{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T01:00:35Z","timestamp":1742950835811,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":27,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819785100"},{"type":"electronic","value":"9789819785117"}],"license":[{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"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":[[2025]]},"DOI":"10.1007\/978-981-97-8511-7_10","type":"book-chapter","created":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T05:02:28Z","timestamp":1730523748000},"page":"129-142","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Improving Scene Text Recognition with Counting-Aware Contrastive Learning and Attention Alignment"],"prefix":"10.1007","author":[{"given":"JunJie","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anna","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,3]]},"reference":[{"key":"10_CR1","doi-asserted-by":"crossref","unstructured":"Aberdam, A., et al.: Sequence-to-sequence contrastive learning for text recognition (2020)","DOI":"10.1109\/CVPR46437.2021.01505"},{"key":"10_CR2","doi-asserted-by":"publisher","unstructured":"Borisyuk, F., Gordo, A., Sivakumar, V.: Rosetta. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. ACM (Jul 2018). https:\/\/doi.org\/10.1145\/3219819.3219861, https:\/\/doi.org\/10.1145%2F3219819.3219861","DOI":"10.1145\/3219819.3219861"},{"key":"10_CR3","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"10_CR4","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale (2021)"},{"key":"10_CR5","doi-asserted-by":"crossref","unstructured":"Du, Y., et al.: Svtr: scene text recognition with a single visual model (2022)","DOI":"10.24963\/ijcai.2022\/124"},{"key":"10_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 (2021)","DOI":"10.1109\/CVPR46437.2021.00702"},{"key":"10_CR7","doi-asserted-by":"crossref","unstructured":"Guan, T., Shen, W., Yang, X., Feng, Q., Jiang, Z., Yang, X.: Self-supervised character-to-character distillation for text recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 19473\u201319484 (2023)","DOI":"10.1109\/ICCV51070.2023.01784"},{"key":"10_CR8","doi-asserted-by":"crossref","unstructured":"Gupta, A., Vedaldi, A., Zisserman, A.: Synthetic data for text localisation in natural images (2016)","DOI":"10.1109\/CVPR.2016.254"},{"key":"10_CR9","unstructured":"Jaderberg, M., Simonyan, K., Vedaldi, A., Zisserman, A.: Synthetic data and artificial neural networks for natural scene text recognition (2014)"},{"key":"10_CR10","doi-asserted-by":"crossref","unstructured":"Jiang, H., et al.: Reciprocal feature learning via explicit and implicit tasks in scene text recognition (2021)","DOI":"10.1007\/978-3-030-86549-8_19"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et al.: Icdar 2015 competition on robust reading. In: International Conference on Document Analysis and Recognition ICDAR (2015)","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"10_CR12","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et al.: Icdar 2013 robust reading competition. In: International Conference on Document Analysis and Recognition ICDAR (2013)","DOI":"10.1109\/ICDAR.2013.221"},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Liu, H., et al.: Perceiving stroke-semantic context: Hierarchical contrastive learning for robust scene text recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 1702\u20131710 (2022)","DOI":"10.1609\/aaai.v36i2.20062"},{"key":"10_CR14","doi-asserted-by":"publisher","unstructured":"Lu, N., et al.: MASTER: multi-aspect non-local network for scene text recognition. Pattern Recognit. 117, 107980 (Sept 2021). https:\/\/doi.org\/10.1016\/j.patcog.2021.107980, https:\/\/doi.org\/10.1016%2Fj.patcog.2021.107980","DOI":"10.1016\/j.patcog.2021.107980"},{"key":"10_CR15","doi-asserted-by":"crossref","unstructured":"Luo, C., Jin, L., Chen, J.: Siman: exploring self-supervised representation learning of scene text via similarity-aware normalization (2022)","DOI":"10.1109\/CVPR52688.2022.00111"},{"key":"10_CR16","doi-asserted-by":"crossref","unstructured":"Luo, C., Zhu, Y., Jin, L., Wang, Y.: Learn to augment: Joint data augmentation and network optimization for text recognition (2020)","DOI":"10.1109\/CVPR42600.2020.01376"},{"key":"10_CR17","unstructured":"Mishra, A., Karteek, A., Jawahar, C.V.: Scene text recognition using higher order language priors. In: British Machine Vision Conference (BMVC) (2009)"},{"key":"10_CR18","doi-asserted-by":"crossref","unstructured":"Phan, T.Q., Shivakumara, P., Tian, S., Tan, C.L.: Recognizing text with perspective distortion in natural scenes. In: International Conference on Computer Vision (ICCV) (2013)","DOI":"10.1109\/ICCV.2013.76"},{"key":"10_CR19","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, 8027\u20138048 (2014)","journal-title":"Expert Syst. Appl."},{"key":"10_CR20","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 (2015)"},{"key":"10_CR21","unstructured":"Sitzmann, V., Zollh\u00f6fer, M., Wetzstein, G.: Scene representation networks: continuous 3d-structure-aware neural scene representations (2020)"},{"key":"10_CR22","unstructured":"Tang, X., Lai, Y., Liu, Y., Fu, Y., Fang, R.: Visual-semantic transformer for scene text recognition (2021)"},{"key":"10_CR23","unstructured":"Wang, K., Babenko, B., Belongie, S.J.: End-to-end scene text recognition. In: International Conference on Computer Vision (ICCV (2011)"},{"issue":"3","key":"10_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11432-023-3935-8","volume":"67","author":"K Xiao","year":"2024","unstructured":"Xiao, K., Zhu, A., Iwana, B.K., Liu, C.L.: Scene text recognition via dual character counting-aware visual and semantic modeling network. Sci. China Inf. Sci. 67(3), 1\u20132 (2024)","journal-title":"Sci. China Inf. Sci."},{"key":"10_CR25","doi-asserted-by":"crossref","unstructured":"Yang, M., et al.: Reading and writing: discriminative and generative modeling for self-supervised text recognition (2023)","DOI":"10.1145\/3503161.3547784"},{"key":"10_CR26","doi-asserted-by":"crossref","unstructured":"Zhang, B., Xie, H., Wang, Y., Xu, J., Zhang, Y.: Linguistic more: taking a further step toward efficient and accurate scene text recognition (2023)","DOI":"10.24963\/ijcai.2023\/189"},{"key":"10_CR27","doi-asserted-by":"crossref","unstructured":"Zhang, J., Lin, T., Xu, Y., Chen, K., Zhang, R.: Relational contrastive learning for scene text recognition (2023)","DOI":"10.1145\/3581783.3612247"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-8511-7_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T05:05:37Z","timestamp":1730523937000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8511-7_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,3]]},"ISBN":["9789819785100","9789819785117"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8511-7_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,3]]},"assertion":[{"value":"3 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Urumqi","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2024.prcv.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}