{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:32:25Z","timestamp":1750221145555,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2018,6,5]],"date-time":"2018-06-05T00:00:00Z","timestamp":1528156800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Key R&D Program of China","award":["2017YFB1002203"],"award-info":[{"award-number":["2017YFB1002203"]}]},{"name":"National Nature Science Foundation of China (NSFC)","award":["61772495"],"award-info":[{"award-number":["61772495"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2018,6,5]]},"DOI":"10.1145\/3206025.3206043","type":"proceedings-article","created":{"date-parts":[[2018,6,11]],"date-time":"2018-06-11T12:36:20Z","timestamp":1528720580000},"page":"152-159","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["A Multi-Oriented Scene Text Detector with Position-Sensitive Segmentation"],"prefix":"10.1145","author":[{"given":"Peirui","family":"Cheng","sequence":"first","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiqiang","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2018,6,5]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_32"},{"key":"e_1_3_2_1_2_1","volume-title":"CVPR 2009. IEEE Conference on. 248--255","author":"Deng Jia","year":"2009","unstructured":"Jia Deng , Wei Dong , Richard Socher , Li Jia Li , Kai Li , and Fei Fei Li . 2009 . ImageNet: A large-scale hierarchical image database Computer Vision and Pattern Recognition, 2009 . CVPR 2009. IEEE Conference on. 248--255 . Jia Deng, Wei Dong, Richard Socher, Li Jia Li, Kai Li, and Fei Fei Li. 2009. ImageNet: A large-scale hierarchical image database Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on. 248--255."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Boris Epshtein Eyal Ofek and Yonatan Wexler. 2010. Detecting text in natural scenes with stroke width transform Computer Vision and Pattern Recognition. 2963--2970.  Boris Epshtein Eyal Ofek and Yonatan Wexler. 2010. Detecting text in natural scenes with stroke width transform Computer Vision and Pattern Recognition. 2963--2970.","DOI":"10.1109\/CVPR.2010.5540041"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Ankush Gupta Andrea Vedaldi and Andrew Zisserman. 2016. Synthetic Data for Text Localisation in Natural Images Computer Vision and Pattern Recognition. 2315--2324.  Ankush Gupta Andrea Vedaldi and Andrew Zisserman. 2016. Synthetic Data for Text Localisation in Natural Images Computer Vision and Pattern Recognition. 2315--2324.","DOI":"10.1109\/CVPR.2016.254"},{"key":"e_1_3_2_1_5_1","volume-title":"2017 IEEE International Conference on. IEEE, 2980--2988","author":"He Kaiming","year":"2017","unstructured":"Kaiming He , Georgia Gkioxari , Piotr Doll\u00e1r , and Ross Girshick . 2017 a. Mask r-cnn Computer Vision (ICCV) , 2017 IEEE International Conference on. IEEE, 2980--2988 . Kaiming He, Georgia Gkioxari, Piotr Doll\u00e1r, and Ross Girshick. 2017 a. Mask r-cnn Computer Vision (ICCV), 2017 IEEE International Conference on. IEEE, 2980--2988."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.331"},{"key":"e_1_3_2_1_8_1","volume-title":"2017 c. Deep direct regression for multi-oriented scene text detection. arXiv preprint arXiv:1703.08289","author":"He Wenhao","year":"2017","unstructured":"Wenhao He , Xu-Yao Zhang , Fei Yin , and Cheng-Lin Liu . 2017 c. Deep direct regression for multi-oriented scene text detection. arXiv preprint arXiv:1703.08289 ( 2017 ). Wenhao He, Xu-Yao Zhang, Fei Yin, and Cheng-Lin Liu. 2017 c. Deep direct regression for multi-oriented scene text detection. arXiv preprint arXiv:1703.08289 (2017)."},{"key":"e_1_3_2_1_9_1","volume-title":"DenseBox: Unifying Landmark Localization with End to End Object Detection. Computer Science","author":"Huang Lichao","year":"2015","unstructured":"Lichao Huang , Yi Yang , Yafeng Deng , and Yinan Yu. 2015. DenseBox: Unifying Landmark Localization with End to End Object Detection. Computer Science ( 2015 ). Lichao Huang, Yi Yang, Yafeng Deng, and Yinan Yu. 2015. DenseBox: Unifying Landmark Localization with End to End Object Detection. Computer Science (2015)."