{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T13:10:41Z","timestamp":1777900241135,"version":"3.51.4"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2020,1,15]],"date-time":"2020-01-15T00:00:00Z","timestamp":1579046400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,15]],"date-time":"2020-01-15T00:00:00Z","timestamp":1579046400000},"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":["Sci. China Inf. Sci."],"published-print":{"date-parts":[[2020,2]]},"DOI":"10.1007\/s11432-019-2737-0","type":"journal-article","created":{"date-parts":[[2020,1,20]],"date-time":"2020-01-20T12:02:45Z","timestamp":1579521765000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":40,"title":["SynthText3D: synthesizing scene text images from 3D virtual worlds"],"prefix":"10.1007","volume":"63","author":[{"given":"Minghui","family":"Liao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Boyu","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shangbang","family":"Long","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minghang","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cong","family":"Yao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiang","family":"Bai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,1,15]]},"reference":[{"key":"2737_CR1","doi-asserted-by":"crossref","unstructured":"Gupta A, Vedaldi A, Zisserman A. Synthetic data for text localisation in natural images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016. 2315\u20132324","DOI":"10.1109\/CVPR.2016.254"},{"key":"2737_CR2","doi-asserted-by":"crossref","unstructured":"Zhan F, Lu S, Xue C. Verisimilar image synthesis for accurate detection and recognition of texts in scenes. In: Proceedings of European Conference on Computer Vision, 2018. 249\u2013266","DOI":"10.1007\/978-3-030-01237-3_16"},{"key":"2737_CR3","unstructured":"Jaderberg M, Simonyan K, Vedaldi A, et al. Synthetic data and artificial neural networks for natural scene text recognition. 2014. ArXiv: 1406.2227"},{"key":"2737_CR4","doi-asserted-by":"crossref","unstructured":"Zhu Z, Huang T, Shi B, et al. Progressive pose attention transfer for person image generation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019. 2347\u20132356","DOI":"10.1109\/CVPR.2019.00245"},{"key":"2737_CR5","doi-asserted-by":"crossref","unstructured":"Varol G, Romero J, Martin X, et al. Learning from synthetic humans. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017. 109\u2013117","DOI":"10.1109\/CVPR.2017.492"},{"key":"2737_CR6","doi-asserted-by":"crossref","unstructured":"Papon J, Schoeler M. Semantic pose using deep networks trained on synthetic RGB-D. In: Proceedings of IEEE International Conference on Computer Vision, 2015. 774\u2013782","DOI":"10.1109\/ICCV.2015.95"},{"key":"2737_CR7","unstructured":"McCormac J, Handa A, Leutenegger S, et al. Scenenet RGB-D: 5 m photorealistic images of synthetic indoor trajectories with ground truth. 2016. ArXiv: 1612.05079"},{"key":"2737_CR8","doi-asserted-by":"crossref","unstructured":"Ros G, Sellart L, Materzynska J, et al. The synthia dataset: a large collection of synthetic images for semantic segmentation of urban scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016. 3234\u20133243","DOI":"10.1109\/CVPR.2016.352"},{"key":"2737_CR9","doi-asserted-by":"crossref","unstructured":"Saleh F S, Aliakbarian M S, Salzmann M, et al. Effective use of synthetic data for urban scene semantic segmentation. In: Proceedings of European Conference on Computer Vision, 2018. 86\u2013103","DOI":"10.1007\/978-3-030-01216-8_6"},{"key":"2737_CR10","doi-asserted-by":"crossref","unstructured":"Peng X, Sun B, Ali K, et al. Learning deep object detectors from 3D models. In: Proceedings of IEEE International Conference on Computer Vision, 2015. 1278\u20131286","DOI":"10.1109\/ICCV.2015.151"},{"key":"2737_CR11","doi-asserted-by":"crossref","unstructured":"Tremblay J, To T, Birchfield S. Falling things: a synthetic dataset for 3D object detection and pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018. 2038\u20132041","DOI":"10.1109\/CVPRW.2018.00275"},{"key":"2737_CR12","doi-asserted-by":"crossref","unstructured":"Hinterstoisser S, Pauly O, Heibel H, et al. An annotation saved is an annotation earned: using fully synthetic training for object instance detection. 2019. ArXiv: 1902.09967","DOI":"10.1109\/ICCVW.2019.00340"},{"key":"2737_CR13","doi-asserted-by":"publisher","first-page":"220104","DOI":"10.1007\/s11432-019-2636-x","volume":"62","author":"Y Y Ye","year":"2019","unstructured":"Ye Y Y, Zhang C, Hao X L. Arpnet: attention regional proposal network for 3D object detection. Sci China Inf Sci, 2019, 62: 220104","journal-title":"Sci China Inf Sci"},{"key":"2737_CR14","doi-asserted-by":"publisher","first-page":"3210","DOI":"10.1109\/TIP.2017.2694224","volume":"26","author":"J Cao","year":"2017","unstructured":"Cao J, Pang Y, Li X. Learning multilayer channel features for pedestrian detection. IEEE Trans Image Process, 2017, 26: 3210\u20133220","journal-title":"IEEE Trans Image Process"},{"key":"2737_CR15","doi-asserted-by":"publisher","first-page":"5538","DOI":"10.1109\/TIP.2016.2609807","volume":"25","author":"J Cao","year":"2016","unstructured":"Cao J, Pang Y, Li X. Pedestrian detection inspired by appearance constancy and shape symmetry. IEEE Trans Image Process, 2016, 25: 5538\u20135551","journal-title":"IEEE Trans Image Process"},{"key":"2737_CR16","unstructured":"Quiter C, Ernst M. deepdrive\/deepdrive: 2.0. 