{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T16:43:42Z","timestamp":1742921022786,"version":"3.40.3"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031204968"},{"type":"electronic","value":"9783031204975"}],"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\/978-3-031-20497-5_12","type":"book-chapter","created":{"date-parts":[[2022,12,16]],"date-time":"2022-12-16T12:09:06Z","timestamp":1671192546000},"page":"142-153","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Scene Text Recognition with\u00a0Single-Point Decoding Network"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7923-2602","authenticated-orcid":false,"given":"Lei","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2663-8830","authenticated-orcid":false,"given":"Haibo","family":"Qin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7030-1974","authenticated-orcid":false,"given":"Shi-Xue","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6297-4500","authenticated-orcid":false,"given":"Chun","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0023-0220","authenticated-orcid":false,"given":"Xucheng","family":"Yin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,12,17]]},"reference":[{"key":"12_CR1","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv:1409.0473 (2014)"},{"key":"12_CR2","doi-asserted-by":"crossref","unstructured":"Cheng, Z., Bai, F., Xu, Y., Zheng, G., Pu, S., Zhou, S.: Focusing attention: towards accurate text recognition in natural images. In: ICCV, pp. 5076\u20135084 (2017)","DOI":"10.1109\/ICCV.2017.543"},{"key":"12_CR3","doi-asserted-by":"crossref","unstructured":"Cheng, Z., Xu, Y., Bai, F., Niu, Y., Pu, S., Zhou, S.: Aon: towards arbitrarily-oriented text recognition. In: CVPR, pp. 5571\u20135579 (2018)","DOI":"10.1109\/CVPR.2018.00584"},{"key":"12_CR4","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":"12_CR5","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: ICML, pp. 369\u2013376 (2006)","DOI":"10.1145\/1143844.1143891"},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Gupta, A., Vedaldi, A., Zisserman, A.: Synthetic data for text localisation in natural images. In: CVPR, pp. 2315\u20132324 (2016)","DOI":"10.1109\/CVPR.2016.254"},{"issue":"11","key":"12_CR7","first-page":"6890","volume":"22","author":"JB Hou","year":"2020","unstructured":"Hou, J.B., et al.: Detecting text in scene and traffic guide panels with attention anchor mechanism. TITS 22(11), 6890\u20136899 (2020)","journal-title":"TITS"},{"key":"12_CR8","unstructured":"Jaderberg, M., Simonyan, K., Vedaldi, A., Zisserman, A.: Synthetic data and artificial neural networks for natural scene text recognition. arXiv:1406.2227 (2014)"},{"key":"12_CR9","first-page":"2017","volume":"28","author":"M Jaderberg","year":"2015","unstructured":"Jaderberg, M., Simonyan, K., Zisserman, A., et al.: Spatial transformer networks. NIPS 28, 2017\u20132025 (2015)","journal-title":"NIPS"},{"key":"12_CR10","doi-asserted-by":"crossref","unstructured":"Jaderberg, M., Vedaldi, A., Zisserman, A.: Deep features for text spotting. In: ECCV, pp. 512\u2013528 (2014)","DOI":"10.1007\/978-3-319-10593-2_34"},{"key":"12_CR11","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":"12_CR12","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":"12_CR13","unstructured":"Kim, Y., Denton, C., Hoang, L., Rush, A.M.: Structured attention networks. arXiv:1702.00887 (2017)"},{"key":"12_CR14","doi-asserted-by":"crossref","unstructured":"Lee, C.Y., Osindero, S.: Recursive recurrent nets with attention modeling for ocr in the wild. In: CVPR, pp. 2231\u20132239 (2016)","DOI":"10.1109\/CVPR.2016.245"},{"key":"12_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: CVPR Workshops, pp. 546\u2013547 (2020)","DOI":"10.1109\/CVPRW50498.2020.00281"},{"key":"12_CR16","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 (2019)","DOI":"10.1609\/aaai.v33i01.33018610"},{"key":"12_CR17","doi-asserted-by":"crossref","unstructured":"Liao, M., et al.: Scene text recognition from two-dimensional perspective. In: AAAI, vol. 33, pp. 8714\u20138721 (2019)","DOI":"10.1609\/aaai.v33i01.33018714"},{"key":"12_CR18","doi-asserted-by":"publisher","first-page":"107980","DOI":"10.1016\/j.patcog.2021.107980","volume":"117","author":"N Lu","year":"2021","unstructured":"Lu, N., et al.: Master: multi-aspect non-local network for scene text recognition. Pattern Recogn. 117, 107980 (2021)","journal-title":"Pattern Recogn."},{"key":"12_CR19","doi-asserted-by":"crossref","unstructured":"Neumann, L., Matas, J.: Real-time scene text localization and recognition. In: CVPR, pp. 3538\u20133545 (2012)","DOI":"10.1109\/CVPR.2012.6248097"},{"key":"12_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: ICCV, pp. 569\u2013576 (2013)","DOI":"10.1109\/ICCV.2013.76"},{"key":"12_CR21","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, pp. 13528\u201313537 (2020)","DOI":"10.1109\/CVPR42600.2020.01354"},{"issue":"18","key":"12_CR22","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":"12_CR23","doi-asserted-by":"crossref","unstructured":"Sheng, F., Chen, Z., Xu, B.: Nrtr: a no-recurrence sequence-to-sequence model for scene text recognition. In: ICDAR, pp. 781\u2013786. