{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T15:19:39Z","timestamp":1784387979783,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":21,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819698622","type":"print"},{"value":"9789819698639","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-981-96-9863-9_14","type":"book-chapter","created":{"date-parts":[[2025,7,23]],"date-time":"2025-07-23T14:38:38Z","timestamp":1753281518000},"page":"162-173","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["MambaSTR: Scene Text Recognition with Masked State Space Model"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-9228-5235","authenticated-orcid":false,"given":"Bo","family":"Zhou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9328-7068","authenticated-orcid":false,"given":"Anna","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8578-1314","authenticated-orcid":false,"given":"JunJie","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,7,24]]},"reference":[{"key":"14_CR1","doi-asserted-by":"crossref","unstructured":"Du, Y., et al.: SVTR: scene text recognition with a single visual model. In: IJCAI (2022). https:\/\/api.semanticscholar.org\/CorpusID:248496672","DOI":"10.24963\/ijcai.2022\/124"},{"key":"14_CR2","unstructured":"Du, Y., Chen, Z., Xie, H., Jia, C., Jiang, Y.G.: SVTRv2: CTC Beats Encoder-Decoder Models in Scene Text Recognition. arXiv preprint arXiv:2411.15858 (2024)"},{"key":"14_CR3","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: CVPR, pp. 7098\u20137107 (2021)","DOI":"10.1109\/CVPR46437.2021.00702"},{"key":"14_CR4","unstructured":"Gu, A., Dao, T.: Mamba: linear-time sequence modeling with selective state spaces. In: COLM (2024)"},{"key":"14_CR5","unstructured":"Gu, A., Goel, K., Re, C.: Efficiently modeling long sequences with structured state spaces. In: ICLR (2022)"},{"key":"14_CR6","doi-asserted-by":"crossref","unstructured":"Huang, T., Pei, X., You, S., Wang, F., Qian, C., Xu, C.: LocalMamba: Visual State Space Model with Windowed Selective Scan. arXiv preprint arXiv:2403.09338 (2024)","DOI":"10.1007\/978-3-031-91979-4_2"},{"key":"14_CR7","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"14_CR8","unstructured":"Shazeer, N., et al.: Outrageously large neural networks: the sparsely-gated mixture-of-experts layer. In: ICLR (2017)"},{"key":"14_CR9","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":"9","key":"14_CR10","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. TPAMI 41(9), 2035\u20132048 (2018)","journal-title":"TPAMI"},{"key":"14_CR11","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Wang, Y., Xie, H., Fang, S., Wang, J., Zhu, S., Zhang, Y.: From two to one: a new scene text recognizer with visual language modeling network. In: ICCV. pp. 14194\u201314203 (2021)","DOI":"10.1109\/ICCV48922.2021.01393"},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"Xie, X., Fu, L., Zhang, Z., Wang, Z., Bai, X.: Toward understanding wordart: corner-guided transformer for scene text recognition. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19815-1_18"},{"key":"14_CR14","doi-asserted-by":"crossref","unstructured":"Xu, J., Wang, Y., Xie, H., Zhang, Y.: OTE: exploring accurate scene text recognition using one token. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.02676"},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Yang, M., Yang, B., Liao, M., Zhu, Y., Bai, X.: Class-Aware mask-guided feature refinement for scene text recognition. PR 149, 110244 (2024)","DOI":"10.1016\/j.patcog.2023.110244"},{"key":"14_CR16","doi-asserted-by":"crossref","unstructured":"Yu, D., Li, X., Zhang, C., Liu, T., Han, J., Liu, J., Ding, E.: Towards accurate scene text recognition with semantic reasoning networks. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01213"},{"key":"14_CR17","doi-asserted-by":"crossref","unstructured":"Yue, X., Kuang, Z., Lin, C., Sun, H., Zhang, W.: RobustScanner: dynamically enhancing positional clues for robust text recognition. In: ECCV. pp. 135\u2013151. Springer (2020)","DOI":"10.1007\/978-3-030-58529-7_9"},{"key":"14_CR18","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. In: IJCAI (2023), https:\/\/api.semanticscholar.org\/CorpusID:258564342","DOI":"10.24963\/ijcai.2023\/189"},{"issue":"2","key":"14_CR19","doi-asserted-by":"publisher","first-page":"300","DOI":"10.1007\/s11263-023-01880-0","volume":"132","author":"T Zheng","year":"2024","unstructured":"Zheng, T., Chen, Z., Fang, S., Xie, H., Jiang, Y.G.: CDistNet: perceiving multi-domain character distance for robust text recognition. IJCV 132(2), 300\u2013318 (2024)","journal-title":"IJCV"},{"key":"14_CR20","doi-asserted-by":"crossref","unstructured":"Zhu, A., Xiao, K., Zhou, B., Wang, R.: Trust prophet or not? taking a further verification step toward accurate scene text recognition. In: ACM MM (2024)","DOI":"10.1145\/3664647.3681551"},{"key":"14_CR21","unstructured":"Zhu, L., Liao, B., Zhang, Q., Wang, X., Liu, W., Wang, X.: Vision mamba: efficient visual representation learning with bidirectional state space model. In: ICML (2024)"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-9863-9_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T04:09:47Z","timestamp":1774670987000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-9863-9_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819698622","9789819698639"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-9863-9_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"24 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ningbo","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/icg\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}