{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T11:17:30Z","timestamp":1753355850278},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2022,2,28]],"date-time":"2022-02-28T00:00:00Z","timestamp":1646006400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,2,28]],"date-time":"2022-02-28T00:00:00Z","timestamp":1646006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2022,5]]},"DOI":"10.1007\/s11042-022-12619-3","type":"journal-article","created":{"date-parts":[[2022,2,28]],"date-time":"2022-02-28T02:02:35Z","timestamp":1646013755000},"page":"15285-15302","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["A spatial feature adaptive network for text detection"],"prefix":"10.1007","volume":"81","author":[{"given":"Qingsong","family":"Tang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoxu","family":"Feng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangde","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,2,28]]},"reference":[{"key":"12619_CR1","first-page":"1206","volume-title":"Proceedings of the IEEE international conference on computer vision","author":"M Busta","year":"2015","unstructured":"Busta M, Neumann L, Matas J (2015) Fastext: efficient unconstrained scene text detector. In: Proceedings of the IEEE international conference on computer vision, pp 1206\u20131214"},{"key":"12619_CR2","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1016\/j.media.2016.11.004","volume":"36","author":"H Chen","year":"2017","unstructured":"Chen H, Qi X, Yu L et al (2017) Dcan: deep contour-aware networks for object instance segmentation from histology images - sciencedirect. Med Image Anal 36:135\u2013146","journal-title":"Med Image Anal"},{"key":"12619_CR3","first-page":"440","volume-title":"International conference on document analysis and recognition","author":"A Coates","year":"2011","unstructured":"Coates A, Carpenter B, Case C et al (2011) Text detection and character recognition in scene images with unsupervised feature learning. In: International conference on document analysis and recognition, pp 440\u2013445"},{"key":"12619_CR4","first-page":"99","volume-title":"IEEE Access","author":"H Gao","year":"2020","unstructured":"Gao H, Cao L, Yu D, Xiong X, Cao M (2020) Semantic Segmentation of Marine Remote Sensing Based on a Cross Direction Attention Mechanism. In: IEEE Access, p 99"},{"issue":"4","key":"12619_CR5","doi-asserted-by":"publisher","first-page":"520","DOI":"10.1109\/LGRS.2016.2521684","volume":"13","author":"H Guan","year":"2016","unstructured":"Guan H, Yu Y et al (2016) Pole-Like Road Object Detection in Mobile LiDAR Data via Supervoxel and Bag-of-Contextual-Visual-Words Representation. IEEE Geoscience and Remote Sensing Letters 13(4):520\u2013524","journal-title":"IEEE Geoscience and Remote Sensing Letters"},{"key":"12619_CR6","first-page":"770","volume-title":"European conference on computer vision","author":"K He","year":"2016","unstructured":"He K, Zhang X, Ren S et al (2016) Deep residual learning for image recognition. In: European conference on computer vision, pp 770\u2013778"},{"key":"12619_CR7","first-page":"3047","volume-title":"Proceedings of the IEEE Conference on computer vision and pattern recognition","author":"P He","year":"2017","unstructured":"He P, Huang W, He T et al (2017) Single shot text detector with regional attention. In: Proceedings of the IEEE Conference on computer vision and pattern recognition, pp 3047\u20133055"},{"key":"12619_CR8","first-page":"2961","volume-title":"Proceedings of the IEEE international conference on computer vision","author":"K He","year":"2017","unstructured":"He K, Gkioxari G, Doll\u00e1r P et al (2017) Mask r-cnn. Proc. In: Proceedings of the IEEE international conference on computer vision, pp 2961\u20132969"},{"key":"12619_CR9","first-page":"497","volume-title":"European conference on computer vision","author":"W Huang","year":"2014","unstructured":"Huang W, Qiao Y, Tang X (2014) Robust scene text detection with convolution neural network induced MSER trees. In: European conference on computer vision, pp 497\u2013511"},{"key":"12619_CR10","first-page":"512","volume-title":"European conference on computer vision","author":"M Jaderberg","year":"2014","unstructured":"Jaderberg M, Vedaldi A, Zisserman A (2014) Deep features for text spotting. In: European conference on computer vision, pp 512\u2013528"},{"key":"12619_CR11","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. International Journal of Computer Vision 116:1\u201320","journal-title":"International Journal of Computer Vision"},{"key":"12619_CR12","first-page":"1156","volume-title":"International conference on document analysis and recognition","author":"D Karatzas","year":"2015","unstructured":"Karatzas D, Gomez-Bigorda L, Nicolaou A et al (2015) ICDAR 2015 competition on robust reading. In: International conference on document analysis and recognition, pp 