},{"volume-title":"Robust scene text detection with convolution neural network induced mser trees European Conference on Computer Vision","author":"Huang Weilin","key":"e_1_3_2_1_10_1","unstructured":"Weilin Huang , Yu Qiao , and Xiaoou Tang . 2014. Robust scene text detection with convolution neural network induced mser trees European Conference on Computer Vision . Springer , 497--511. Weilin Huang, Yu Qiao, and Xiaoou Tang. 2014. Robust scene text detection with convolution neural network induced mser trees European Conference on Computer Vision. Springer, 497--511."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0823-z"},{"key":"e_1_3_2_1_12_1","volume-title":"Deep Features for Text Spotting. In European Conference on Computer Vision. 512--528","author":"Jaderberg Max","year":"2014","unstructured":"Max Jaderberg , Andrea Vedaldi , and Andrew Zisserman . 2014 b . Deep Features for Text Spotting. In European Conference on Computer Vision. 512--528 . Max Jaderberg, Andrea Vedaldi, and Andrew Zisserman. 2014 b. Deep Features for Text Spotting. In European Conference on Computer Vision. 512--528."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967274"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.221"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"Yi Li Haozhi Qi Jifeng Dai Xiangyang Ji and Yichen Wei. 2017. Fully convolutional instance-aware semantic segmentation IEEE Conf. on Computer Vision and Pattern Recognition (CVPR). 2359--2367.  Yi Li Haozhi Qi Jifeng Dai Xiangyang Ji and Yichen Wei. 2017. Fully convolutional instance-aware semantic segmentation IEEE Conf. on Computer Vision and Pattern Recognition (CVPR). 2359--2367.","DOI":"10.1109\/CVPR.2017.472"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Minghui Liao Baoguang Shi Xiang Bai Xinggang Wang and Wenyu Liu. 2017. TextBoxes: A Fast Text Detector with a Single Deep Neural Network. AAAI. 4161--4167.  Minghui Liao Baoguang Shi Xiang Bai Xinggang Wang and Wenyu Liu. 2017. TextBoxes: A Fast Text Detector with a Single Deep Neural Network. AAAI. 4161--4167.","DOI":"10.1609\/aaai.v31i1.11196"},{"key":"e_1_3_2_1_18_1","volume-title":"Feature Pyramid Networks for Object Detection. In IEEE Conference on Computer Vision and Pattern Recognition. 936--944","author":"Lin Tsung Yi","year":"2017","unstructured":"Tsung Yi Lin , Piotr Dollar , Ross Girshick , Kaiming He , Bharath Hariharan , and Serge Belongie . 2017 . Feature Pyramid Networks for Object Detection. In IEEE Conference on Computer Vision and Pattern Recognition. 936--944 . Tsung Yi Lin, Piotr Dollar, Ross Girshick, Kaiming He, Bharath Hariharan, and Serge Belongie. 2017. Feature Pyramid Networks for Object Detection. In IEEE Conference on Computer Vision and Pattern Recognition. 936--944."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"volume-title":"Deep matching prior network: Toward tighter multi-oriented text detection Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Liu Yuliang","key":"e_1_3_2_1_21_1","unstructured":"Yuliang Liu and Lianwen Jin . 2017. Deep matching prior network: Toward tighter multi-oriented text detection Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , Vol. Vol. 2 . 8. Yuliang Liu and Lianwen Jin. 2017. Deep matching prior network: Toward tighter multi-oriented text detection Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Vol. Vol. 2. 8."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"crossref","unstructured":"Jonathan Long Evan Shelhamer and Trevor Darrell. 2015. Fully convolutional networks for semantic segmentation IEEE Conference on Computer Vision and Pattern Recognition. 3431--3440.  Jonathan Long Evan Shelhamer and Trevor Darrell. 