{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T19:20:28Z","timestamp":1757618428154,"version":"3.44.0"},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T00:00:00Z","timestamp":1750118400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T00:00:00Z","timestamp":1750118400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372242"],"award-info":[{"award-number":["62372242"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Complex Intell. Syst."],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1007\/s40747-025-01987-6","type":"journal-article","created":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T04:50:34Z","timestamp":1750135834000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["GDText-VM: an arbitrary-shaped scene text detector based on globally deformable VMamba"],"prefix":"10.1007","volume":"11","author":[{"given":"Yingnan","family":"Zhao","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1661-8714","authenticated-orcid":false,"given":"Zheng","family":"Hu","sequence":"additional","affiliation":[]},{"given":"Fangqi","family":"Ding","sequence":"additional","affiliation":[]},{"given":"Jielin","family":"Jiang","sequence":"additional","affiliation":[]},{"given":"Xiaolong","family":"Xu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,6,17]]},"reference":[{"issue":"5","key":"1987_CR1","doi-asserted-by":"publisher","first-page":"977","DOI":"10.1016\/j.patcog.2003.10.012","volume":"37","author":"K Jung","year":"2004","unstructured":"Jung K, Kim KI, Jain AK (2004) Text information extraction in images and video: a survey. Pattern Recogn 37(5):977\u2013997","journal-title":"Pattern Recogn"},{"issue":"17","key":"1987_CR2","doi-asserted-by":"publisher","first-page":"5866","DOI":"10.3390\/s21175866","volume":"21","author":"G De-Las-Heras","year":"2021","unstructured":"De-Las-Heras G, Sanchez-Soriano J, Puertas E (2021) Advanced driver assistance systems (adas) based on machine learning techniques for the detection and transcription of variable message signs on roads. Sensors 21(17):5866","journal-title":"Sensors"},{"doi-asserted-by":"crossref","unstructured":"Huang W, Lin Z, Yang J, Wang J (2013) Text localization in natural images using stroke feature transform and text covariance descriptors. Proceedings of the IEEE International Conference on Computer Vision pp. 1241\u20131248","key":"1987_CR3","DOI":"10.1109\/ICCV.2013.157"},{"doi-asserted-by":"crossref","unstructured":"Lee J-J, Lee P-H, Lee S-W, Yuille A (2011) Koch, C (2011) Adaboost for text detection in natural scene. In: International Conference on Document Analysis and Recognition pp. 429\u2013434 IEEE","key":"1987_CR4","DOI":"10.1109\/ICDAR.2011.93"},{"doi-asserted-by":"crossref","unstructured":"Gupta A, Vedaldi A, Zisserman A (2016) Synthetic data for text localisation in natural images. Proc IEEE Conf Comput Vis Pattern Recognit pp. 2315\u20132324","key":"1987_CR5","DOI":"10.1109\/CVPR.2016.254"},{"issue":"12","key":"1987_CR6","doi-asserted-by":"publisher","first-page":"23831","DOI":"10.1109\/TITS.2022.3196814","volume":"23","author":"D Liu","year":"2022","unstructured":"Liu D, Cao J, Wang T, Wu H, Wang J, Tian J, Xu F (2022) Slpr: A deep learning based chinese ship license plate recognition framework. IEEE Trans Intell Transp Syst 23(12):23831\u201323843","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"1987_CR7","doi-asserted-by":"publisher","first-page":"36802","DOI":"10.1109\/ACCESS.2021.3063030","volume":"9","author":"P Keserwani","year":"2021","unstructured":"Keserwani P, Dhankhar A, Saini R, Roy PP (2021) Quadbox: Quadrilateral bounding box based scene text detection using vector regression. IEEE Access 9:36802\u201336818","journal-title":"IEEE Access"},{"doi-asserted-by":"crossref","unstructured":"Xue C, Lu S, Zhang W (2019) Msr: multi-scale shape regression for scene text detection. arXiv:1901.02596","key":"1987_CR8","DOI":"10.24963\/ijcai.2019\/139"},{"key":"1987_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107336","volume":"110","author":"Y Zhu","year":"2021","unstructured":"Zhu Y, Du J (2021) Textmountain: Accurate scene text detection via instance segmentation. Pattern Recogn 110:107336","journal-title":"Pattern Recogn"},{"doi-asserted-by":"crossref","unstructured":"Lyu P, Yao C, Wu W, Yan S, Bai X (2018) Multi-oriented scene text detection via corner localization and region segmentation. Proc IEEE Conf Comput Vis Pattern Recognit pp. 