1156\u20131160"},{"key":"12619_CR13","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y Lecun","year":"1998","unstructured":"Lecun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proceedings of the IEEE 86:2278\u20132324","journal-title":"Proceedings of the IEEE"},{"key":"12619_CR14","first-page":"4161","volume-title":"Proceedings of the AAAI conference on artificial intelligence","author":"M Liao","year":"2017","unstructured":"Liao M, Shi B, Bai X et al (2017) Textboxes: a fast text detector with a single deep neural network. In: Proceedings of the AAAI conference on artificial intelligence, pp 4161\u20134167"},{"key":"12619_CR15","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 Transactions on Image Processing 27:3676\u20133690","journal-title":"IEEE Transactions on Image Processing"},{"key":"12619_CR16","first-page":"11474","volume-title":"Proceedings of the AAAI conference on artificial intelligence","author":"M Liao","year":"2020","unstructured":"Liao M, Wan Z, Yao C et al (2020) Real-time scene text detection with differentiable Binarization. In: Proceedings of the AAAI conference on artificial intelligence, pp 11474\u201311481"},{"key":"12619_CR17","first-page":"2117","volume-title":"Proceedings of the IEEE Conference on computer vision and pattern recognition","author":"TY Lin","year":"2017","unstructured":"Lin TY, Doll\u00e1r P, Girshick R et al (2017) Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on computer vision and pattern recognition, pp 2117\u20132125"},{"key":"12619_CR18","first-page":"21","volume-title":"European conference on computer vision","author":"W Liu","year":"2016","unstructured":"Liu W, Anguelov D, Erhan D et al (2016) SSD: single shot multibox detector. In: European conference on computer vision, pp 21\u201337"},{"key":"12619_CR19","unstructured":"Liu J, Liu X, Sheng J et al (2019) Pyramid mask text detector. In: arXiv preprint arXiv:1903.11800, 2019"},{"issue":"4","key":"12619_CR20","first-page":"640","volume":"39","author":"J Long","year":"2015","unstructured":"Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence 39(4):640\u2013651","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"12619_CR21","first-page":"4898","volume-title":"Proceedings of the 30th International Conference on Neural Information Processing Systems","author":"W Luo","year":"2016","unstructured":"Luo W, Li Y, Urtasun R, Zemel R (2016) Understanding the effective receptive field in deep convolutional neural networks. In: Proceedings of the 30th International Conference on Neural Information Processing Systems, vol 29, pp 4898\u20134906"},{"key":"12619_CR22","doi-asserted-by":"publisher","first-page":"565","DOI":"10.1109\/3DV.2016.79","volume-title":"2016 fourth international conference on 3D vision (3DV)","author":"F Milletari","year":"2016","unstructured":"Milletari F, Navab N, Ahmadi SA (2016) V-net: Fully convolutional neural networks for volumetric medical image segmentation. In: 2016 fourth international conference on 3D vision (3DV), pp 565\u2013571"},{"key":"12619_CR23","first-page":"1454","volume-title":"International conference on document analysis and recognition","author":"N Nayef","year":"2017","unstructured":"Nayef N, Yin F, Bizid I et al (2017) ICDAR2017 robust reading challenge on multi-lingual scene text detection and script identification-rrc-mlt. In: International conference on document analysis and recognition, pp 1454\u20131459"},{"issue":"1","key":"12619_CR24","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1016\/0734-189X(86)90128-3","volume":"35","author":"T Pavlidis","year":"1986","unstructured":"Pavlidis T (1986) A vectorizer and feature extractor for document recognition. Computer Vision, Graphics, and Image Processing 35(1):111\u2013127","journal-title":"Computer Vision, Graphics, and Image Processing"},{"key":"12619_CR25","unstructured":"Powers DM (2011) Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation. arXiv preprint arXiv:2010.16061, 2(1):37\u201363"},{"key":"12619_CR26","first-page":"1874","volume-title":"Proceedings of the IEEE Conference on computer vision and pattern recognition","author":"W Shi","year":"2016","unstructured":"Shi W, Caballero J, Husz\u00e1r F et al (2016) Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In: Proceedings of the IEEE Conference on computer vision and pattern recognition, pp 1874\u20131883"},{"key":"12619_CR27","first-page":"2550","volume-title":"Proceedings of the IEEE Conference on computer vision and pattern recognition","author":"BG Shi","year":"2017","unstructured":"Shi BG, Bai X, Belongie S (2017) Detecting oriented text in natural images by linking segments. In: Proceedings of the IEEE Conference on computer vision and pattern recognition, pp 2550\u20132558"},{"key":"12619_CR28","volume-title":"International Conference on Learning Representations 2015","author":"K Simonyan","year":"2015","unstructured":"Simonyan K, Zisserman A (2015) Very Deep