{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T04:53:55Z","timestamp":1781585635999,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T00:00:00Z","timestamp":1634428800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"the Shanghai Committee of Science and Technology","award":["20DZ1100800"],"award-info":[{"award-number":["20DZ1100800"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,10,17]]},"DOI":"10.1145\/3474085.3478328","type":"proceedings-article","created":{"date-parts":[[2021,10,18]],"date-time":"2021-10-18T20:00:05Z","timestamp":1634587205000},"page":"3791-3794","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":75,"title":["MMOCR"],"prefix":"10.1145","author":[{"given":"Zhanghui","family":"Kuang","sequence":"first","affiliation":[{"name":"SenseTime Research, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongbin","family":"Sun","sequence":"additional","affiliation":[{"name":"SenseTime Research, Shen Zhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhizhong","family":"Li","sequence":"additional","affiliation":[{"name":"SenseTime Research, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyu","family":"Yue","sequence":"additional","affiliation":[{"name":"Center for Perceptual and Interactive Intelligence, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tsui Hin","family":"Lin","sequence":"additional","affiliation":[{"name":"SenseTime Research, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianyong","family":"Chen","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guang Zhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huaqiang","family":"Wei","sequence":"additional","affiliation":[{"name":"SenseTime Research, Shen Zhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiqin","family":"Zhu","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guang Zhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tong","family":"Gao","sequence":"additional","affiliation":[{"name":"SenseTime Research, Shen Zhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Chen","sequence":"additional","affiliation":[{"name":"SenseTime Research & Shanghai AI Laboratory, Guang Zhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wayne","family":"Zhang","sequence":"additional","affiliation":[{"name":"SenseTime Research, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dahua","family":"Lin","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2021,10,17]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"Youngmin Baek Bado Lee Dongyoon Han Sangdoo Yun and Hwalsuk Lee. 2019. Character region awareness for text detection. In CVPR. 9365--9374. Youngmin Baek Bado Lee Dongyoon Han Sangdoo Yun and Hwalsuk Lee. 2019. Character region awareness for text detection. In CVPR. 9365--9374.","DOI":"10.1109\/CVPR.2019.00959"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219861"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00104"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Jiaqi Duan Youjiang Xu Zhanghui Kuang Xiaoyu Yue Hongbin Sun Yue Guan and Wayne Zhang. 2019. Geometry normalization networks for accurate scene text detection. In ICCV. 9136--9145. Jiaqi Duan Youjiang Xu Zhanghui Kuang Xiaoyu Yue Hongbin Sun Yue Guan and Wayne Zhang. 2019. Geometry normalization networks for accurate scene text detection. In ICCV. 9136--9145.","DOI":"10.1109\/ICCV.2019.00923"},{"key":"e_1_3_2_1_5_1","volume-title":"Sebastian Brarda, Steffen Bickel, Johannes H\u00f6 hne, and Jean Baptiste.","author":"Katti Faddoul Anoop Raveendra","year":"2018","unstructured":"Anoop Raveendra Katti Faddoul , Christian Reisswig Cordula Guder , Sebastian Brarda, Steffen Bickel, Johannes H\u00f6 hne, and Jean Baptiste. 2018 . Chargrid : Towards Understanding 2D Documents. In EMNLP. 4459--4469. Anoop Raveendra Katti Faddoul, Christian Reisswig Cordula Guder, Sebastian Brarda, Steffen Bickel, Johannes H\u00f6 hne, and Jean Baptiste. 2018. Chargrid: Towards Understanding 2D Documents. In EMNLP. 4459--4469."