2018. https:\/\/zenodo.org\/record\/1248998#.Xhd25Ef0laQ"},{"key":"2737_CR17","unstructured":"Martinez M, Sitawarin C, Finch K, et al. Beyond grand theft auto V for training, testing and enhancing deep learning in self driving cars. 2017. ArXiv: 1712.01397"},{"key":"2737_CR18","doi-asserted-by":"crossref","unstructured":"Qiu W, Yuille A. Unrealcv: connecting computer vision to unreal engine. In: Proceedings of European Conference on Computer Vision, 2016. 909\u2013916","DOI":"10.1007\/978-3-319-49409-8_75"},{"key":"2737_CR19","unstructured":"Ganoni O, Mukundan R. A framework for visually realistic multi-robot simulation in natural environment. 2017. ArXiv: 1708.01938"},{"key":"2737_CR20","unstructured":"Wang T, Wu J D, Coates A, et al. End-to-end text recognition with convolutional neural networks. In: Proceedings of the 21st International Conference on Pattern Recognition (ICPR), 2012. 3304\u20133308"},{"key":"2737_CR21","doi-asserted-by":"crossref","unstructured":"Zhan F, Zhu H, Lu S. Spatial fusion gan for image synthesis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019. 3653\u20133662","DOI":"10.1109\/CVPR.2019.00377"},{"key":"2737_CR22","unstructured":"Goodfellow I, Pouget-Abadie J, Mirza M, et al. Generative adversarial nets. In: Proceedings of Advances in Neural Information Processing Systems, 2014. 2672\u20132680"},{"key":"2737_CR23","doi-asserted-by":"publisher","first-page":"1480","DOI":"10.1109\/TPAMI.2014.2366765","volume":"37","author":"Q Ye","year":"2015","unstructured":"Ye Q, Doermann D. Text detection and recognition in imagery: a survey. IEEE Trans Pattern Anal Mach Intell, 2015, 37: 1480\u20131500","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2737_CR24","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1360\/N112018-00003","volume":"48","author":"X Bai","year":"2018","unstructured":"Bai X, Yang M K, Shi B G, et al. Deep learning for scene text detection and recognition (in Chinese). Sci Sin Inform, 2018, 48: 531\u2013544","journal-title":"Sci Sin Inform"},{"key":"2737_CR25","unstructured":"Liu Y, Jin L, Zhang S, et al. Detecting curve text in the wild: new dataset and new solution. 2017. ArXiv: 1712.02170"},{"key":"2737_CR26","doi-asserted-by":"crossref","unstructured":"Liao M, Shi B, Bai X, et al. TextBoxes: a fast text detector with a single deep neural network. In: Proceedings of the AAAI Conference on Artificial Intelligence, 2017. 4161\u20134167","DOI":"10.1609\/aaai.v31i1.11196"},{"key":"2737_CR27","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, et al. Arbitrary-oriented scene text detection via rotation proposals. IEEE Trans Multimedia, 2018, 20: 3111\u20133122","journal-title":"IEEE Trans Multimedia"},{"key":"2737_CR28","doi-asserted-by":"crossref","unstructured":"Liu Y, Jin L. Deep matching prior network: toward tighter multi-oriented text detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017. 1962\u20131969","DOI":"10.1109\/CVPR.2017.368"},{"key":"2737_CR29","doi-asserted-by":"crossref","unstructured":"He W, Zhang Y-X, Yin F, et al. Deep direct regression for multi-oriented scene text detection. In: Proceedings of IEEE International Conference on Computer Vision, 2017. 745\u2013753","DOI":"10.1109\/ICCV.2017.87"},{"key":"2737_CR30","doi-asserted-by":"crossref","unstructured":"Zhou X, Yao C, Wen H, et al. EAST: an efficient and accurate scene text detector. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017. 5551\u20135560","DOI":"10.1109\/CVPR.2017.283"},{"key":"2737_CR31","doi-asserted-by":"crossref","unstructured":"Liao M, Zhu Z, Shi B, et al. Rotation-sensitive regression for oriented scene text detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018. 5909\u20135918","DOI":"10.1109\/CVPR.2018.00619"},{"key":"2737_CR32","unstructured":"Liao M, Lyu P, He M, et al. Mask TextSpotter: an end-to-end trainable neural network for spotting text with arbitrary shapes. IEEE Trans Pattern Anal Mach Intell, 2019"},{"key":"2737_CR33","unstructured":"Ren S, He K, Girshick R, et al. Faster R-CNN: towards real-time object detection with region proposal networks. In: Proceedings of Advances in Neural Information Processing Systems, 2015. 91\u201399"},{"key":"2737_CR34","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, et al. SSD: single shot multibox detector. In: Proceedings of European Conference on Computer Vision, 2016. 