Convolutional Networks for Large-Scale Image Recognition. In: International Conference on Learning Representations 2015. (ICLR 2015)"},{"key":"12619_CR29","first-page":"56","volume-title":"European conference on computer vision","author":"Z Tian","year":"2016","unstructured":"Tian Z, Huang W, He T et al (2016) Detecting text in natural image with connectionist text proposal network. In: European conference on computer vision, pp 56\u201372"},{"key":"12619_CR30","first-page":"243","volume-title":"European conference on computer vision","author":"T Vu","year":"2018","unstructured":"Vu T, Van Nguyen C, Pham TX et al (2018) Fast and efficient image quality enhancement via desubpixel convolutional neural networks. In: European conference on computer vision, pp 243\u2013259"},{"key":"12619_CR31","first-page":"9336","volume-title":"Proceedings of the IEEE Conference on computer vision and pattern recognition","author":"W Wang","year":"2019","unstructured":"Wang W, Xie E, Li X et al (2019) Shape robust text detection with progressive scale expansion network. In: Proceedings of the IEEE Conference on computer vision and pattern recognition, pp 9336\u20139345"},{"key":"12619_CR32","first-page":"8440","volume-title":"Proceedings of the IEEE international conference on computer vision","author":"W Wang","year":"2019","unstructured":"Wang W, Xie E, Song X et al (2019) Efficient and accurate arbitrary-shaped text detection with pixel aggregation network. In: Proceedings of the IEEE international conference on computer vision, pp 8440\u20138449"},{"key":"12619_CR33","first-page":"3","volume-title":"European conference on computer vision","author":"S Woo","year":"2018","unstructured":"Woo S, Park J, Lee JY et al (2018) Cbam: convolutional block attention module. In: European conference on computer vision, pp 3\u201319"},{"key":"12619_CR34","first-page":"9038","volume-title":"Proceedings of the AAAI conference on artificial intelligence","author":"E Xie","year":"2019","unstructured":"Xie E, Zang Y, Shao S, Yu G, Yao C, Li G (2019) Scene text detection with supervised pyramid context network. In: Proceedings of the AAAI conference on artificial intelligence, vol 33, pp 9038\u20139045"},{"issue":"5","key":"12619_CR35","doi-asserted-by":"publisher","first-page":"1280","DOI":"10.1109\/TIFS.2018.2871746","volume":"14","author":"ZL Yang","year":"2019","unstructured":"Yang ZL, Guo XQ, Chen ZM, Huang YF, Zhang YJ (2019) RNN-Stega: linguistic steganography based on recurrent neural networks. IEEE Transactions on Information Forensics and Security 14(5):1280\u20131295","journal-title":"IEEE Transactions on Information Forensics and Security"},{"key":"12619_CR36","unstructured":"Yuliang L, Lianwen J, Shuaitao Z et al (2017) Detecting curve text in the wild: new dataset and new solution. In: arXiv preprint arXiv:1712.02170, 2017"},{"key":"12619_CR37","first-page":"4159","volume-title":"Proceedings of the IEEE Conference on computer vision and pattern recognition","author":"Z Zhang","year":"2016","unstructured":"Zhang Z, Zhang C, Shen W et al (2016) Multi-oriented text detection with fully convolutional networks. In: Proceedings of the IEEE Conference on computer vision and pattern recognition, pp 4159\u20134167"},{"key":"12619_CR38","first-page":"5551","volume-title":"Proceedings of the IEEE Conference on computer vision and pattern recognition","author":"X Zhou","year":"2017","unstructured":"Zhou X, Yao C, Wen H et al (2017) East: an efficient and accurate scene text detector. In: Proceedings of the IEEE Conference on computer vision and pattern recognition, pp 5551\u20135560"},{"key":"12619_CR39","first-page":"3735","volume-title":"2018 24th international conference on pattern recognition (ICPR), Beijing, 2018","author":"Y Zhu","year":"2018","unstructured":"Zhu Y, Du J (2018) Sliding line point regression for shape robust scene text detection. In: 2018 24th international conference on pattern recognition (ICPR), Beijing, 2018, pp 3735\u20133740"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-022-12619-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-022-12619-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-022-12619-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,2]],"date-time":"2022-05-02T11:20:03Z","timestamp":1651490403000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-022-12619-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,28]]},"references-count":39,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2022,5]]}},"alternative-id":["12619"],"URL":"https:\/\/doi.org\/10.1007\/s11042-022-12619-3","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,2,28]]},"assertion":[{"value":"23 October 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 February 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 February 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 February 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}