{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T11:09:10Z","timestamp":1747998550200,"version":"3.37.3"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2022,8,11]],"date-time":"2022-08-11T00:00:00Z","timestamp":1660176000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,8,11]],"date-time":"2022-08-11T00:00:00Z","timestamp":1660176000000},"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":["62176062","61771145"],"award-info":[{"award-number":["62176062","61771145"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Process Lett"],"published-print":{"date-parts":[[2023,8]]},"DOI":"10.1007\/s11063-022-10975-7","type":"journal-article","created":{"date-parts":[[2022,8,11]],"date-time":"2022-08-11T12:02:38Z","timestamp":1660219358000},"page":"3967-3983","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["High-speed Scene Text Detection with Attention and Multi-scale Label Generation"],"prefix":"10.1007","volume":"55","author":[{"given":"Yanzhao","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7096-1830","authenticated-orcid":false,"given":"Xiaodong","family":"Gu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,8,11]]},"reference":[{"issue":"7","key":"10975_CR1","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1145\/129902.129906","volume":"35","author":"BR Vatti","year":"1992","unstructured":"Vatti BR (1992) A generic solution to polygon clipping. Commun ACM 35(7):56\u201364. https:\/\/doi.org\/10.1145\/129902.129906","journal-title":"Commun ACM"},{"key":"10975_CR2","doi-asserted-by":"crossref","unstructured":"Fu J, Liu J, Tian H J, Li Y (2019) Dual Attention Network for Scene Segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. IEEE Computer Society Press, Los Alamitos, pp 3146\u20133154","DOI":"10.1109\/CVPR.2019.00326"},{"key":"10975_CR3","doi-asserted-by":"publisher","unstructured":"Li H C, Xiong P F, An J, Wang L X (2018) Pyramid Attention Network for Semantic Segmentation. https:\/\/doi.org\/10.48550\/arXiv.1805.10180","DOI":"10.48550\/arXiv.1805.10180"},{"key":"10975_CR4","doi-asserted-by":"crossref","unstructured":"Liao M H, Wan Z Y, Yao C, Chen K, Bai X (2020) Real-time Scene Text Detection with Differentiable Binarization. In: Proceedings of the AAAI Conference on Artificial Intelligence. AAAI Press, Palo Alto, pp 11474\u201311481","DOI":"10.1609\/aaai.v34i07.6812"},{"key":"10975_CR5","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C, Reed S E (2016) SSD: single shot multibox detector. In: Proceedings of European Conference on Computer Vision. Springer, Heidelberg, pp 21\u201337","DOI":"10.1007\/978-3-319-46448-0_2"},{"issue":"8","key":"10975_CR6","doi-asserted-by":"publisher","first-page":"3676","DOI":"10.1109\/TIP.2018.2825107","volume":"27","author":"M Liao","year":"2018","unstructured":"Liao M, Shi B, Bai X (2018) Textboxes++: A single-shot oriented scene text detector. IEEE Trans Image Process 27(8):3676\u20133690. https:\/\/doi.org\/10.1109\/TIP.2018.2825107","journal-title":"IEEE Trans Image Process"},{"key":"10975_CR7","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. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE Computer Society Press, Los Alamitos, pp 5551\u20135560","DOI":"10.1109\/CVPR.2017.283"},{"key":"10975_CR8","doi-asserted-by":"crossref","unstructured":"Liao M, Zhu Z, Shi B, Xia G, Bai X (2018) Rotation-sensitive regression for oriented scene text detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. IEEE Computer Society Press, Los Alamitos, pp 5909\u20135918","DOI":"10.1109\/CVPR.2018.00619"},{"key":"10975_CR9","doi-asserted-by":"crossref","unstructured":"Lyu P, Liao M, Yao C, Wu W, Bai X (2018) Mask textspotter: An end-to-end trainable neural network for spotting text with arbitrary shapes. In: Proceedings of European Conference on Computer Vision. Springer, Heidelberg, pp 71\u201388","DOI":"10.1007\/978-3-030-01264-9_5"},{"key":"10975_CR10","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. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. IEEE Computer Society Press, Los Alamitos, pp 9336\u20139345","DOI":"10.1109\/CVPR.2019.00956"},{"issue":"11","key":"10975_CR11","doi-asserted-by":"publisher","first-page":"5566","DOI":"10.1109\/TIP.2019.2900589","volume":"28","author":"YC Xu","year":"2019","unstructured":"Xu YC, Wang YK, Zhou W, Wang YP (2019) TextField: learning a deep direction field for irregular scene text detection. IEEE Trans Image Process 28(11):5566\u20135579. https:\/\/doi.org\/10.1109\/TIP.2019.2900589","journal-title":"IEEE Trans Image Process"},{"key":"10975_CR12","doi-asserted-by":"crossref","unstructured":"Yu F, Koltun V, Funkhouser T (2017) Dilated Residual Networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE Computer Society Press, Los Alamitos, pp 472\u2013480","DOI":"10.1109\/CVPR.2017.75"},{"key":"10975_CR13","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE Computer Society Press, Los Alamitos, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"10975_CR14","doi-asserted-by":"crossref","unstructured":"Gupta A, Vedaldi A, Zisserman A (2016) Synthetic data for text localisation in natural images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE Computer Society Press, Los Alamitos, pp 2315\u20132324","DOI":"10.1109\/CVPR.2016.254"},{"key":"10975_CR15","doi-asserted-by":"crossref","unstructured":"Chng C K, Chan C S (2017) Total-text: A comprehensive dataset for scene text detection and recognition. In: Proceedings of the 14th IAPR International Conference on Document Analysis and Recognition. IAPR Press, New York, pp 935\u2013942","DOI":"10.1109\/ICDAR.2017.157"},{"key":"10975_CR16","doi-asserted-by":"publisher","unstructured":"Karatzas D, Gomez-Bigorda L, Nicolaou A, Ghosh S K, Bagdanov A D, Iwamura M, et al (2015) ICDAR 2015 competition on robust reading. In: Proceedings of 2015 13th International Conference on Document Analysis and Recognition. https:\/\/doi.org\/10.1109\/ICDAR.2015. 7333942","DOI":"10.1109\/ICDAR.2015"},{"key":"10975_CR17","unstructured":"Yao C, Bai X, Liu W Y, Ma Y, Tu Z W (2012) Detecting texts of arbitrary orientations in natural images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE Computer Society Press, Los Alamitos, pp 1083\u20131090"},{"issue":"11","key":"10975_CR18","doi-asserted-by":"publisher","first-page":"4737","DOI":"10.1109\/TIP.2014.2353813","volume":"23","author":"C Yao","year":"2014","unstructured":"Yao C, Bai X, Liu W (2014) A unified framework for multioriented text detection and recognition. IEEE Trans Image Process 23(11):4737\u20134749","journal-title":"IEEE Trans Image Process"},{"key":"10975_CR19","doi-asserted-by":"crossref","unstructured":"Dai J, Qi H, Xiong Y, Li Y, Zhang G, Hu H, Wei Y (2017) Deformable convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision. IEEE Computer Society Press, Los Alamitos, pp 764\u2013773","DOI":"10.1109\/ICCV.2017.89"},{"key":"10975_CR20","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. In: Proceedings of European Conference on Computer Vision. Springer, Heidelberg, pp 20\u201336","DOI":"10.1007\/978-3-030-01216-8_2"},{"key":"10975_CR21","doi-asserted-by":"crossref","unstructured":"Wang X, Jiang Y, Luo Z, Liu C L, Choi H, Kim S (2019) Arbitrary shape scene text detection with adaptive text region representation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. IEEE Computer Society Press, Los Alamitos, pp 6449\u20136458","DOI":"10.1109\/CVPR.2019.00661"},{"key":"10975_CR22","doi-asserted-by":"crossref","unstructured":"Zhang C, Liang B, Huang Z, En M, Han J, Ding E, Ding X (2019) Look more than once: An accurate detector for text of arbitrary shapes. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. IEEE Computer Society Press, Los Alamitos, pp 10552\u201310561","DOI":"10.1109\/CVPR.2019.01080"},{"key":"10975_CR23","doi-asserted-by":"crossref","unstructured":"Baek Y, Lee B, Han D, Yun S, Lee H (2019) Character region awareness for text detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. IEEE Computer Society Press, Los Alamitos, pp 9365\u20139374","DOI":"10.1109\/CVPR.2019.00959"},{"key":"10975_CR24","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. https:\/\/doi.org\/10.1016\/j.patcog.2019.02.002","journal-title":"Pattern Recogn"},{"key":"10975_CR25","doi-asserted-by":"publisher","unstructured":"Tian Z, Huang W, He T, He P, Qiao Y (2016) Detecting text in natural image with connectionist text proposal network. https:\/\/doi.org\/10.48550\/arXiv.1609.03605","DOI":"10.48550\/arXiv.1609.03605"},{"key":"10975_CR26","doi-asserted-by":"crossref","unstructured":"He P, Huang W, He T, Zhu Q, Qiao Y, Li X (2017) Single shot text detector with regional attention. In: Proceedings of the IEEE International Conference on Computer Vision. IEEE Computer Society Press, Los Alamitos, pp 3047\u20133055","DOI":"10.1109\/ICCV.2017.331"},{"key":"10975_CR27","doi-asserted-by":"crossref","unstructured":"Hu H, Zhang C, Luo Y, Wang Y, Han J, Ding E (2017) Wordsup: Exploiting word annotations for character based text detection. In: Proceedings of the IEEE International Conference on Computer Vision. IEEE Computer Society Press, Los Alamitos, pp 4940\u20134949","DOI":"10.1109\/ICCV.2017.529"},{"key":"10975_CR28","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. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. IEEE Computer Society Press, Los Alamitos, pp 7553\u20137563","DOI":"10.1109\/CVPR.2018.00788"},{"key":"10975_CR29","doi-asserted-by":"crossref","unstructured":"He W, Zhang X, Yin F, Liu C (2017) Deep direct regression for multi-oriented scene text detection. In: Proceedings of the IEEE International Conference on Computer Vision. IEEE Computer Society Press, Los Alamitos, pp 745\u2013753","DOI":"10.1109\/ICCV.2017.87"},{"issue":"11","key":"10975_CR30","doi-asserted-by":"publisher","first-page":"3111","DOI":"10.1109\/TMM.2018.2818020","volume":"20","author":"J Ma","year":"2018","unstructured":"Ma J, Shao W, Ye H, Wang L, Wang H, Zheng Y, Xue X (2018) Arbitrary-oriented scene text detection via rotation proposals. IEEE Trans Multimedia 20(11):3111\u20133122. https:\/\/doi.org\/10.1109\/TMM.2018.2818020","journal-title":"IEEE Trans Multimedia"},{"key":"10975_CR31","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. AAAI Press, Palo Alto, pp 6773-6780","DOI":"10.1609\/aaai.v32i1.12269"},{"key":"10975_CR32","doi-asserted-by":"crossref","unstructured":"Liu Z, Lin G, Yang S, Feng J, Lin W, Goh W L (2018) Learning markov clustering networks for scene text detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. IEEE Computer Society Press, Los Alamitos, pp 6936\u20136944","DOI":"10.1109\/CVPR.2018.00725"},{"key":"10975_CR33","doi-asserted-by":"crossref","unstructured":"Tian Z, Shu M, Lyu P, Li R, Zhou C, Shen X, Jia J (2019) Learning shape-aware embedding for scene text detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. IEEE Computer Society Press, Los Alamitos, pp 4234\u20134243","DOI":"10.1109\/CVPR.2019.00436"}],"container-title":["Neural Processing Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-022-10975-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11063-022-10975-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-022-10975-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,31]],"date-time":"2023-07-31T16:34:41Z","timestamp":1690821281000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11063-022-10975-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,11]]},"references-count":33,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023,8]]}},"alternative-id":["10975"],"URL":"https:\/\/doi.org\/10.1007\/s11063-022-10975-7","relation":{},"ISSN":["1370-4621","1573-773X"],"issn-type":[{"type":"print","value":"1370-4621"},{"type":"electronic","value":"1573-773X"}],"subject":[],"published":{"date-parts":[[2022,8,11]]},"assertion":[{"value":"18 July 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 August 2022","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 that there is no conflict of interests regarding the publication of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}