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00130"},{"issue":"11","key":"12_CR24","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. TPAMI 39(11), 2298\u20132304 (2016)","journal-title":"TPAMI"},{"key":"12_CR25","doi-asserted-by":"crossref","unstructured":"Shi, B., Wang, X., Lyu, P., Yao, C., Bai, X.: Robust scene text recognition with automatic rectification. In: CVPR, pp. 4168\u20134176 (2016)","DOI":"10.1109\/CVPR.2016.452"},{"issue":"9","key":"12_CR26","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. TPAMI 41(9), 2035\u20132048 (2018)","journal-title":"TPAMI"},{"key":"12_CR27","unstructured":"Wang, K., Babenko, B., Belongie, S.: End-to-end scene text recognition. In: ICCV, pp. 1457\u20131464. IEEE (2011)"},{"key":"12_CR28","doi-asserted-by":"crossref","unstructured":"Wang, K., Belongie, S.: Word spotting in the wild. In: ECCV, pp. 591\u2013604 (2010)","DOI":"10.1007\/978-3-642-15549-9_43"},{"key":"12_CR29","doi-asserted-by":"crossref","unstructured":"Wang, T., et al.: Decoupled attention network for text recognition. In: AAAI, vol. 34, pp. 12216\u201312224 (2020)","DOI":"10.1609\/aaai.v34i07.6903"},{"key":"12_CR30","doi-asserted-by":"crossref","unstructured":"Wang, T., et al.: Implicit feature alignment: learn to convert text recognizer to text spotter. In: CVPR, pp. 5973\u20135982 (2021)","DOI":"10.1109\/CVPR46437.2021.00591"},{"key":"12_CR31","doi-asserted-by":"crossref","unstructured":"Warps, F.L.B.P.: Thin-plate splines and the decompositions of deformations. TPAMI 11(6) (1989)","DOI":"10.1109\/34.24792"},{"key":"12_CR32","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":"12_CR33","doi-asserted-by":"crossref","unstructured":"Zhang, S.X., Zhu, X., Chen, L., Hou, J.B., Yin, X.C.: Arbitrary shape text detection via segmentation with probability maps. TPAMI (2022)","DOI":"10.1109\/TPAMI.2022.3176122"},{"key":"12_CR34","doi-asserted-by":"crossref","unstructured":"Zhang, S.X., et al.: Deep relational reasoning graph network for arbitrary shape text detection. In: CVPR, pp. 9699\u20139708 (2020)","DOI":"10.1109\/CVPR42600.2020.00972"},{"key":"12_CR35","doi-asserted-by":"crossref","unstructured":"Zhang, S.X., Zhu, X., Yang, C., Wang, H., Yin, X.C.: Adaptive boundary proposal network for arbitrary shape text detection. In: ICCV, pp. 1305\u20131314 (2021)","DOI":"10.1109\/ICCV48922.2021.00134"},{"key":"12_CR36","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1016\/j.ins.2019.12.013","volume":"515","author":"X Zhu","year":"2020","unstructured":"Zhu, X., Li, Z., Li, X., Li, S., Dai, F.: Attention-aware perceptual enhancement nets for low-resolution image classification. Inf. Sci. 515, 233\u2013247 (2020)","journal-title":"Inf. Sci."},{"key":"12_CR37","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107619","volume":"110","author":"X Zhu","year":"2021","unstructured":"Zhu, X., Li, Z., Lou, J., Shen, Q.: Video super-resolution based on a spatio-temporal matching network. Pattern Recogn. 110, 107619 (2021)","journal-title":"Pattern Recogn."},{"key":"12_CR38","doi-asserted-by":"crossref","unstructured":"Zhu, X., Li, Z., Zhang, X.Y., Li, C., Liu, Y., Xue, Z.: Residual invertible spatio-temporal network for video super-resolution. In: AAAI, vol. 33, pp. 5981\u20135988 (2019)","DOI":"10.1609\/aaai.v33i01.33015981"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20497-5_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,16]],"date-time":"2022-12-16T12:16:02Z","timestamp":1671192962000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20497-5_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031204968","9783031204975"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20497-5_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"17 December 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CAAI International Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Beijing","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"27 August 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cicai2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/cicai.caai.cn\/#\/","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":"472","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":"164","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":"35% - 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":"3.1","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":"3.7","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)"}}]}}