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"e_1_3_2_1_7_1","unstructured":"Kaiming He Georgia Gkioxari Piotr Doll\u00e1r and Ross Girshick. 2017. Mask R-CNN. In ICCV. 2961--2969. Kaiming He Georgia Gkioxari Piotr Doll\u00e1r and Ross Girshick. 2017. Mask R-CNN. In ICCV. 2961--2969."},{"key":"e_1_3_2_1_8_1","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep residual learning for image recognition. In CVPR. 770--778. Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep residual learning for image recognition. In CVPR. 770--778."},{"key":"e_1_3_2_1_9_1","volume-title":"Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes. CoRR","author":"Hong Yuanduo","year":"2021","unstructured":"Yuanduo Hong , Huihui Pan , Weichao Sun , and Yisong Jia . 2021. Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes. CoRR , Vol. abs\/ 2101 .06085 ( 2021 ). Yuanduo Hong, Huihui Pan, Weichao Sun, and Yisong Jia. 2021. Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes. CoRR, Vol. abs\/2101.06085 (2021)."},{"key":"e_1_3_2_1_10_1","volume-title":"Neural architectures for named entity recognition. arXiv preprint arXiv:1603.01360","author":"Lample Guillaume","year":"2016","unstructured":"Guillaume Lample , Miguel Ballesteros , Sandeep Subramanian , Kazuya Kawakami , and Chris Dyer . 2016. Neural architectures for named entity recognition. arXiv preprint arXiv:1603.01360 ( 2016 ). Guillaume Lample, Miguel Ballesteros, Sandeep Subramanian, Kazuya Kawakami, and Chris Dyer. 2016. Neural architectures for named entity recognition. arXiv preprint arXiv:1603.01360 (2016)."},{"key":"e_1_3_2_1_11_1","volume-title":"Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition. AAAI","author":"Li Hui","year":"2019","unstructured":"Hui Li , Peng Wang , Chunhua Shen , and Guyu Zhang . 2019. Show , Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition. AAAI ( 2019 ), 8610--8617. Hui Li, Peng Wang, Chunhua Shen, and Guyu Zhang. 2019. Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition. AAAI (2019), 8610--8617."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Minghui Liao Zhaoyi Wan Cong Yao Kai Chen and Xiang Bai. 2020. Real-Time Scene Text Detection with Differentiable Binarization. In AAAI. 11474--11481. Minghui Liao Zhaoyi Wan Cong Yao Kai Chen and Xiang Bai. 2020. Real-Time Scene Text Detection with Differentiable Binarization. In AAAI. 11474--11481.","DOI":"10.1609\/aaai.v34i07.6812"},{"key":"e_1_3_2_1_13_1","volume-title":"Scene text recognition from two-dimensional perspective. AAAI","author":"Liao Minghui","year":"2019","unstructured":"Minghui Liao , Jian Zhang , Zhaoyi Wan , Fengming Xie , Jiajun Liang , Pengyuan Lyu , Cong Yao , and Xiang Bai . 2019. Scene text recognition from two-dimensional perspective. AAAI ( 2019 ), 8714--8721. Minghui Liao, Jian Zhang, Zhaoyi Wan, Fengming Xie, Jiajun Liang, Pengyuan Lyu, Cong Yao, and Xiang Bai. 2019. Scene text recognition from two-dimensional perspective. AAAI (2019), 8714--8721."},{"key":"e_1_3_2_1_14_1","volume-title":"Pyramid Mask Text Detector. CoRR","author":"Liu Jingchao","year":"2019","unstructured":"Jingchao Liu , Xuebo Liu , Jie Sheng , Ding Liang , Xin Li , and Qingjie Liu . 2019. Pyramid Mask Text Detector. CoRR ( 2019 ). Jingchao Liu, Xuebo Liu, Jie Sheng, Ding Liang, Xin Li, and Qingjie Liu. 2019. Pyramid Mask Text Detector. CoRR (2019)."},{"key":"e_1_3_2_1_15_1","volume-title":"Cheng Yang Fu, and Alexander C","author":"Liu Wei","year":"2016","unstructured":"Wei Liu , Dragomir Anguelov , Dumitru Erhan , Christian Szegedy , Scott Reed , Cheng Yang Fu, and Alexander C . Berg . 2016 a. SSD: single shot multibox detector. In ECCV. 21--37. Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng Yang Fu, and Alexander C. Berg. 2016a. SSD: single shot multibox detector. In ECCV. 21--37."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"Wei Liu Chaofeng Chen Kwan-Yee K Wong Zhizhong Su and Junyu Han. 2016b. STAR-Net: A SpaTial Attention Residue Network for Scene Text Recognition.. In BMVC. Wei Liu Chaofeng Chen Kwan-Yee K Wong Zhizhong Su and Junyu Han. 2016b. STAR-Net: A SpaTial Attention Residue Network for Scene Text Recognition.. In BMVC.","DOI":"10.5244\/C.30.43"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Jonathan Long Evan Shelhamer and Trevor Darrell. 