2015. Fully convolutional networks for semantic segmentation IEEE Conference on Computer Vision and Pattern Recognition. 3431--3440.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"e_1_3_2_1_23_1","volume-title":"Queenstown, New Zealand, November 8--12","author":"Neumann Lukas","year":"2010","unstructured":"Lukas Neumann and Jiri Matas . 2010. A Method for Text Localization and Recognition in Real-World Images Computer Vision - ACCV 2010 - Asian Conference on Computer Vision , Queenstown, New Zealand, November 8--12 , 2010 , Revised Selected Papers . 770--783. Lukas Neumann and Jiri Matas. 2010. A Method for Text Localization and Recognition in Real-World Images Computer Vision - ACCV 2010 - Asian Conference on Computer Vision, Queenstown, New Zealand, November 8--12, 2010, Revised Selected Papers. 770--783."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"L. Neumann and J. Matas. 2012. Real-time scene text localization and recognition. In Computer Vision and Pattern Recognition. 3538--3545.   L. Neumann and J. Matas. 2012. Real-time scene text localization and recognition. In Computer Vision and Pattern Recognition. 3538--3545.","DOI":"10.1109\/CVPR.2012.6248097"},{"key":"e_1_3_2_1_25_1","volume-title":"Cascaded Segmentation-Detection Networks for Word-Level Text Spotting. arXiv preprint arXiv:1704.00834","author":"Qin Siyang","year":"2017","unstructured":"Siyang Qin and Roberto Manduchi . 2017. Cascaded Segmentation-Detection Networks for Word-Level Text Spotting. arXiv preprint arXiv:1704.00834 ( 2017 ). Siyang Qin and Roberto Manduchi. 2017. Cascaded Segmentation-Detection Networks for Word-Level Text Spotting. arXiv preprint arXiv:1704.00834 (2017)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Joseph Redmon Santosh Divvala Ross Girshick and Ali Farhadi. 2016. You Only Look Once: Unified Real-Time Object Detection Computer Vision and Pattern Recognition. 779--788.  Joseph Redmon Santosh Divvala Ross Girshick and Ali Farhadi. 2016. You Only Look Once: Unified Real-Time Object Detection Computer Vision and Pattern Recognition. 779--788.","DOI":"10.1109\/CVPR.2016.91"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.371"},{"volume-title":"Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support","author":"Sudre Carole H","key":"e_1_3_2_1_29_1","unstructured":"Carole H Sudre , Wenqi Li , Tom Vercauteren , Sebastien Ourselin , and M Jorge Cardoso . 2017. Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations . In Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support . Springer , 240--248. Carole H Sudre, Wenqi Li, Tom Vercauteren, Sebastien Ourselin, and M Jorge Cardoso. 2017. Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations. In Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support. Springer, 240--248."},{"key":"e_1_3_2_1_30_1","volume-title":"Detecting Text in Natural Image with Connectionist Text Proposal Network European Conference on Computer Vision. 56--72","author":"Tian Zhi","year":"2016","unstructured":"Zhi Tian , Weilin Huang , Tong He , Pan He , and Yu Qiao . 2016 . Detecting Text in Natural Image with Connectionist Text Proposal Network European Conference on Computer Vision. 56--72 . Zhi Tian, Weilin Huang, Tong He, Pan He, and Yu Qiao. 2016. Detecting Text in Natural Image with Connectionist Text Proposal Network European Conference on Computer Vision. 56--72."},{"key":"e_1_3_2_1_31_1","volume-title":"Coco-text: Dataset and benchmark for text detection and recognition in natural images. arXiv preprint arXiv:1601.07140","author":"Veit Andreas","year":"2016","unstructured":"Andreas Veit , Tomas Matera , Lukas Neumann , Jiri Matas , and Serge Belongie . 2016 . Coco-text: Dataset and benchmark for text detection and recognition in natural images. arXiv preprint arXiv:1601.07140 (2016). Andreas Veit, Tomas Matera, Lukas Neumann, Jiri Matas, and Serge Belongie. 2016. Coco-text: Dataset and benchmark for text detection and recognition in natural images. arXiv preprint arXiv:1601.07140 (2016)."