{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T15:43:03Z","timestamp":1758123783301,"version":"3.40.3"},"publisher-location":"Cham","reference-count":31,"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_15","type":"book-chapter","created":{"date-parts":[[2023,10,29]],"date-time":"2023-10-29T18:01:24Z","timestamp":1698602484000},"page":"175-186","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Vision-Language Adaptive Mutual Decoder for\u00a0OOV-STR"],"prefix":"10.1007","author":[{"given":"Jinshui","family":"Hu","sequence":"first","affiliation":[]},{"given":"Chenyu","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Qiandong","family":"Yan","sequence":"additional","affiliation":[]},{"given":"Xuyang","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Jiajia","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Jun","family":"Du","sequence":"additional","affiliation":[]},{"given":"Lirong","family":"Dai","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,10,30]]},"reference":[{"key":"15_CR1","doi-asserted-by":"crossref","unstructured":"Aberdam, A., et al.: Sequence-to-sequence contrastive learning for text recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15302\u201315312 (2021)","DOI":"10.1109\/CVPR46437.2021.01505"},{"key":"15_CR2","unstructured":"Alsharif, O., Pineau, J.: End-to-end text recognition with hybrid hmm maxout models. arXiv preprint arXiv:1310.1811 (2013)"},{"key":"15_CR3","doi-asserted-by":"crossref","unstructured":"Baek, J., et al.: What is wrong with scene text recognition model comparisons? dataset and model analysis. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4715\u20134723 (2019)","DOI":"10.1109\/ICCV.2019.00481"},{"key":"15_CR4","doi-asserted-by":"crossref","unstructured":"Chan, W., Jaitly, N., Le, Q., Vinyals, O.: Listen, attend and spell: a neural network for large vocabulary conversational speech recognition. In: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4960\u20134964. IEEE (2016)","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"15_CR5","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"15_CR6","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7098\u20137107 (2021)","DOI":"10.1109\/CVPR46437.2021.00702"},{"key":"15_CR7","doi-asserted-by":"publisher","unstructured":"Garcia-Bordils, S. et al.: Out-of-vocabulary challenge report. In: Karlinsky, L., Michaeli, T., Nishino, K. (eds.) Computer Vision - ECCV 2022 Workshops. ECCV 2022, Part IV, LNCS, vol. 13804, pp 359\u2013375. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-25069-9_24","DOI":"10.1007\/978-3-031-25069-9_24"},{"key":"15_CR8","doi-asserted-by":"crossref","unstructured":"Gupta, A., Vedaldi, A., Zisserman, A.: Synthetic data for text localisation in natural images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2315\u20132324 (2016)","DOI":"10.1109\/CVPR.2016.254"},{"key":"15_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask r-cnn. In: Proceedings of the IEEE International Conference on Computer vision, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"15_CR10","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":"15_CR11","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":"15_CR12","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et al.: Icdar 2015 competition on robust reading. In: 2015 13th international conference on document analysis and recognition (ICDAR), pp. 1156\u20131160. IEEE (2015)","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"15_CR13","unstructured":"Krylov, I., Nosov, S., Sovrasov, V.: Open images v5 text annotation and yet another mask text spotter. In: Asian Conference on Machine Learning, pp. 379\u2013389. PMLR (2021)"},{"key":"15_CR14","doi-asserted-by":"crossref","unstructured":"Kuang, Z., et al.: Mmocr: a comprehensive toolbox for text detection, recognition and understanding. arXiv preprint arXiv:2108.06543 (2021)","DOI":"10.1145\/3474085.3478328"},{"key":"15_CR15","doi-asserted-by":"crossref","unstructured":"Lee, J., et al.: On recognizing texts of arbitrary shapes with 2d self-attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 546\u2013547 (2020)","DOI":"10.1109\/CVPRW50498.2020.00281"},{"key":"15_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: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 8610\u20138617 (2019)","DOI":"10.1609\/aaai.v33i01.33018610"},{"key":"15_CR17","doi-asserted-by":"crossref","unstructured":"Litman, R., Anschel, O., Tsiper, S., Litman, R., Mazor, S., Manmatha, R.: Scatter: selective context attentional scene text recognizer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11962\u201311972 (2020)","DOI":"10.1109\/CVPR42600.2020.01198"},{"key":"15_CR18","doi-asserted-by":"crossref","unstructured":"Liu, C., Yang, C., Yin, X.C.: Open-set text recognition via character-context decoupling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4523\u20134532 (2022)","DOI":"10.1109\/CVPR52688.2022.00448"},{"key":"15_CR19","doi-asserted-by":"crossref","unstructured":"Liu, Q., Wang, L., Huo, Q.: A study on effects of implicit and explicit language model information for DBLSTM-CTC based handwriting recognition. In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR), pp. 461\u2013465. IEEE (2015)","DOI":"10.1109\/ICDAR.2015.7333804"},{"key":"15_CR20","doi-asserted-by":"crossref","unstructured":"Long, S., Qin, S., Panteleev, D., Bissacco, A., Fujii, Y., Raptis, M.: Towards end-to-end unified scene text detection and layout analysis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1049\u20131059 (2022)","DOI":"10.1109\/CVPR52688.2022.00112"},{"key":"15_CR21","doi-asserted-by":"crossref","unstructured":"Luo, C., Jin, L., Chen, J.: Siman: exploring self-supervised representation learning of scene text via similarity-aware normalization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1039\u20131048 (2022)","DOI":"10.1109\/CVPR52688.2022.00111"},{"key":"15_CR22","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: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1582\u20131587. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00254"},{"key":"15_CR23","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: Towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, vol. 28 (2015)"},{"issue":"11","key":"15_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. IEEE Trans. Pattern Anal. Mach. Intell. 39(11), 2298\u20132304 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"9","key":"15_CR25","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. IEEE Trans. Pattern Anal. Mach. Intell. 41(9), 2035\u20132048 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"15_CR26","doi-asserted-by":"crossref","unstructured":"Singh, A., Pang, G., Toh, M., Huang, J., Galuba, W., Hassner, T.: TextOcr: towards large-scale end-to-end reasoning for arbitrary-shaped scene text. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8802\u20138812 (2021)","DOI":"10.1109\/CVPR46437.2021.00869"},{"key":"15_CR27","doi-asserted-by":"crossref","unstructured":"Tu, Z., Lu, Z., Liu, Y., Liu, X., Li, H.: Modeling coverage for neural machine translation. arXiv preprint arXiv:1601.04811 (2016)","DOI":"10.18653\/v1\/P16-1008"},{"key":"15_CR28","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"15_CR29","doi-asserted-by":"crossref","unstructured":"Wan, Z., Zhang, J., Zhang, L., Luo, J., Yao, C.: On vocabulary reliance in scene text recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11425\u201311434 (2020)","DOI":"10.1109\/CVPR42600.2020.01144"},{"key":"15_CR30","doi-asserted-by":"crossref","unstructured":"Yang, M., et al.: Reading and writing: discriminative and generative modeling for self-supervised text recognition. arXiv preprint arXiv:2207.00193 (2022)","DOI":"10.1145\/3503161.3547784"},{"key":"15_CR31","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"}],"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_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,29]],"date-time":"2023-10-29T18:03:32Z","timestamp":1698602612000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-46308-2_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031463075","9783031463082"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-46308-2_15","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)"}}]}}