21\u201337","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"2737_CR35","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. TextBoxes++: a single-shot oriented scene text detector. IEEE Trans Image Process, 2018, 27: 3676\u20133690","journal-title":"IEEE Trans Image Process"},{"key":"2737_CR36","doi-asserted-by":"crossref","unstructured":"Shi B, Bai X, Belongie S. Detecting oriented text in natural images by linking segments. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017. 2550\u20132558","DOI":"10.1109\/CVPR.2017.371"},{"key":"2737_CR37","doi-asserted-by":"crossref","unstructured":"Wu Y, Natarajan P. Self-organized text detection with minimal post-processing via border learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017. 5000\u20135009","DOI":"10.1109\/ICCV.2017.535"},{"key":"2737_CR38","doi-asserted-by":"crossref","unstructured":"Long S, Ruan J, Zhang W, et al. Textsnake: a flexible representation for detecting text of arbitrary shapes. In: Proceedings of European Conference on Computer Vision, 2018. 20\u201336","DOI":"10.1007\/978-3-030-01216-8_2"},{"key":"2737_CR39","doi-asserted-by":"crossref","unstructured":"Deng D, Liu H, Li X, et al. Pixellink: detecting scene text via instance segmentation. In: Proceedings of the AAAI Conference on Artificial Intelligence, 2018. 6773\u20136780","DOI":"10.1609\/aaai.v32i1.12269"},{"key":"2737_CR40","doi-asserted-by":"crossref","unstructured":"Lyu P, Yao C, Wu W, et al. Multi-oriented scene text detection via corner localization and region segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018. 7553\u20137563","DOI":"10.1109\/CVPR.2018.00788"},{"key":"2737_CR41","doi-asserted-by":"publisher","first-page":"220103","DOI":"10.1007\/s11432-019-2673-8","volume":"62","author":"J Chen","year":"2019","unstructured":"Chen J, Lian Z H, Wang Y Z, et al. Irregular scene text detection via attention guided border labeling. Sci China Inf Sci, 2019, 62: 220103","journal-title":"Sci China Inf Sci"},{"key":"2737_CR42","doi-asserted-by":"publisher","first-page":"898","DOI":"10.1109\/TPAMI.2010.161","volume":"33","author":"P Arbel\u00e1ez","year":"2011","unstructured":"Arbel\u00e1ez P, Maire M, Fowlkes C, et al. Contour detection and hierarchical image segmentation. IEEE Trans Pattern Anal Mach Intell, 2011, 33: 898\u2013916","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2737_CR43","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1109\/TPAMI.2013.158","volume":"36","author":"S J Lu","year":"2014","unstructured":"Lu S J, Tan C, Lim J-H. Robust and efficient saliency modeling from image co-occurrence histograms. IEEE Trans Pattern Anal Mach Intell, 2014, 36: 195\u2013201","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2737_CR44","doi-asserted-by":"crossref","unstructured":"Lin Y-T, Maire M, Belongie S, et al. Microsoft COCO: common objects in context. In: Proceedings of European Conference on Computer Vision, 2014. 740\u2013755","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2737_CR45","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/0146-664X(82)90169-1","volume":"18","author":"S D Roth","year":"1982","unstructured":"Roth S D. Ray casting for modeling solids. Comput Graph Image Process, 1982, 18: 109\u2013144","journal-title":"Comput Graph Image Process"},{"key":"2737_CR46","doi-asserted-by":"crossref","unstructured":"Karatzas D, Shafait F, Uchida S, et al. ICDAR 2013 robust reading competition. In: Proceedings of International Conference on Document Analysis and Recognition, 2013. 1484\u20131493","DOI":"10.1109\/ICDAR.2013.221"},{"key":"2737_CR47","doi-asserted-by":"crossref","unstructured":"Karatzas D, Gomez-Bigorda L, Nicolaou A, et al. ICDAR 2015 competition on robust reading. In: Proceedings of International Conference on Document Analysis and Recognition, 2015. 1156\u20131160","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"2737_CR48","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, et al. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016. 770\u2013778","DOI":"10.1109\/CVPR.2016.90"}],"container-title":["Science China Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-019-2737-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11432-019-2737-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-019-2737-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,12]],"date-time":"2023-05-12T11:30:16Z","timestamp":1683891016000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11432-019-2737-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,1,15]]},"references-count":48,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2020,2]]}},"alternative-id":["2737"],"URL":"https:\/\/doi.org\/10.1007\/s11432-019-2737-0","relation":{},"ISSN":["1674-733X","1869-1919"],"issn-type":[{"value":"1674-733X","type":"print"},{"value":"1869-1919","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,1,15]]},"assertion":[{"value":"15 October 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 November 2019","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 December 2019","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 January 2020","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"120105"}}