2015. Fully convolutional networks for semantic segmentation. In CVPR. 3431--3440. Jonathan Long Evan Shelhamer and Trevor Darrell. 2015. Fully convolutional networks for semantic segmentation. In CVPR. 3431--3440.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"Shangbang Long Jiaqiang Ruan Wenjie Zhang Xin He Wenhao Wu and Cong Yao. 2018. TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes. In ECCV. 19--35. Shangbang Long Jiaqiang Ruan Wenjie Zhang Xin He Wenhao Wu and Cong Yao. 2018. TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes. In ECCV. 19--35.","DOI":"10.1007\/978-3-030-01216-8_2"},{"key":"e_1_3_2_1_19_1","unstructured":"Rasmus Berg Palm Ole Winther and Florian Laws. 2017. CloudScan - A configuration-free invoice analysis system using recurrent neural networks. In ICDAR. 406--413. Rasmus Berg Palm Ole Winther and Florian Laws. 2017. CloudScan - A configuration-free invoice analysis system using recurrent neural networks. In ICDAR. 406--413."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"crossref","unstructured":"Joseph Redmon and Ali Farhadi. 2017. YOLO9000: Better Faster Stronger. In CVPR. 6517--6525. Joseph Redmon and Ali Farhadi. 2017. YOLO9000: Better Faster Stronger. In CVPR. 6517--6525.","DOI":"10.1109\/CVPR.2017.690"},{"key":"e_1_3_2_1_21_1","volume-title":"YOLOv3: An Incremental Improvement. CoRR","author":"Redmon Joseph","year":"2018","unstructured":"Joseph Redmon and Ali Farhadi . 2018. YOLOv3: An Incremental Improvement. CoRR , Vol. abs\/ 1804 .02767 ( 2018 ). Joseph Redmon and Ali Farhadi. 2018. YOLOv3: An Incremental Improvement. CoRR, Vol. abs\/1804.02767 (2018)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.5555\/2969239.2969250"},{"key":"e_1_3_2_1_23_1","volume-title":"NRTR: A no-recurrence sequence-to-sequence model for scene text recognition. In ICDAR. 781--786.","author":"Sheng Fenfen","year":"2019","unstructured":"Fenfen Sheng , Zhineng Chen , and Bo Xu . 2019 . NRTR: A no-recurrence sequence-to-sequence model for scene text recognition. In ICDAR. 781--786. Fenfen Sheng, Zhineng Chen, and Bo Xu. 2019. NRTR: A no-recurrence sequence-to-sequence model for scene text recognition. In ICDAR. 781--786."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2646371"},{"key":"e_1_3_2_1_25_1","unstructured":"Baoguang Shi Xinggang Wang Pengyuan Lyu Cong Yao and Xiang Bai. 2016b. Robust Scene Text Recognition with Automatic Rectification. In CVPR. 4168--4176. Baoguang Shi Xinggang Wang Pengyuan Lyu Cong Yao and Xiang Bai. 2016b. Robust Scene Text Recognition with Automatic Rectification. In CVPR. 4168--4176."},{"key":"e_1_3_2_1_26_1","first-page":"2035","article-title":"ASTER","volume":"41","author":"Shi Baoguang","year":"2018","unstructured":"Baoguang Shi , Mingkun Yang , Xinggang Wang , Pengyuan Lyu , Cong Yao , and Xiang Bai . 2018 . ASTER : An Attentional Scene Text Recognizer with Flexible Rectification. PAMI , Vol. 41 , 9 (2018), 2035 -- 2048 . Baoguang Shi, Mingkun Yang, Xinggang Wang, Pengyuan Lyu, Cong Yao, and Xiang Bai. 2018. ASTER : An Attentional Scene Text Recognizer with Flexible Rectification. PAMI, Vol. 41, 9 (2018), 2035--2048.","journal-title":"An Attentional Scene Text Recognizer with Flexible Rectification. PAMI"},{"key":"e_1_3_2_1_27_1","unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. In ICLR. Karen Simonyan and Andrew Zisserman. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. In ICLR."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.5555\/1304596.1304846"},{"key":"e_1_3_2_1_29_1","volume-title":"Spatial Dual-Modality Graph Reasoning for Key Information Extraction. arXiv preprint","author":"Sun Hongbin","year":"2021","unstructured":"Hongbin Sun , Zhanghui Kuang , Xiaoyu Yue , Chenhao Lin , and Wayne Zhang . 