},{"key":"e_1_3_2_1_32_1","volume-title":"Scene text detection via holistic, multi-channel prediction. arXiv preprint arXiv:1606.09002","author":"Yao Cong","year":"2016","unstructured":"Cong Yao , Xiang Bai , Nong Sang , Xinyu Zhou , Shuchang Zhou , and Zhimin Cao . 2016. Scene text detection via holistic, multi-channel prediction. arXiv preprint arXiv:1606.09002 ( 2016 ). Cong Yao, Xiang Bai, Nong Sang, Xinyu Zhou, Shuchang Zhou, and Zhimin Cao. 2016. Scene text detection via holistic, multi-channel prediction. arXiv preprint arXiv:1606.09002 (2016)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-29364-1_2"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.182"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","unstructured":"Zheng Zhang Wei Shen Cong Yao and Xiang Bai. 2015. Symmetry-based text line detection in natural scenes IEEE Conference on Computer Vision and Pattern Recognition. 2558--2567.  Zheng Zhang Wei Shen Cong Yao and Xiang Bai. 2015. Symmetry-based text line detection in natural scenes IEEE Conference on Computer Vision and Pattern Recognition. 2558--2567.","DOI":"10.1109\/CVPR.2015.7298871"},{"key":"e_1_3_2_1_36_1","volume-title":"Multi-oriented text detection with fully convolutional networks. arXiv preprint arXiv:1604.04018","author":"Zhang Zheng","year":"2016","unstructured":"Zheng Zhang , Chengquan Zhang , Wei Shen , Cong Yao , Wenyu Liu , and Xiang Bai . 2016. Multi-oriented text detection with fully convolutional networks. arXiv preprint arXiv:1604.04018 ( 2016 ). Zheng Zhang, Chengquan Zhang, Wei Shen, Cong Yao, Wenyu Liu, and Xiang Bai. 2016. Multi-oriented text detection with fully convolutional networks. arXiv preprint arXiv:1604.04018 (2016)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.179"},{"key":"e_1_3_2_1_38_1","first-page":"1","article-title":"DeepText: A Unified Framework for Text Proposal Generation and Text Detection in Natural Images","volume":"12","author":"Zhong Zhuoyao","year":"2016","unstructured":"Zhuoyao Zhong , Lianwen Jin , Shuye Zhang , and Ziyong Feng . 2016 . DeepText: A Unified Framework for Text Proposal Generation and Text Detection in Natural Images . Architecture Science 12 (2016), 1 -- 18 . Zhuoyao Zhong, Lianwen Jin, Shuye Zhang, and Ziyong Feng. 2016. DeepText: A Unified Framework for Text Proposal Generation and Text Detection in Natural Images. Architecture Science 12 (2016), 1--18.","journal-title":"Architecture Science"},{"key":"e_1_3_2_1_39_1","volume-title":"EAST: an efficient and accurate scene text detector. arXiv preprint arXiv:1704.03155","author":"Zhou Xinyu","year":"2017","unstructured":"Xinyu Zhou , Cong Yao , He Wen , Yuzhi Wang , Shuchang Zhou , Weiran He , and Jiajun Liang . 2017. EAST: an efficient and accurate scene text detector. arXiv preprint arXiv:1704.03155 ( 2017 ). Xinyu Zhou, Cong Yao, He Wen, Yuzhi Wang, Shuchang Zhou, Weiran He, and Jiajun Liang. 2017. EAST: an efficient and accurate scene text detector. arXiv preprint arXiv:1704.03155 (2017)."}],"event":{"name":"ICMR '18: International Conference on Multimedia Retrieval","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Yokohama Japan","acronym":"ICMR '18"},"container-title":["Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3206025.3206043","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3206025.3206043","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T01:08:15Z","timestamp":1750208895000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3206025.3206043"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,6,5]]},"references-count":39,"alternative-id":["10.1145\/3206025.3206043","10.1145\/3206025"],"URL":"https:\/\/doi.org\/10.1145\/3206025.3206043","relation":{},"subject":[],"published":{"date-parts":[[2018,6,5]]},"assertion":[{"value":"2018-06-05","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}