{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T18:26:57Z","timestamp":1742927217429,"version":"3.40.3"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031463075"},{"type":"electronic","value":"9783031463082"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-46308-2_29","type":"book-chapter","created":{"date-parts":[[2023,10,29]],"date-time":"2023-10-29T18:01:24Z","timestamp":1698602484000},"page":"348-359","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["VQA-CLPR: Turning a\u00a0Visual Question Answering Model into\u00a0a\u00a0Chinese License Plate Recognizer"],"prefix":"10.1007","author":[{"given":"Gang","family":"Lv","sequence":"first","affiliation":[]},{"given":"Xuhao","family":"Jiang","sequence":"additional","affiliation":[]},{"given":"Yining","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Weiya","family":"Ni","sequence":"additional","affiliation":[]},{"given":"Fudong","family":"Nian","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,10,30]]},"reference":[{"key":"29_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 - 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":"29_CR2","doi-asserted-by":"crossref","unstructured":"Azadbakht, A., Kheradpisheh, S.R., Farahani, H.: Multipath vit ocr: A lightweight visual transformer-based license plate optical character recognition. In: 2022 12th International Conference on Computer and Knowledge Engineering (ICCKE), pp. 092\u2013095. IEEE (2022)","DOI":"10.1109\/ICCKE57176.2022.9960026"},{"key":"29_CR3","first-page":"3965","volume":"34","author":"Z Dai","year":"2021","unstructured":"Dai, Z., Liu, H., Le, Q.V., Tan, M.: Coatnet: Marrying convolution and attention for all data sizes. Adv. Neural. Inf. Process. Syst. 34, 3965\u20133977 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"29_CR4","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"29_CR5","doi-asserted-by":"crossref","unstructured":"Du, Y., et al.: Svtr: Scene text recognition with a single visual model. arXiv preprint arXiv:2205.00159 (2022)","DOI":"10.24963\/ijcai.2022\/124"},{"key":"29_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2022.103541","volume":"86","author":"Y Gong","year":"2022","unstructured":"Gong, Y., et al.: Unified Chinese license plate detection and recognition with high efficiency. J. Vis. Commun. Image Represent. 86, 103541 (2022)","journal-title":"J. Vis. Commun. Image Represent."},{"key":"29_CR7","unstructured":"Goodfellow, I.J., Bulatov, Y., Ibarz, J., Arnoud, S., Shet, V.: Multi-digit number recognition from street view imagery using deep convolutional neural networks. arXiv preprint arXiv:1312.6082 (2013)"},{"key":"29_CR8","doi-asserted-by":"crossref","unstructured":"Goyal, Y., Khot, T., Summers-Stay, D., Batra, D., Parikh, D.: Making the V in VQA matter: Elevating the role of image understanding in visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6904\u20136913 (2017)","DOI":"10.1109\/CVPR.2017.670"},{"key":"29_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"29_CR10","doi-asserted-by":"crossref","unstructured":"Jiang, Y., et al.: An efficient and unified recognition method for multiple license plates in unconstrained scenarios. IEEE Trans. Intell. Transport. Syst. (2023)","DOI":"10.1109\/TITS.2023.3237743"},{"key":"29_CR11","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"29_CR12","doi-asserted-by":"crossref","unstructured":"Kudo, T., Richardson, J.: Sentencepiece: A simple and language independent subword tokenizer and detokenizer for neural text processing. arXiv preprint arXiv:1808.06226 (2018)","DOI":"10.18653\/v1\/D18-2012"},{"key":"29_CR13","unstructured":"Li, B., Weinberger, K.Q., Belongie, S., Koltun, V., Ranftl, R.: Language-driven semantic segmentation. arXiv preprint arXiv:2201.03546 (2022)"},{"key":"29_CR14","unstructured":"Li, C., et al.: Pp-ocrv3: More attempts for the improvement of ultra lightweight OCR system. arXiv preprint arXiv:2206.03001 (2022)"},{"key":"29_CR15","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: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 8610\u20138617 (2019)","DOI":"10.1609\/aaai.v33i01.33018610"},{"key":"29_CR16","doi-asserted-by":"crossref","unstructured":"Lin, J., et al.: Transferring general multimodal pretrained models to text recognition. arXiv preprint arXiv:2212.09297 (2022)","DOI":"10.18653\/v1\/2023.findings-acl.37"},{"key":"29_CR17","doi-asserted-by":"publisher","first-page":"11203","DOI":"10.1109\/ACCESS.2020.3047929","volume":"9","author":"J Shashirangana","year":"2020","unstructured":"Shashirangana, J., Padmasiri, H., Meedeniya, D., Perera, C.: Automated license plate recognition: a survey on methods and techniques. IEEE Access 9, 11203\u201311225 (2020)","journal-title":"IEEE Access"},{"key":"29_CR18","doi-asserted-by":"crossref","unstructured":"Sheng, F., Chen, Z., Xu, B.: NRTR: A no-recurrence sequence-to-sequence model for scene text recognition. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 781\u2013786. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00130"},{"issue":"11","key":"29_CR19","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. IEEE Trans. Pattern Anal. Mach. Intell. 39(11), 2298\u20132304 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"29_CR20","unstructured":"Subramani, N., Matton, A., Greaves, M., Lam, A.: A survey of deep learning approaches for ocr and document understanding. arXiv preprint arXiv:2011.13534 (2020)"},{"key":"29_CR21","unstructured":"Wang, P., et al.: OFA: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework. In: International Conference on Machine Learning, pp. 23318\u201323340. PMLR (2022)"},{"key":"29_CR22","doi-asserted-by":"crossref","unstructured":"Xu, Z., et al.: Towards end-to-end license plate detection and recognition: A large dataset and baseline. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 255\u2013271 (2018)","DOI":"10.1007\/978-3-030-01261-8_16"},{"key":"29_CR23","doi-asserted-by":"crossref","unstructured":"Yu, W., Liu, Y., Hua, W., Jiang, D., Ren, B., Bai, X.: Turning a clip model into a scene text detector. arXiv preprint arXiv:2302.14338 (2023)","DOI":"10.1109\/CVPR52729.2023.00674"},{"key":"29_CR24","unstructured":"Zhang, J., Huang, J., Jin, S., Lu, S.: Vision-language models for vision tasks: A survey. arXiv preprint arXiv:2304.00685 (2023)"},{"key":"29_CR25","unstructured":"Zherzdev, S., Gruzdev, A.: Lprnet: License plate recognition via deep neural networks. arXiv preprint arXiv:1806.10447 (2018)"},{"key":"29_CR26","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Conditional prompt learning for vision-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16816\u201316825 (2022)","DOI":"10.1109\/CVPR52688.2022.01631"}],"container-title":["Lecture Notes in Computer Science","Image and Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-46308-2_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,29]],"date-time":"2023-10-29T18:05:37Z","timestamp":1698602737000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-46308-2_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031463075","9783031463082"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-46308-2_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"30 October 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIG","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Image and Graphics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nanjing","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icig2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/icig2023.csig.org.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":"Conference Management Toolkit","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"409","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":"166","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":"41% - 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":"3","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)"}}]}}