2021. Spatial Dual-Modality Graph Reasoning for Key Information Extraction. arXiv preprint ( 2021 ). Hongbin Sun, Zhanghui Kuang, Xiaoyu Yue, Chenhao Lin, and Wayne Zhang. 2021. Spatial Dual-Modality Graph Reasoning for Key Information Extraction. arXiv preprint (2021)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"C Szegedy W Liu Y Jia and P Sermanet. 2015. Going deeper with convolutions. In CVPR. 1--9. C Szegedy W Liu Y Jia and P Sermanet. 2015. Going deeper with convolutions. In CVPR. 1--9.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350988"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"crossref","unstructured":"Pengfei Wang Chengquan Zhang Fei Qi Shanshan Liu Xiaoqiang Zhang Pengyuan Lyu Junyu Han Jingtuo Liu Errui Ding and Guangming Shi. 2021. PGNet: Real-time Arbitrarily-Shaped Text Spotting with Point Gathering Network. In AAAI. 2782--2790. Pengfei Wang Chengquan Zhang Fei Qi Shanshan Liu Xiaoqiang Zhang Pengyuan Lyu Junyu Han Jingtuo Liu Errui Ding and Guangming Shi. 2021. PGNet: Real-time Arbitrarily-Shaped Text Spotting with Point Gathering Network. In AAAI. 2782--2790.","DOI":"10.1609\/aaai.v35i4.16383"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Wenhai Wang Enze Xie Xiang Li Wenbo Hou Tong Lu Gang Yu and Shuai Shao. 2019 a. Shape robust text detection with progressive scale expansion network. In CVPR. 9336--9345. Wenhai Wang Enze Xie Xiang Li Wenbo Hou Tong Lu Gang Yu and Shuai Shao. 2019 a. Shape robust text detection with progressive scale expansion network. In CVPR. 9336--9345.","DOI":"10.1109\/CVPR.2019.00956"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"crossref","unstructured":"Wenhai Wang Enze Xie Xiaoge Song Yuhang Zang Wenjia Wang Tong Lu Gang Yu and Chunhua Shen. 2019 b. Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network. In ICCV. 8439--8448. Wenhai Wang Enze Xie Xiaoge Song Yuhang Zang Wenjia Wang Tong Lu Gang Yu and Chunhua Shen. 2019 b. Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network. In ICCV. 8439--8448.","DOI":"10.1109\/ICCV.2019.00853"},{"key":"e_1_3_2_1_35_1","unstructured":"Zecheng Xie Yaoxiong Huang Yuanzhi Zhu Lianwen Jin Yuliang Liu and Lele Xie. 2019. Aggregation cross-entropy for sequence recognition. In CVPR. 6538--6547. Zecheng Xie Yaoxiong Huang Yuanzhi Zhu Lianwen Jin Yuliang Liu and Lele Xie. 2019. Aggregation cross-entropy for sequence recognition. In CVPR. 6538--6547."},{"key":"e_1_3_2_1_36_1","volume-title":"CLUENER2020: Fine-grained Named Entity Recognition Dataset and Benchmark for Chinese. arXiv preprint","author":"Xu Liang","year":"2020","unstructured":"Liang Xu , Yu Tong , Qianqian Dong , Yixuan Liao , Cong Yu , Yin Tian , Weitang Liu , Lu Li , Caiquan Liu , and Xuanwei Zhang . 2020 . CLUENER2020: Fine-grained Named Entity Recognition Dataset and Benchmark for Chinese. arXiv preprint (2020). Liang Xu, Yu Tong, Qianqian Dong, Yixuan Liao, Cong Yu, Yin Tian, Weitang Liu, Lu Li, Caiquan Liu, and Xuanwei Zhang. 2020. CLUENER2020: Fine-grained Named Entity Recognition Dataset and Benchmark for Chinese. arXiv preprint (2020)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"crossref","unstructured":"Mingkun Yang Yushuo Guan Minghui Liao Xin He Kaigui Bian Song Bai Cong Yao and Xiang Bai. 2019. Symmetry-constrained rectification network for scene text recognition. In ICCV. 9146--9155. Mingkun Yang Yushuo Guan Minghui Liao Xin He Kaigui Bian Song Bai Cong Yao and Xiang Bai. 2019. Symmetry-constrained rectification network for scene text recognition. In ICCV. 9146--9155.","DOI":"10.1109\/ICCV.2019.00924"},{"key":"e_1_3_2_1_38_1","unstructured":"Deli Yu Xuan Li Chengquan Zhang Tao Liu Junyu Han Jingtuo Liu and Errui Ding. 2020 a. Towards Accurate Scene Text Recognition With Semantic Reasoning Networks. In CVPR. 12110--12119. Deli Yu Xuan Li Chengquan Zhang Tao Liu Junyu Han Jingtuo Liu and Errui Ding. 2020 a. Towards Accurate Scene Text Recognition With Semantic Reasoning Networks. In CVPR. 12110--12119."