{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T08:56:36Z","timestamp":1765356996025,"version":"3.44.0"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030865481"},{"type":"electronic","value":"9783030865498"}],"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.springernature.com\/gp\/researchers\/text-and-data-mining"},{"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.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-86549-8_19","type":"book-chapter","created":{"date-parts":[[2021,9,4]],"date-time":"2021-09-04T02:05:57Z","timestamp":1630721157000},"page":"287-303","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Reciprocal Feature Learning via Explicit and Implicit Tasks in Scene Text Recognition"],"prefix":"10.1007","author":[{"given":"Hui","family":"Jiang","sequence":"first","affiliation":[]},{"given":"Yunlu","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Zhanzhan","family":"Cheng","sequence":"additional","affiliation":[]},{"given":"Shiliang","family":"Pu","sequence":"additional","affiliation":[]},{"given":"Yi","family":"Niu","sequence":"additional","affiliation":[]},{"given":"Wenqi","family":"Ren","sequence":"additional","affiliation":[]},{"given":"Fei","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Wenming","family":"Tan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,9,2]]},"reference":[{"key":"19_CR1","doi-asserted-by":"crossref","unstructured":"Baek, J., et al.: What is wrong with scene text recognition model comparisons? Dataset and model analysis. In: ICCV, pp. 4714\u20134722 (2019)","DOI":"10.1109\/ICCV.2019.00481"},{"key":"19_CR2","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1162\/tacl_a_00051","volume":"5","author":"P Bojanowski","year":"2017","unstructured":"Bojanowski, P., Grave, E., Joulin, A., Mikolov, T.: Enriching word vectors with subword information. Trans. Assoc. Comput. Linguist. 5, 135\u2013146 (2017)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"19_CR3","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: ICCV Workshops, pp. 1971\u20131980 (2019)","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"19_CR4","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":"19_CR5","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":"19_CR6","doi-asserted-by":"crossref","unstructured":"Gao, Y., Huang, Z., Dai, Y., Xu, C., et al.: DSAN: double supervised network with attention mechanism for scene text recognition. In: VCIP, pp. 1\u20134 (2019)","DOI":"10.1109\/VCIP47243.2019.8965779"},{"key":"19_CR7","doi-asserted-by":"crossref","unstructured":"Graves, A., et al.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: ICML, pp. 369\u2013376 (2006)","DOI":"10.1145\/1143844.1143891"},{"key":"19_CR8","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"},{"key":"19_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Jian, S.: Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. In: ICCV, pp. 1026\u20131034 (2015)","DOI":"10.1109\/ICCV.2015.123"},{"key":"19_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"19_CR11","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: CVPR, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"19_CR12","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, pp. 11005\u201311012 (2020)","DOI":"10.1609\/aaai.v34i07.6735"},{"key":"19_CR13","unstructured":"Jaderberg, M., Simonyan, K., Vedaldi, A., et al.: Synthetic data and artificial neural networks for natural scene text recognition. CoRR abs\/1406.2227 (2014)"},{"key":"19_CR14","unstructured":"Kang, L., Riba, P., Rusi\u00f1ol, M., et al.: Pay attention to what you read: non-recurrent handwritten text-line recognition. CoRR abs\/2005.13044 (2020)"},{"key":"19_CR15","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et al.: ICDAR 2015 competition on robust reading. In: ICDAR, pp. 1156\u20131160. IEEE (2015)","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"19_CR16","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et al.: ICDAR 2013 robust reading competition. In: ICDAR, pp. 1484\u20131493. IEEE (2013)","DOI":"10.1109\/ICDAR.2013.221"},{"key":"19_CR17","doi-asserted-by":"crossref","unstructured":"Kim, S., Hori, T., Watanabe, S.: Joint CTC-attention based end-to-end speech recognition using multi-task learning. In: ICASSP, pp. 4835\u20134839 (2017)","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"19_CR18","doi-asserted-by":"crossref","unstructured":"Liao, M., et al.: Scene text recognition from two-dimensional perspective. In: AAAI, pp. 8714\u20138721 (2019)","DOI":"10.1609\/aaai.v33i01.33018714"},{"key":"19_CR19","doi-asserted-by":"crossref","unstructured":"Lucas, S.M., Panaretos, A., Sosa, L., Tang, A., Wong, S., Young, R.: ICDAR 2003 robust reading competitions. In: ICDAR, pp. 682\u2013687 (2003)","DOI":"10.1109\/ICDAR.2003.1227749"},{"key":"19_CR20","doi-asserted-by":"crossref","unstructured":"Luong, T., Pham, H., Manning, C.D.: Effective approaches to attention-based neural machine translation. In: EMNLP, pp. 1412\u20131421 (2015)","DOI":"10.18653\/v1\/D15-1166"},{"key":"19_CR21","doi-asserted-by":"crossref","unstructured":"Mishra, A., Alahari, K., Jawahar, C.: Scene text recognition using higher order language priors. In: BMVC, pp. 1\u201311 (2012)","DOI":"10.5244\/C.26.127"},{"key":"19_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1007\/978-3-030-58555-6_10","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Mou","year":"2020","unstructured":"Mou, Y., et al.: PlugNet: degradation aware scene text recognition supervised by a pluggable super-resolution unit. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12360, pp. 158\u2013174. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58555-6_10"},{"key":"19_CR23","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. 13525\u201313534 (2020)","DOI":"10.1109\/CVPR42600.2020.01354"},{"key":"19_CR24","doi-asserted-by":"crossref","unstructured":"Quy Phan, T., Shivakumara, P., Tian, S., Lim Tan, C.: Recognizing text with perspective distortion in natural scenes. In: ICCV, pp. 569\u2013576 (2013)","DOI":"10.1109\/ICCV.2013.76"},{"key":"19_CR25","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. Exp. Syst. Appl. 41, 8027\u20138048 (2014)","journal-title":"Exp. Syst. Appl."},{"key":"19_CR26","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 (2019)","DOI":"10.1109\/ICDAR.2019.00130"},{"issue":"11","key":"19_CR27","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.: An end-to-end trainable neural network for image-based sequence recognition and its application to STR. TPAMI 39(11), 2298\u20132304 (2016)","journal-title":"TPAMI"},{"issue":"9","key":"19_CR28","doi-asserted-by":"publisher","first-page":"2035","DOI":"10.1109\/TPAMI.2018.2848939","volume":"41","author":"B Shi","year":"2019","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 (2019)","journal-title":"TPAMI"},{"key":"19_CR29","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR, pp. 770\u2013778 (2015)"},{"key":"19_CR30","doi-asserted-by":"crossref","unstructured":"Su, B., Lu, S.: Accurate scene text recognition based on recurrent neural network. In: ACCV, pp. 35\u201348 (2014)","DOI":"10.1007\/978-3-319-16865-4_3"},{"key":"19_CR31","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, pp. 12120\u201312127 (2020)","DOI":"10.1609\/aaai.v34i07.6891"},{"key":"19_CR32","unstructured":"Wan, Z., Xie, F., Liu, Y., Bai, X., Yao, C.: 2D-CTC for scene text recognition. CoRR abs\/1907.09705 (2019)"},{"key":"19_CR33","doi-asserted-by":"crossref","unstructured":"Wan, Z., Zhang, J., Zhang, L., Luo, J., Yao, C.: On vocabulary reliance in scene text recognition. In: CVPR, pp. 11422\u201311431 (2020)","DOI":"10.1109\/CVPR42600.2020.01144"},{"key":"19_CR34","unstructured":"Wang, K., Babenko, B., Belongie, S.: End-to-end scene text recognition. In: ICCV, pp. 1457\u20131464 (2011)"},{"key":"19_CR35","doi-asserted-by":"crossref","unstructured":"Wang, T., et al.: Decoupled attention network for text recognition. In: AAAI, pp. 12216\u201312224 (2020)","DOI":"10.1609\/aaai.v34i07.6903"},{"key":"19_CR36","doi-asserted-by":"crossref","unstructured":"Xie, Z., Huang, Y., Zhu, Y., Jin, L., Liu, Y., Xie, L.: Aggregation cross-entropy for sequence recognition. In: CVPR, pp. 6538\u20136547 (2019)","DOI":"10.1109\/CVPR.2019.00670"},{"key":"19_CR37","doi-asserted-by":"publisher","first-page":"2789","DOI":"10.1109\/TIP.2016.2599102","volume":"25","author":"C Yao","year":"2016","unstructured":"Yao, C., Bai, X., Liu, W.: Strokelets: a learned multi-scale mid-level representation for scene text recognition. IEEE Trans. Image Process. 25, 2789\u20132802 (2016)","journal-title":"IEEE Trans. Image Process."},{"key":"19_CR38","doi-asserted-by":"crossref","unstructured":"Yu, D., Li, X., Zhang, C., Han, J., Ding, E.: Towards accurate scene text recognition with semantic reasoning networks. In: CVPR, pp. 12110\u201312119 (2020)","DOI":"10.1109\/CVPR42600.2020.01213"},{"key":"19_CR39","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":"19_CR40","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"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition \u2013 ICDAR 2021"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-86549-8_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T22:02:50Z","timestamp":1756936970000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86549-8_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030865481","9783030865498"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86549-8_19","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":"2 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)"}}]}}