{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:34:29Z","timestamp":1777656869555,"version":"3.51.4"},"publisher-location":"Cham","reference-count":50,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585853","type":"print"},{"value":"9783030585860","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-58586-0_44","type":"book-chapter","created":{"date-parts":[[2020,11,29]],"date-time":"2020-11-29T17:02:42Z","timestamp":1606669362000},"page":"751-767","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":37,"title":["AutoSTR: Efficient Backbone Search for Scene Text Recognition"],"prefix":"10.1007","author":[{"given":"Hui","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Quanming","family":"Yao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingkun","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongchao","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiang","family":"Bai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,11,30]]},"reference":[{"key":"44_CR1","doi-asserted-by":"publisher","first-page":"2552","DOI":"10.1109\/TPAMI.2014.2339814","volume":"36","author":"J Almaz\u00e1n","year":"2014","unstructured":"Almaz\u00e1n, J., Gordo, A., Forn\u00e9s, A., Valveny, E.: Word spotting and recognition with embedded attributes. IEEE Trans. Pattern Anal. Mach. Intell. 36, 2552\u20132566 (2014)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"44_CR2","doi-asserted-by":"crossref","unstructured":"Baek, J., et al.: What is wrong with scene text recognition model comparisons? Dataset and model analysis. In: International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00481"},{"key":"44_CR3","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. Technical report arXiv preprint arXiv:1409.0473 (2014)"},{"key":"44_CR4","doi-asserted-by":"crossref","unstructured":"Bai, F., Cheng, Z., Niu, Y., Pu, S., Zhou, S.: Edit probability for scene text recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00163"},{"key":"44_CR5","unstructured":"Cai, H., Zhu, L., Han, S.: ProxylessNAS: direct neural architecture search on target task and hardware. In: International Conference on Learning Representations (2019)"},{"key":"44_CR6","unstructured":"Chen, Y., Yang, T., Zhang, X., Meng, G., Xiao, X., Sun, J.: DetNAS: backbone search for object detection. In: Advances in Neural Information Processing Systems (2019)"},{"key":"44_CR7","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: IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/ICCV.2017.543"},{"key":"44_CR8","doi-asserted-by":"crossref","unstructured":"Cheng, Z., Xu, Y., Bai, F., Niu, Y., Pu, S., Zhou, S.: Aon: towards arbitrarily-oriented text recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00584"},{"key":"44_CR9","doi-asserted-by":"crossref","unstructured":"Dutta, K., Mathew, M., Krishnan, P., Jawahar, C.: Localizing and recognizing text in lecture videos. In: International Conference on Frontiers in Handwriting Recognition (2018)","DOI":"10.1109\/ICFHR-2018.2018.00049"},{"key":"44_CR10","doi-asserted-by":"crossref","unstructured":"Elsken, T., Metzen, J.H., Hutter, F.: Neural architecture search: a survey. J. Mach. Learn. Res. (2019)","DOI":"10.1007\/978-3-030-05318-5_3"},{"key":"44_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 (2006)","DOI":"10.1145\/1143844.1143891"},{"key":"44_CR12","doi-asserted-by":"crossref","unstructured":"Guo, Z., et al.: Single path one-shot neural architecture search with uniform sampling. Technical report arXiv preprint arXiv:1904.00420 (2019)","DOI":"10.1007\/978-3-030-58517-4_32"},{"key":"44_CR13","doi-asserted-by":"crossref","unstructured":"Gupta, A., Vedaldi, A., Zisserman, A.: Synthetic data for text localisation in natural images. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2315\u20132324 (2016)","DOI":"10.1109\/CVPR.2016.254"},{"key":"44_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"44_CR15","unstructured":"Jaderberg, M., Simonyan, K., Vedaldi, A., Zisserman, A.: Synthetic data and artificial neural networks for natural scene text recognition. Technical report arXiv preprint arXiv:1406.2227 (2014)"},{"key":"44_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11263-015-0823-z","volume":"116","author":"M Jaderberg","year":"2016","unstructured":"Jaderberg, M., Simonyan, K., Vedaldi, A., Zisserman, A.: Reading text in the wild with convolutional neural networks. Int. J. Comput. Vis. 116, 1\u201320 (2016). https:\/\/doi.org\/10.1007\/s11263-015-0823-z","journal-title":"Int. J. Comput. Vis."