7553\u20137563","key":"1987_CR10","DOI":"10.1109\/CVPR.2018.00788"},{"doi-asserted-by":"crossref","unstructured":"Deng D, Liu H, Li X, Cai D (2018) Pixellink: Detecting scene text via instance segmentation. In: Proceedings of the AAAI Conference on Artificial Intelligence vol. 32","key":"1987_CR11","DOI":"10.1609\/aaai.v32i1.12269"},{"issue":"1","key":"1987_CR12","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1007\/s11263-020-01369-0","volume":"129","author":"S Long","year":"2021","unstructured":"Long S, He X, Yao C (2021) Scene text detection and recognition: The deep learning era. Int J Comput Vision 129(1):161\u2013184","journal-title":"Int J Comput Vision"},{"doi-asserted-by":"crossref","unstructured":"Long S, Ruan J, Zhang W, He X, Wu W, Yao C (2018) Textsnake: A flexible representation for detecting text of arbitrary shapes. Proceedings of the European Conference on Computer Vision (ECCV) pp. 20\u201336","key":"1987_CR13","DOI":"10.1007\/978-3-030-01216-8_2"},{"doi-asserted-by":"crossref","unstructured":"Liu Y, Chen H, Shen C, He T, Jin L, Wang L (2020) Abcnet: Real-time scene text spotting with adaptive bezier-curve network. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition pp. 9809\u20139818","key":"1987_CR14","DOI":"10.1109\/CVPR42600.2020.00983"},{"doi-asserted-by":"crossref","unstructured":"Wang F, Chen Y, Wu F, Li X (2020) Textray: Contour-based geometric modeling for arbitrary-shaped scene text detection. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 111\u2013119","key":"1987_CR15","DOI":"10.1145\/3394171.3413819"},{"doi-asserted-by":"crossref","unstructured":"Zhu Y, Chen J, Liang L, Kuang Z, Jin L, Zhang W (2021) Fourier contour embedding for arbitrary-shaped text detection. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition pp. 3123\u20133131","key":"1987_CR16","DOI":"10.1109\/CVPR46437.2021.00314"},{"doi-asserted-by":"crossref","unstructured":"Zhao Y, Cai Y, Wu W, Wang W (2023) (2023) Explore faster localization learning for scene text detection. In: IEEE International Conference on Multimedia and Expo (ICME) pp. 156\u2013161. IEEE","key":"1987_CR17","DOI":"10.1109\/ICME55011.2023.00035"},{"key":"1987_CR18","first-page":"3241","volume":"37","author":"M Ye","year":"2023","unstructured":"Ye M, Zhang J, Zhao S, Liu J, Du B, Tao D (2023) Dptext-detr: Towards better scene text detection with dynamic points in transformer. Proc AAAI Conf Artif Intell 37:3241\u20133249","journal-title":"Proc AAAI Conf Artif Intell"},{"unstructured":"Gu A, Dao T (2023) Mamba: Linear-time sequence modeling with selective state spaces. arXiv:2312.00752","key":"1987_CR19"},{"unstructured":"Liu Y, Tian Y, Zhao Y, Yu H, Xie L, Wang Y, Ye Q, Liu Y (2024) Vmamba: Visual state space model 2024. arXiv:2401.10166","key":"1987_CR20"},{"doi-asserted-by":"crossref","unstructured":"Pang J, Chen K, Shi J, Feng H, Ouyang W, Lin D (2019) Libra r-cnn: Towards balanced learning for object detection. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition pp. 821\u2013830","key":"1987_CR21","DOI":"10.1109\/CVPR.2019.00091"},{"doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. Proc IEEE Conf Comput Vis Pattern Recognit pp. 7132\u20137141","key":"1987_CR22","DOI":"10.1109\/CVPR.2018.00745"},{"doi-asserted-by":"crossref","unstructured":"Woo S, Park J, Lee J-Y, Kweon IS (2018) Cbam: Convolutional block attention module. Proceedings of the European Conference on Computer Vision (ECCV) pp. 3\u201319","key":"1987_CR23","DOI":"10.1007\/978-3-030-01234-2_1"},{"doi-asserted-by":"crossref","unstructured":"Zhang X, Zhou X, Lin M, Sun J (2018) Shufflenet: An extremely efficient convolutional neural network for mobile devices. Proc IEEE Conf Comput Vis Pattern Recognit pp. 6848\u20136856","key":"1987_CR24","DOI":"10.1109\/CVPR.2018.00716"},{"doi-asserted-by":"crossref","unstructured":"Ch\u2019ng CK, Chan CS (2017) Total-text: A comprehensive dataset for scene text detection and recognition. 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR) pp. 935\u2013942 IEEE","key":"1987_CR25","DOI":"10.1109\/ICDAR.2017.157"},{"key":"1987_CR26","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1016\/j.patcog.2019.02.002","volume":"90","author":"Y Liu","year":"2019","unstructured":"Liu Y, Jin L, Zhang S, Luo C, Zhang S (2019) Curved scene text detection via transverse and longitudinal sequence connection. Pattern Recogn 90:337\u2013345","journal-title":"Pattern Recogn"},{"doi-asserted-by":"crossref","unstructured":"Karatzas D, Gomez-Bigorda L, Nicolaou A, Ghosh S, Bagdanov A, Iwamura M, Matas J, Neumann L, Chandrasekhar VR, Lu S et al (2015) Icdar 2015 competition on robust reading. In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR), pp. 1156\u20131160. IEEEE","key":"1987_CR27","DOI":"10.1109\/ICDAR.2015.7333942"},{"doi-asserted-by":"crossref","unstructured":"Liao M, Shi B, Bai X, Wang X, Liu W (2017) Textboxes: A fast text detector with a single deep neural network. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 31","key":"1987_CR28","DOI":"10.1609\/aaai.v31i1.11196"},{"doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu C-Y, Berg AC (2016) Ssd: Single shot multibox detector. In: Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part I 14, pp. 21\u201337. Springer","key":"1987_CR29","DOI":"10.1007\/978-3-319-46448-0_2"},{"doi-asserted-by":"crossref","unstructured":"Liao M, Zhu Z, Shi B, Xia G-s, Bai X (2018) Rotation-sensitive regression for oriented scene text detection. Proc IEEE Conf Comput Vis Pattern Recognit pp. 5909\u20135918","key":"1987_CR30","DOI":"10.1109\/CVPR.2018.00619"},{"doi-asserted-by":"crossref","unstructured":"Zhou X, Yao C, Wen H, Wang Y, Zhou S, He W, Liang J (2017) East: an efficient and accurate scene text detector. Proc IEEE Conf Comput Vis Pattern Recognit pp. 5551\u20135560","key":"1987_CR31","DOI":"10.1109\/CVPR.2017.283"},{"doi-asserted-by":"crossref","unstructured":"Wang W, Xie E, Li X, Hou W, Lu T, Yu G, Shao S (2019) Shape robust text detection with progressive scale expansion network. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition pp. 9336\u20139345","key":"1987_CR32","DOI":"10.1109\/CVPR.2019.00956"},{"key":"1987_CR33","first-page":"11474","volume":"34","author":"M Liao","year":"2020","unstructured":"Liao M, Wan Z, Yao C, Chen K, Bai X (2020) Real-time scene text detection with differentiable binarization. Proc AAAI Conf Artif Intell 34:11474\u201311481","journal-title":"Proc AAAI Conf Artif Intell"},{"doi-asserted-by":"crossref","unstructured":"Jiang F, Wang Z (2022) Textfouriernet: Arbitrary-shaped scene text detection based on fourier contour modeling. In: 2022 China Automation Congress (CAC) pp. 1571\u20131576 IEEE","key":"1987_CR34","DOI":"10.1109\/CAC57257.2022.10055369"},{"unstructured":"Gu A, Goel K, R\u00e9 C (2021) Efficiently modeling long sequences with structured state spaces. arXiv:2111.00396","key":"1987_CR35"},{"doi-asserted-by":"crossref","unstructured":"Zhu X, Hu H, Lin S, Dai J (2019) Deformable convnets v2: More deformable, better results. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition pp. 9308\u20139316","key":"1987_CR36","DOI":"10.1109\/CVPR.2019.00953"},{"doi-asserted-by":"crossref","unstructured":"Gao Z, Xie J, Wang Q, Li P (2019) Global second-order pooling convolutional networks. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition pp. 3024\u20133033","key":"1987_CR37","DOI":"10.1109\/CVPR.2019.00314"},{"doi-asserted-by":"crossref","unstructured":"Wang Q, Wu B, Zhu P, Li P, Zuo W, Hu Q (2020) Eca-net: Efficient channel attention for deep convolutional neural networks. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition pp. 11534\u201311542","key":"1987_CR38","DOI":"10.1109\/CVPR42600.2020.01155"},{"doi-asserted-by":"crossref","unstructured":"Lee H, Kim H-E, Nam H (2019) Srm: A style-based recalibration module for convolutional neural networks. Proceedings of the IEEE\/CVF International Conference on Computer Vision pp. 1854\u20131862","key":"1987_CR39","DOI":"10.1109\/ICCV.2019.00194"},{"unstructured":"Jaderberg M, Simonyan K, Zisserman A et\u00a0al (2015) Spatial transformer networks. Adv Neural Inf Process Syst 28","key":"1987_CR40"},{"doi-asserted-by":"crossref","unstructured":"Liu J, Wu S, He D, Xiao G (2022) Ms-rocanet: Multi-scale residual orthogonal-channel attention network for scene text detection. In: ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2200\u20132204. IEEE","key":"1987_CR41","DOI":"10.1109\/ICASSP43922.2022.9746345"},{"key":"1987_CR42","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1016\/j.neucom.2021.04.095","volume":"454","author":"C Liu","year":"2021","unstructured":"Liu C, Yang C, Hou J-B, Wu L-H, Zhu X-B, Xiao L, Yin X-C (2021) Gccnet: Grouped channel composition network for scene text detection. Neurocomputing 454:135\u2013151","journal-title":"Neurocomputing"},{"issue":"12","key":"1987_CR43","doi-asserted-by":"publisher","first-page":"3758","DOI":"10.3390\/s24123758","volume":"24","author":"N