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"Wenwen Yu Ning Lu Xianbiao Qi Ping Gong and Rong Xiao. 2020 b. PICK: Processing key information extraction from documents using improved graph learning-convolutional networks. In ICPR. 4363--4370. Wenwen Yu Ning Lu Xianbiao Qi Ping Gong and Rong Xiao. 2020 b. PICK: Processing key information extraction from documents using improved graph learning-convolutional networks. In ICPR. 4363--4370.","DOI":"10.1109\/ICPR48806.2021.9412927"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"crossref","unstructured":"Xiaoyu Yue Zhanghui Kuang Chenhao Lin Hongbin Sun and Wayne Zhang. 2020. RobustScanner: Dynamically Enhancing Positional Clues for Robust Text Recognition. In ECCV. 135--151. Xiaoyu Yue Zhanghui Kuang Chenhao Lin Hongbin Sun and Wayne Zhang. 2020. RobustScanner: Dynamically Enhancing Positional Clues for Robust Text Recognition. In ECCV. 135--151.","DOI":"10.1007\/978-3-030-58529-7_9"},{"key":"e_1_3_2_1_41_1","unstructured":"Xiaoyu Yue Zhanghui Kuang and Wayne Zhang. 2021. SegOCR:\u00a0Simple\u00a0Baseline. In Unpublished\u00a0Manuscript. Xiaoyu Yue Zhanghui Kuang and Wayne Zhang. 2021. SegOCR:\u00a0Simple\u00a0Baseline. In Unpublished\u00a0Manuscript."},{"key":"e_1_3_2_1_42_1","unstructured":"Xiaoyu Yue Zhanghui Kuang Zhaoyang Zhang Zhenfang Chen Pan He Yu Qiao and Wei Zhang. 2018. Boosting up Scene Text Detectors with Guided CNN. In BMVC. Xiaoyu Yue Zhanghui Kuang Zhaoyang Zhang Zhenfang Chen Pan He Yu Qiao and Wei Zhang. 2018. Boosting up Scene Text Detectors with Guided CNN. In BMVC."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"crossref","unstructured":"Shi-Xue Zhang Xiaobin Zhu Jie-Bo Hou Chang Liu Chun Yang Hongfa Wang and Xu-Cheng Yin. 2020. Deep Relational Reasoning Graph Network for Arbitrary Shape Text Detection. In CVPR. 9696--9705. Shi-Xue Zhang Xiaobin Zhu Jie-Bo Hou Chang Liu Chun Yang Hongfa Wang and Xu-Cheng Yin. 2020. Deep Relational Reasoning Graph Network for Arbitrary Shape Text Detection. In CVPR. 9696--9705.","DOI":"10.1109\/CVPR42600.2020.00972"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"crossref","unstructured":"Suncong Zheng Feng Wang Hongyun Bao Yuexing Hao Peng Zhou and Bo Xu. 2017. Joint Extraction of Entities and Relations Based on a Novel Tagging Scheme. In ACL. 1227--1236. Suncong Zheng Feng Wang Hongyun Bao Yuexing Hao Peng Zhou and Bo Xu. 2017. Joint Extraction of Entities and Relations Based on a Novel Tagging Scheme. In ACL. 1227--1236.","DOI":"10.18653\/v1\/P17-1113"},{"key":"e_1_3_2_1_45_1","volume-title":"EAST: An Efficient and Accurate Scene Text Detector. CVPR","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. CVPR (2017), 2642--2651. Xinyu Zhou, Cong Yao, He Wen, Yuzhi Wang, Shuchang Zhou, Weiran He, and Jiajun Liang. 2017. EAST: An Efficient and Accurate Scene Text Detector. CVPR (2017), 2642--2651."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"crossref","unstructured":"Yiqin Zhu Jianyong Chen Lingyu Liang Zhuanghui Kuang Lianwen Jin and Wayne Zhang. 2021. Fourier Contour Embedding for Arbitrary-Shaped Text Detection. In CVPR. Yiqin Zhu Jianyong Chen Lingyu Liang Zhuanghui Kuang Lianwen Jin and Wayne Zhang. 2021. Fourier Contour Embedding for Arbitrary-Shaped Text Detection. In CVPR.","DOI":"10.1109\/CVPR46437.2021.00314"}],"event":{"name":"MM '21: ACM Multimedia Conference","location":"Virtual Event China","acronym":"MM '21","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 29th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3478328","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3474085.3478328","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:48:26Z","timestamp":1750193306000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3478328"}},"subtitle":["A Comprehensive Toolbox for Text Detection, Recognition and Understanding"],"short-title":[],"issued":{"date-parts":[[2021,10,17]]},"references-count":46,"alternative-id":["10.1145\/3474085.3478328","10.1145\/3474085"],"URL":"https:\/\/doi.org\/10.1145\/3474085.3478328","relation":{},"subject":[],"published":{"date-parts":[[2021,10,17]]},"assertion":[{"value":"2021-10-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}