},{"key":"44_CR17","unstructured":"Jaderberg, M., Simonyan, K., Zisserman, A., et al.: Spatial transformer networks. In: Advances in Neural Information Processing Systems (2015)"},{"key":"44_CR18","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et al.: ICDAR 2015 competition on robust reading. In: International Conference on Document Analysis and Recognition (2015)","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"44_CR19","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et al.: ICDAR 2013 robust reading competition. In: International Conference on Document Analysis and Recognition (2013)","DOI":"10.1109\/ICDAR.2013.221"},{"key":"44_CR20","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 (2016)","DOI":"10.1109\/CVPR.2016.245"},{"key":"44_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 Conference on Artificial Intelligence (2019)","DOI":"10.1609\/aaai.v33i01.33018610"},{"key":"44_CR22","unstructured":"Li, L., Talwalkar, A.: Random search and reproducibility for neural architecture search. In: Uncertainty in Artificial Intelligence (2019)"},{"key":"44_CR23","doi-asserted-by":"crossref","unstructured":"Liao, M., et al.: Scene text recognition from two-dimensional perspective. In: AAAI Conference on Artificial Intelligence (2019)","DOI":"10.1609\/aaai.v33i01.33018714"},{"key":"44_CR24","doi-asserted-by":"crossref","unstructured":"Liu, C., et al.: Auto-deeplab: hierarchical neural architecture search for semantic image segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00017"},{"key":"44_CR25","unstructured":"Liu, H., Simonyan, K., Yang, Y.: DARTS: differentiable architecture search. In: International Conference on Learning Representations (2019)"},{"key":"44_CR26","doi-asserted-by":"crossref","unstructured":"Liu, W., Chen, C., Wong, K.Y.K.: Char-net: a character-aware neural network for distorted scene text recognition. In: AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.12246"},{"key":"44_CR27","doi-asserted-by":"crossref","unstructured":"Liu, Y., Wang, Z., Jin, H., Wassell, I.: Synthetically supervised feature learning for scene text recognition. In: European Conference on Computer Vision (2018)","DOI":"10.1007\/978-3-030-01228-1_27"},{"key":"44_CR28","unstructured":"Long, S., He, X., Yao, C.: Scene text detection and recognition: the deep learning era. Technical report arXiv preprint arXiv:1811.04256 (2018)"},{"key":"44_CR29","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1007\/s10032-004-0134-3","volume":"7","author":"SM Lucas","year":"2005","unstructured":"Lucas, S.M., et al.: ICDAR 2003 robust reading competitions: entries, results, and future directions. Int. J. Doc. Anal. Recogn. 7, 105\u2013122 (2005). https:\/\/doi.org\/10.1007\/s10032-004-0134-3","journal-title":"Int. J. Doc. Anal. Recogn."},{"key":"44_CR30","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/j.patcog.2019.01.020","volume":"90","author":"C Luo","year":"2019","unstructured":"Luo, C., Jin, L., Sun, Z.: MORAN: a multi-object rectified attention network for scene text recognition. Pattern Recogn. 90, 109\u2013118 (2019)","journal-title":"Pattern Recogn."},{"key":"44_CR31","doi-asserted-by":"crossref","unstructured":"Mishra, A., Alahari, K., Jawahar, C.: Top-down and bottom-up cues for scene text recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (2012)","DOI":"10.1109\/CVPR.2012.6247990"},{"key":"44_CR32","unstructured":"Pham, H., Guan, M.Y., Zoph, B., Le, Q.V., Dean, J.: Efficient neural architecture search via parameter sharing. In: International Conference on Machine Learning (2018)"},{"key":"44_CR33","doi-asserted-by":"crossref","unstructured":"Quy Phan, T., Shivakumara, P., Tian, S., Lim Tan, C.: Recognizing text with perspective distortion in natural scenes. In: IEEE Conference on Computer Vision and Pattern Recognition (2013)","DOI":"10.1109\/ICCV.2013.76"},{"key":"44_CR34","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: Mobilenetv 2: inverted residuals and linear bottlenecks. In: IEEE Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"44_CR35","unstructured":"Sciuto, C., Yu, K., Jaggi, M., Musat, C., Salzmann, M.: Evaluating the search phase of neural architecture search. In: International Conference on Learning Representations (2020)"},{"key":"44_CR36","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, 2298\u20132304 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"44_CR37","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 (2016)","DOI":"10.1109\/CVPR.2016.452"},{"key":"44_CR38","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. IEEE Trans. Pattern Anal. Mach. Intell. 