Li","year":"2024","unstructured":"Li N, Wang Z, Huang Y, Tian J, Li X, Xiao Z (2024) A multi-scale natural scene text detection method based on attention feature extraction and cascade feature fusion. Sensors 24(12):3758","journal-title":"Sensors"},{"doi-asserted-by":"crossref","unstructured":"Yu Y, Liang Y, Wanga Y, Ding Z, Yu L, Li X (2023) A text detection algorithm for natural scenes based on improved gau and cbam. In: 2023 4th International Conference on Computer Engineering and Intelligent Control (ICCEIC), pp. 256\u2013262. IEEE","key":"1987_CR44","DOI":"10.1109\/ICCEIC60201.2023.10426674"},{"doi-asserted-by":"crossref","unstructured":"Lin T-Y, Doll\u00e1r P, Girshick R, He K, Hariharan B, Belongie S (2017) Feature pyramid networks for object detection. Proc IEEE Conf Comput Vis Pattern Recognit pp. 2117\u20132125","key":"1987_CR45","DOI":"10.1109\/CVPR.2017.106"},{"doi-asserted-by":"crossref","unstructured":"Guo H, Li J, Dai T, Ouyang Z, Ren X, Xia S-T (2025) Mambair: A simple baseline for image restoration with state-space model. European Conference on Computer Vision pp. 222\u2013241. Springer","key":"1987_CR46","DOI":"10.1007\/978-3-031-72649-1_13"},{"doi-asserted-by":"crossref","unstructured":"Shrivastava A, Gupta A, Girshick R (2016) Training region-based object detectors with online hard example mining. Proc IEEE Conf Comput Vis Pattern Recognit pp. 761\u2013769","key":"1987_CR47","DOI":"10.1109\/CVPR.2016.89"},{"unstructured":"Luo W, Li Y, Urtasun R, Zemel R (2016) Understanding the effective receptive field in deep convolutional neural networks. Adv Neural Inf Process Syst 29","key":"1987_CR48"},{"doi-asserted-by":"crossref","unstructured":"Zheng J, Fan H, Zhang L (2024) Kernel adaptive convolution for scene text detection via distance map prediction. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition pp. 5957\u20135966","key":"1987_CR49","DOI":"10.1109\/CVPR52733.2024.00569"},{"issue":"1","key":"1987_CR50","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1007\/s40747-023-01134-z","volume":"10","author":"H Chen","year":"2024","unstructured":"Chen H, Qiu Y, Jiang M, Lin J, Chen P (2024) Kernel-mask knowledge distillation for efficient and accurate arbitrary-shaped text detection. Complex & Intell Syst 10(1):75\u201386","journal-title":"Complex & Intell Syst"},{"issue":"3","key":"1987_CR51","doi-asserted-by":"publisher","first-page":"1815","DOI":"10.1109\/TCSVT.2023.3299087","volume":"34","author":"Z Shao","year":"2023","unstructured":"Shao Z, Su Y, Zhou Y, Meng F, Zhu H, Liu B, Yao R (2023) Ct-net: Arbitrary-shaped text detection via contour transformer. IEEE Trans Circuits Syst Video Technol 34(3):1815\u20131826","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. Proc IEEE Conf Comput Vis Pattern Recognit pp. 770\u2013778","key":"1987_CR52","DOI":"10.1109\/CVPR.2016.90"},{"doi-asserted-by":"crossref","unstructured":"Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, Lin S, Guo B (2021) Swin transformer: Hierarchical vision transformer using shifted windows. Proceedings of the IEEE\/CVF International Conference on Computer Vision pp. 10012\u201310022","key":"1987_CR53","DOI":"10.1109\/ICCV48922.2021.00986"}],"container-title":["Complex & Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-025-01987-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s40747-025-01987-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-025-01987-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T20:17:51Z","timestamp":1757189871000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s40747-025-01987-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,17]]},"references-count":53,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2025,8]]}},"alternative-id":["1987"],"URL":"https:\/\/doi.org\/10.1007\/s40747-025-01987-6","relation":{},"ISSN":["2199-4536","2198-6053"],"issn-type":[{"type":"print","value":"2199-4536"},{"type":"electronic","value":"2198-6053"}],"subject":[],"published":{"date-parts":[[2025,6,17]]},"assertion":[{"value":"10 January 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 June 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 June 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no known competing financial interests or personal relationships that could have appeared to influence the work reported in this paper.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"348"}}