{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T15:30:14Z","timestamp":1772119814508,"version":"3.50.1"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"14","license":[{"start":{"date-parts":[[2024,6,9]],"date-time":"2024-06-09T00:00:00Z","timestamp":1717891200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,6,9]],"date-time":"2024-06-09T00:00:00Z","timestamp":1717891200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No.62166043"],"award-info":[{"award-number":["No.62166043"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1007\/s11227-024-06268-6","type":"journal-article","created":{"date-parts":[[2024,6,9]],"date-time":"2024-06-09T02:01:15Z","timestamp":1717898475000},"page":"21394-21411","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Visual and semantic guided scene text retrieval"],"prefix":"10.1007","volume":"80","author":[{"given":"Hailong","family":"Luo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mayire","family":"Ibrayim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Askar","family":"Hamdulla","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qilin","family":"Deng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,6,9]]},"reference":[{"key":"6268_CR1","unstructured":"Chen Z, Wang W, Xie E, Yang Z, Lu T, Luo P (2021) FAST: searching for a faster arbitrarily-shaped text detector with minimalist kernel representation. CoRR arXiv:2111.02394"},{"issue":"1","key":"6268_CR2","doi-asserted-by":"publisher","first-page":"919","DOI":"10.1109\/TPAMI.2022.3155612","volume":"45","author":"M Liao","year":"2023","unstructured":"Liao M, Zou Z, Wan Z, Yao C, Bai X (2023) Real-time scene text detection with differentiable binarization and adaptive scale fusion. IEEE Trans Pattern Anal Mach Intell 45(1):919\u2013931. https:\/\/doi.org\/10.1109\/TPAMI.2022.3155612","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"6268_CR3","doi-asserted-by":"publisher","unstructured":"Liao M, Zhu Z, Shi B, Xia G-S, Bai X (2018) Rotation-sensitive regression for oriented scene text detection. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 5909\u20135918. https:\/\/doi.org\/10.1109\/CVPR.2018.00619","DOI":"10.1109\/CVPR.2018.00619"},{"key":"6268_CR4","doi-asserted-by":"publisher","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. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 9806\u20139815. https:\/\/doi.org\/10.1109\/CVPR42600.2020.00983","DOI":"10.1109\/CVPR42600.2020.00983"},{"key":"6268_CR5","doi-asserted-by":"publisher","unstructured":"Mishra A, Alahari K, Jawahar CV (2013) Image retrieval using textual cues. In: 2013 IEEE International Conference on Computer Vision, pp 3040\u20133047. https:\/\/doi.org\/10.1109\/ICCV.2013.378","DOI":"10.1109\/ICCV.2013.378"},{"key":"6268_CR6","doi-asserted-by":"publisher","unstructured":"He T, Tian Z, Huang W, Shen C, Qiao Y, Sun C (2018) An end-to-end textspotter with explicit alignment and attention. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 5020\u20135029. https:\/\/doi.org\/10.1109\/CVPR.2018.00527","DOI":"10.1109\/CVPR.2018.00527"},{"key":"6268_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11263-015-0823-z","volume":"116","author":"M Jaderberg","year":"2016","unstructured":"Jaderberg M, Simonyan K, Vedaldi A, Zisserman A (2016) Reading text in the wild with convolutional neural networks. Int J Comput Vision 116:1\u201320. https:\/\/doi.org\/10.1007\/s11263-015-0823-z","journal-title":"Int J Comput Vision"},{"key":"6268_CR8","doi-asserted-by":"publisher","first-page":"706","DOI":"10.1007\/978-3-030-58621-8_41","volume-title":"Computer Vision - ECCV 2020","author":"M Liao","year":"2020","unstructured":"Liao M, Pang G, Huang J, Hassner T, Bai X (2020) Mask textspotter v3: Segmentation proposal network for robust scene text spotting. In: Vedaldi A, Bischof H, Brox T, Frahm J-M (eds) Computer Vision - ECCV 2020. Springer, Cham, pp 706\u2013722. https:\/\/doi.org\/10.1007\/978-3-030-58621-8_41"},{"key":"6268_CR9","doi-asserted-by":"publisher","unstructured":"Huang M, Liu Y, Peng Z, Liu C, Lin D, Zhu S, Yuan N, Ding K, Jin L (2022) Swintextspotter: Scene text spotting via better synergy between text detection and text recognition. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 4583\u20134593. https:\/\/doi.org\/10.1109\/CVPR52688.2022.00455","DOI":"10.1109\/CVPR52688.2022.00455"},{"issue":"16","key":"6268_CR10","doi-asserted-by":"publisher","first-page":"17810","DOI":"10.1007\/s11227-023-05318-9","volume":"79","author":"X Shi","year":"2023","unstructured":"Shi X, Yu Z, Wang X, Li Y, Niu Y (2023) Text-image matching for multi-model machine translation. J Supercomput 79(16):17810\u201317823. https:\/\/doi.org\/10.1007\/s11227-023-05318-9","journal-title":"J Supercomput"},{"key":"6268_CR11","doi-asserted-by":"publisher","unstructured":"Yang X, He D, Huang W, Ororbia A, Zhou Z, Kifer D, Giles CL (2017) Smart library: Identifying books on library shelves using supervised deep learning for scene text reading. In: 2017 ACM\/IEEE Joint Conference on Digital Libraries (JCDL), pp 1\u20134. https:\/\/doi.org\/10.1109\/JCDL.2017.7991581","DOI":"10.1109\/JCDL.2017.7991581"},{"key":"6268_CR12","doi-asserted-by":"publisher","unstructured":"Song H, Wang H, Huang S, Xu P, Huang S, Ju Q (2019) Text siamese network for video textual keyframe detection. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp 442\u2013447. https:\/\/doi.org\/10.1109\/ICDAR.2019.00077","DOI":"10.1109\/ICDAR.2019.00077"},{"issue":"18","key":"6268_CR13","doi-asserted-by":"publisher","first-page":"20562","DOI":"10.1007\/s11227-023-05478-8","volume":"79","author":"A-E Benrazek","year":"2023","unstructured":"Benrazek A-E, Kouahla Z, Farou B, Seridi H, Allele I, Ferrag MA (2023) Tree-based indexing technique for efficient and real-time label retrieval in the object tracking system. J Supercomput 79(18):20562\u201320599. https:\/\/doi.org\/10.1007\/s11227-023-05478-8","journal-title":"J Supercomput"},{"issue":"12","key":"6268_CR14","doi-asserted-by":"publisher","first-page":"2552","DOI":"10.1109\/TPAMI.2014.2339814","volume":"36","author":"J Almaz\u00e1n","year":"2014","unstructured":"Almaz\u00e1n J, Gordo A, Forn\u00e9s A, Valveny E (2014) Word spotting and recognition with embedded attributes. IEEE Trans Pattern Anal Mach Intell 36(12):2552\u20132566. https:\/\/doi.org\/10.1109\/TPAMI.2014.2339814","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"6268_CR15","doi-asserted-by":"publisher","unstructured":"G\u00f3mez L, Rusi\u00f1ol M, Karatzas D (2017) Lsde: Levenshtein space deep embedding for query-by-string word spotting. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol 01, pp 499\u2013504. https:\/\/doi.org\/10.1109\/ICDAR.2017.88","DOI":"10.1109\/ICDAR.2017.88"},{"key":"6268_CR16","doi-asserted-by":"publisher","unstructured":"Wilkinson T, Brun A (2016) Semantic and verbatim word spotting using deep neural networks. In: 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp 307\u2013312. https:\/\/doi.org\/10.1109\/ICFHR.2016.0065","DOI":"10.1109\/ICFHR.2016.0065"},{"key":"6268_CR17","doi-asserted-by":"publisher","unstructured":"Ghosh SK, G\u00f3mez L, Karatzas D, Valveny E (2015) Efficient indexing for query by string text retrieval. In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR), pp 1236\u20131240. https:\/\/doi.org\/10.1109\/ICDAR.2015.7333961","DOI":"10.1109\/ICDAR.2015.7333961"},{"key":"6268_CR18","unstructured":"Levenshtein VI, et al (1966) Binary codes capable of correcting deletions, insertions, and reversals. In: Soviet Physics Doklady, vol 10, pp 707\u2013710. Soviet Union"},{"key":"6268_CR19","doi-asserted-by":"publisher","unstructured":"Wang H, Bai X, Yang M, Zhu S, Wang J, Liu W (2021) Scene text retrieval via joint text detection and similarity learning. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 4556\u20134565. https:\/\/doi.org\/10.1109\/CVPR46437.2021.00453","DOI":"10.1109\/CVPR46437.2021.00453"},{"key":"6268_CR20","doi-asserted-by":"publisher","first-page":"728","DOI":"10.1007\/978-3-030-01264-9_43","volume-title":"Computer Vision - ECCV 2018","author":"L G\u00f3mez","year":"2018","unstructured":"G\u00f3mez L, Mafla A, Rusi\u00f1ol M, Karatzas D (2018) Single shot scene text retrieval. In: Ferrari V, Hebert M, Sminchisescu C, Weiss Y (eds) Computer Vision - ECCV 2018. Springer, Cham, pp 728\u2013744"},{"key":"6268_CR21","doi-asserted-by":"publisher","first-page":"107656","DOI":"10.1016\/j.patcog.2020.107656","volume":"110","author":"A Mafla","year":"2021","unstructured":"Mafla A, Tito R, Dey S, G\u00f3mez L, Rusi\u00f1ol M, Valveny E, Karatzas D (2021) Real-time lexicon-free scene text retrieval. Pattern Recogn 110:107656. https:\/\/doi.org\/10.1016\/j.patcog.2020.107656","journal-title":"Pattern Recogn"},{"key":"6268_CR22","doi-asserted-by":"publisher","unstructured":"Wu J, Zhao J, Xu J (2022) Hglnet: A generic hierarchical global-local feature fusion network for multi-modal classification. In: 2022 IEEE International Conference on Multimedia and Expo (ICME). IEEE. https:\/\/doi.org\/10.1109\/icme52920.2022.9859834","DOI":"10.1109\/icme52920.2022.9859834"},{"key":"6268_CR23","doi-asserted-by":"publisher","unstructured":"Wen L, Wang Y, Zhang D, Chen G (2023) Visual matching is enough for scene text retrieval. WSDM \u201923. Association for Computing Machinery, New York, pp 447\u2013455. https:\/\/doi.org\/10.1145\/3539597.3570428","DOI":"10.1145\/3539597.3570428"},{"key":"6268_CR24","doi-asserted-by":"publisher","unstructured":"Aldavert D, Rusi\u00f1ol M, Toledo R, Llad\u00f3s J (2013) Integrating visual and textual cues for query-by-string word spotting. In: 2013 12th International Conference on Document Analysis and Recognition, pp 511\u2013515. https:\/\/doi.org\/10.1109\/ICDAR.2013.108","DOI":"10.1109\/ICDAR.2013.108"},{"key":"6268_CR25","doi-asserted-by":"publisher","unstructured":"Sudholt S, Fink GA (2016) Phocnet: A deep convolutional neural network for word spotting in handwritten documents. In: 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp 277\u2013282. https:\/\/doi.org\/10.1109\/ICFHR.2016.0060","DOI":"10.1109\/ICFHR.2016.0060"},{"key":"6268_CR26","doi-asserted-by":"publisher","unstructured":"Matas J, Chum O, Urban M, Pajdla T (2004) Robust wide-baseline stereo from maximally stable extremal regions. Image Vis Comput 22(10):761\u2013767. https:\/\/doi.org\/10.1016\/j.imavis.2004.02.006. British Machine Vision Computing 2002","DOI":"10.1016\/j.imavis.2004.02.006"},{"key":"6268_CR27","doi-asserted-by":"publisher","unstructured":"Shaila SG, Vadivel A, Devi Mahalakshmi R, Karthika J (2012) N-grams corpus generation from inverted index for query refinement in information retrieval applications. In: 2012 International Conference on Emerging Trends in Science, Engineering and Technology (INCOSET), pp 130\u2013138. https:\/\/doi.org\/10.1109\/INCOSET.2012.6513893","DOI":"10.1109\/INCOSET.2012.6513893"},{"key":"6268_CR28","doi-asserted-by":"publisher","unstructured":"Redmon J, Farhadi A (2017) Yolo9000: Better, faster, stronger. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 6517\u20136525. https:\/\/doi.org\/10.1109\/CVPR.2017.690","DOI":"10.1109\/CVPR.2017.690"},{"key":"6268_CR29","doi-asserted-by":"publisher","unstructured":"Chollet F (2017) Xception: Deep learning with depthwise separable convolutions. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 1800\u20131807. https:\/\/doi.org\/10.1109\/CVPR.2017.195","DOI":"10.1109\/CVPR.2017.195"},{"key":"6268_CR30","doi-asserted-by":"publisher","unstructured":"Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 7132\u20137141. https:\/\/doi.org\/10.1109\/CVPR.2018.00745","DOI":"10.1109\/CVPR.2018.00745"},{"key":"6268_CR31","doi-asserted-by":"publisher","unstructured":"Tian Z, Shen C, Chen H, He T (2019) Fcos: Fully convolutional one-stage object detection. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp 9626\u20139635. https:\/\/doi.org\/10.1109\/ICCV.2019.00972","DOI":"10.1109\/ICCV.2019.00972"},{"key":"6268_CR32","doi-asserted-by":"publisher","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 770\u2013778. https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"6268_CR33","doi-asserted-by":"publisher","unstructured":"Lin T-Y, Doll\u00e1r P, Girshick R, He K, Hariharan B, Belongie S (2017) Feature pyramid networks for object detection. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 936\u2013944. https:\/\/doi.org\/10.1109\/CVPR.2017.106","DOI":"10.1109\/CVPR.2017.106"},{"key":"6268_CR34","doi-asserted-by":"publisher","unstructured":"Du Y, Chen Z, Jia C, Yin X, Zheng T, Li C, Du Y, Jiang Y-G (2022) Svtr: Scene text recognition with a single visual model. In: Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI-22, pp 884\u2013890. https:\/\/doi.org\/10.24963\/ijcai.2022\/124","DOI":"10.24963\/ijcai.2022\/124"},{"key":"6268_CR35","unstructured":"Chung J, G\u00fcl\u00e7ehre \u00c7, Cho K, Bengio Y (2014) Empirical evaluation of gated recurrent neural networks on sequence modeling. CoRR arXiv:1412.3555"},{"key":"6268_CR36","doi-asserted-by":"crossref","unstructured":"He K, Gkioxari G, Doll\u00e1r P, Girshick R (2017) Mask r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp 2961\u20132969","DOI":"10.1109\/ICCV.2017.322"},{"key":"6268_CR37","doi-asserted-by":"publisher","unstructured":"Wang K, Babenko B, Belongie S (2011) End-to-end scene text recognition. In: 2011 International Conference on Computer Vision, pp 1457\u20131464. https:\/\/doi.org\/10.1109\/ICCV.2011.6126402","DOI":"10.1109\/ICCV.2011.6126402"},{"key":"6268_CR38","unstructured":"Veit A, Matera T, Neumann L, Matas J, Belongie SJ (2016) Coco-text: Dataset and benchmark for text detection and recognition in natural images. CoRR arXiv:1601.07140"},{"key":"6268_CR39","doi-asserted-by":"publisher","unstructured":"Ch\u2019ng CK, Chan CS (2017) Total-text: A comprehensive dataset for scene text detection and recognition. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol 01, pp 935\u2013942. https:\/\/doi.org\/10.1109\/ICDAR.2017.157","DOI":"10.1109\/ICDAR.2017.157"},{"key":"6268_CR40","doi-asserted-by":"publisher","unstructured":"Nayef N, Patel Y, Busta M, Chowdhury PN, Karatzas D, Khlif W, Matas J, Pal U, Burie J-C, Liu C-L, Ogier J-M (2019) Icdar2019 robust reading challenge on multi-lingual scene text detection and recognition\u2014rrc-mlt-2019. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp 1582\u20131587. https:\/\/doi.org\/10.1109\/ICDAR.2019.00254","DOI":"10.1109\/ICDAR.2019.00254"},{"key":"6268_CR41","unstructured":"Loshchilov I, Hutter F (2018) Fixing Weight Decay Regularization in Adam. https:\/\/openreview.net\/forum?id=rk6qdGgCZ"},{"issue":"11","key":"6268_CR42","first-page":"2579","volume":"9","author":"L Maaten","year":"2008","unstructured":"Maaten L, Hinton G (2008) Visualizing data using t-sne. J Mach Learn Res 9(11):2579\u2013605","journal-title":"J Mach Learn Res"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-024-06268-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-024-06268-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-024-06268-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T10:07:36Z","timestamp":1722593256000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-024-06268-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,9]]},"references-count":42,"journal-issue":{"issue":"14","published-print":{"date-parts":[[2024,9]]}},"alternative-id":["6268"],"URL":"https:\/\/doi.org\/10.1007\/s11227-024-06268-6","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-4280435\/v1","asserted-by":"object"}]},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"value":"0920-8542","type":"print"},{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,9]]},"assertion":[{"value":"24 May 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 June 2024","order":2,"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 no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}