41, 2035\u20132048 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"44_CR39","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. Technical report arXiv preprint arXiv:1409.1556 (2014)"},{"key":"44_CR40","unstructured":"Wang, K., Babenko, B., Belongie, S.: End-to-end scene text recognition. In: International Conference on Computer Vision (2011)"},{"key":"44_CR41","first-page":"14","volume":"2018","author":"F Xie","year":"2018","unstructured":"Xie, F., Zhang, M., Zhao, J., Yang, J., Liu, Y., Yuan, X.: A robust license plate detection and character recognition algorithm based on a combined feature extraction model and BPNN. J. Adv. Transp. 2018, 14 (2018)","journal-title":"J. Adv. Transp."},{"key":"44_CR42","doi-asserted-by":"crossref","unstructured":"Xie, L., Yuille, A.: Genetic CNN. In: IEEE International Conference on Computer Vision (2017)","DOI":"10.1109\/ICCV.2017.154"},{"key":"44_CR43","doi-asserted-by":"crossref","unstructured":"Yang, M., et al.: Symmetry-constrained rectification network for scene text recognition. In: IEEE International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00924"},{"key":"44_CR44","doi-asserted-by":"crossref","unstructured":"Yang, X., He, D., Zhou, Z., Kifer, D., Giles, C.L.: Learning to read irregular text with attention mechanisms. In: International Joint Conferences on Artificial Intelligence (2017)","DOI":"10.24963\/ijcai.2017\/458"},{"key":"44_CR45","doi-asserted-by":"crossref","unstructured":"Yao, Q., Xu, J., Tu, W.W., Zhu, Z.: Efficient neural architecture search via proximal iterations. In: AAAI Conference on Artificial Intelligence (2020)","DOI":"10.1609\/aaai.v34i04.6143"},{"key":"44_CR46","unstructured":"Yao, Q., Wang, M.: Taking human out of learning applications: a survey on automated machine learning. Technical report arXiv preprint arXiv:1810.13306 (2018)"},{"key":"44_CR47","unstructured":"Zeiler, M.: Adadelta: an adaptive learning rate method. Technical report arXiv preprint arXiv:1212.5701 (2012)"},{"key":"44_CR48","doi-asserted-by":"crossref","unstructured":"Zhan, F., Lu, S.: ESIR: end-to-end scene text recognition via iterative image rectification. In: IEEE Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00216"},{"key":"44_CR49","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1007\/s11704-015-4488-0","volume":"10","author":"Y Zhu","year":"2016","unstructured":"Zhu, Y., Yao, C., Bai, X.: Scene text detection and recognition: recent advances and future trends. Front. Comput. Sci. 10, 19\u201336 (2016). https:\/\/doi.org\/10.1007\/s11704-015-4488-0","journal-title":"Front. Comput. Sci."},{"key":"44_CR50","unstructured":"Zoph, B., Le, Q.V.: Neural architecture search with reinforcement learning. In: International Conference on Learning Representations (2017)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58586-0_44","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T00:18:58Z","timestamp":1732839538000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58586-0_44"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585853","9783030585860"],"references-count":50,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58586-0_44","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"30 November 2020","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":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","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":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","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":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","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":"1360","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":"27% - 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","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":"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)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic. From the ECCV Workshops 249 full papers, 18 short papers, and 21 further contributions were published out of a total of 467 submissions.","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)"}}]}}