-asserted-by":"publisher","first-page":"2298","DOI":"10.1109\/TPAMI.2016.2646371","volume":"39","author":"B Shi","year":"2016","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. PAMI 39(11), 2298\u20132304 (2016)","journal-title":"PAMI"},{"issue":"9","key":"28_CR35","doi-asserted-by":"publisher","first-page":"2035","DOI":"10.1109\/TPAMI.2018.2848939","volume":"41","author":"B Shi","year":"2018","unstructured":"Shi, B., Yang, M., Wang, X., Lyu, P., Yao, C., Bai, X.: Aster: an attentional scene text recognizer with flexible rectification. PAMI 41(9), 2035\u20132048 (2018)","journal-title":"PAMI"},{"key":"28_CR36","doi-asserted-by":"crossref","unstructured":"Tsai, S.S., Chen, H., Chen, D., Schroth, G., Grzeszczuk, R., Girod, B.: Mobile visual search on printed documents using text and low bit-rate features. In: ICIP, pp. 2601\u20132604 (2011)","DOI":"10.1109\/ICIP.2011.6116198"},{"key":"28_CR37","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NIPS, vol. 30 (2017)"},{"key":"28_CR38","doi-asserted-by":"crossref","unstructured":"Wan, Z., He, M., Chen, H., Bai, X., Yao, C.: Textscanner: reading characters in order for robust scene text recognition. In: AAAI, vol. 34, pp. 12120\u201312127, April 2020","DOI":"10.1609\/aaai.v34i07.6891"},{"key":"28_CR39","doi-asserted-by":"crossref","unstructured":"Wang, K., Babenko, B., Belongie, S.: End-to-end scene text recognition. In: ICCV, pp. 1457\u20131464 (2011)","DOI":"10.1109\/ICCV.2011.6126402"},{"key":"28_CR40","doi-asserted-by":"publisher","unstructured":"Wang, T., et al.: Decoupled attention network for text recognition. In: AAAI, vol. 34, pp. 12216\u201312224, April 2020. https:\/\/doi.org\/10.1609\/aaai.v34i07.6903","DOI":"10.1609\/aaai.v34i07.6903"},{"key":"28_CR41","doi-asserted-by":"crossref","unstructured":"Wang, Y., Xie, H., Fang, S., Wang, J., Zhu, S., Zhang, Y.: From two to one: a new scene text recognizer with visual language modeling network. In: ICCV, pp. 14194\u201314203 (2021)","DOI":"10.1109\/ICCV48922.2021.01393"},{"key":"28_CR42","doi-asserted-by":"crossref","unstructured":"Wu, L., Liu, X., Hao, Y., Ma, Y., Hong, R.: Naster: non-local attentional scene text recognizer. In: ICMR, pp. 331\u2013338 (2021)","DOI":"10.1145\/3460426.3463623"},{"key":"28_CR43","doi-asserted-by":"crossref","unstructured":"Yan, R., Peng, L., Xiao, S., Yao, G.: Primitive representation learning for scene text recognition. In: CVPR, pp. 284\u2013293 (2021)","DOI":"10.1109\/CVPR46437.2021.00035"},{"key":"28_CR44","doi-asserted-by":"crossref","unstructured":"Yang, M., et al.: Symmetry-constrained rectification network for scene text recognition. In: ICCV, October 2019","DOI":"10.1109\/ICCV.2019.00924"},{"key":"28_CR45","doi-asserted-by":"crossref","unstructured":"Yu, D., et al.: Towards accurate scene text recognition with semantic reasoning networks. In: CVPR, pp. 12113\u201312122 (2020)","DOI":"10.1109\/CVPR42600.2020.01213"},{"key":"28_CR46","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1007\/978-3-030-58529-7_9","volume-title":"Computer Vision \u2013 ECCV 2020","author":"X Yue","year":"2020","unstructured":"Yue, X., Kuang, Z., Lin, C., Sun, H., Zhang, W.: RobustScanner: dynamically enhancing positional clues for robust text recognition. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12364, pp. 135\u2013151. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58529-7_9"},{"key":"28_CR47","doi-asserted-by":"crossref","unstructured":"Zhan, F., Lu, S.: ESIR: end-to-end scene text recognition via iterative image rectification. In: CVPR, June 2019","DOI":"10.1109\/CVPR.2019.00216"},{"key":"28_CR48","doi-asserted-by":"crossref","unstructured":"Zhang, C., et al.: Spin: structure-preserving inner offset network for scene text recognition. In: AAAI, vol. 35, pp. 3305\u20133314 (2021)","DOI":"10.1609\/aaai.v35i4.16442"},{"key":"28_CR49","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"751","DOI":"10.1007\/978-3-030-58586-0_44","volume-title":"Computer Vision \u2013 ECCV 2020","author":"H Zhang","year":"2020","unstructured":"Zhang, H., Yao, Q., Yang, M., Xu, Y., Bai, X.: AutoSTR: efficient backbone search for scene text recognition. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12369, pp. 751\u2013767. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58586-0_44"},{"key":"28_CR50","doi-asserted-by":"crossref","unstructured":"Zhang, M., Ma, M., Wang, P.: Scene text recognition with cascade attention network. In: ICMR, pp. 385\u2013393 (2021)","DOI":"10.1145\/3460426.3463639"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19815-1_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T01:03:00Z","timestamp":1792458180000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/chapter\/10.1007\/978-3-031-19815-1_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031198144","9783031198151"],"references-count":50,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19815-1_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"20 October 2022","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":"This content has been made available to all.","name":"free","label":"Free to read"}]}}