{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,23]],"date-time":"2025-07-23T12:04:28Z","timestamp":1753272268575,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,8,24]],"date-time":"2021-08-24T00:00:00Z","timestamp":1629763200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61976076, 61632007, 61932009 and 61806066"],"award-info":[{"award-number":["61976076, 61632007, 61932009 and 61806066"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018AAA0102002"],"award-info":[{"award-number":["2018AAA0102002"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,8,24]]},"DOI":"10.1145\/3460426.3463623","type":"proceedings-article","created":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T22:50:29Z","timestamp":1630536629000},"page":"331-338","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["NASTER: Non-local Attentional Scene Text Recognizer"],"prefix":"10.1145","author":[{"given":"Lei","family":"Wu","sequence":"first","affiliation":[{"name":"Hefei University of Technology, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xueliang","family":"Liu","sequence":"additional","affiliation":[{"name":"Hefei University of Technology, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanbin","family":"Hao","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunjie","family":"Ma","sequence":"additional","affiliation":[{"name":"Hefei University of Technology, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Richang","family":"Hong","sequence":"additional","affiliation":[{"name":"Hefei University of Technology, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,9]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00481"},{"key":"e_1_3_2_1_2_1","volume-title":"Edit Probability for Scene Text Recognition. In 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 1508--1516","author":"Bai F.","year":"2018","unstructured":"F. Bai , Z. Cheng , and Y. Niu . 2018 . Edit Probability for Scene Text Recognition. In 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 1508--1516 . https:\/\/doi.org\/10.1109\/CVPR. 2018 .00163 10.1109\/CVPR.2018.00163 F. Bai, Z. Cheng, and Y. Niu. 2018. Edit Probability for Scene Text Recognition. In 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 1508--1516. https:\/\/doi.org\/10.1109\/CVPR.2018.00163"},{"key":"e_1_3_2_1_3_1","volume-title":"GCNet: Non-Local Networks Meet Squeeze-Excitation Networks and Beyond. 1971--1980","author":"Cao Yue","year":"2019","unstructured":"Yue Cao , Jiarui Xu , and Stephen Lin . 2019 . GCNet: Non-Local Networks Meet Squeeze-Excitation Networks and Beyond. 1971--1980 . https:\/\/doi.org\/10.1109\/ICCVW.2019.00246 10.1109\/ICCVW.2019.00246 Yue Cao, Jiarui Xu, and Stephen Lin. 2019. GCNet: Non-Local Networks Meet Squeeze-Excitation Networks and Beyond. 1971--1980. https:\/\/doi.org\/10.1109\/ICCVW.2019.00246"},{"key":"e_1_3_2_1_4_1","volume-title":"Focusing Attention: Towards Accurate Text Recognition in Natural Images. 5086--5094. https:\/\/doi.org\/10.1109\/ICCV.2017.543","author":"Cheng Zhanzhan","year":"2017","unstructured":"Zhanzhan Cheng , Fan Bai , and Yunlu Xu . 2017 . Focusing Attention: Towards Accurate Text Recognition in Natural Images. 5086--5094. https:\/\/doi.org\/10.1109\/ICCV.2017.543 10.1109\/ICCV.2017.543 Zhanzhan Cheng, Fan Bai, and Yunlu Xu. 2017. Focusing Attention: Towards Accurate Text Recognition in Natural Images. 5086--5094. https:\/\/doi.org\/10.1109\/ICCV.2017.543"},{"key":"e_1_3_2_1_5_1","volume-title":"AON: Towards Arbitrarily-Oriented Text Recognition. In 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 5571--5579","author":"Cheng Z.","year":"2018","unstructured":"Z. Cheng , Y. Xu , and F. Bai . 2018 . AON: Towards Arbitrarily-Oriented Text Recognition. In 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 5571--5579 . https:\/\/doi.org\/10.1109\/CVPR. 2018 .00584 10.1109\/CVPR.2018.00584 Z. Cheng, Y. Xu, and F. Bai. 2018. AON: Towards Arbitrarily-Oriented Text Recognition. In 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 5571--5579. https:\/\/doi.org\/10.1109\/CVPR.2018.00584"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.01.094"},{"key":"e_1_3_2_1_7_1","volume-title":"Double Supervised Network with Attention Mechanism for Scene Text Recognition. CoRR","author":"Gao Yuting","year":"2018","unstructured":"Yuting Gao , Zheng Huang , and Yuchen Dai . 2018. Double Supervised Network with Attention Mechanism for Scene Text Recognition. CoRR , Vol. abs\/ 1808 .00677 ( 2018 ). arxiv: 1808.00677 http:\/\/arxiv.org\/abs\/1808.00677 Yuting Gao, Zheng Huang, and Yuchen Dai. 2018. Double Supervised Network with Attention Mechanism for Scene Text Recognition. CoRR, Vol. abs\/1808.00677 (2018). arxiv: 1808.00677 http:\/\/arxiv.org\/abs\/1808.00677"},{"key":"e_1_3_2_1_8_1","volume-title":"Synthetic Data for Text Localisation in Natural Images. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2315--2324","author":"Gupta A.","year":"2016","unstructured":"A. Gupta , A. Vedaldi , and A. Zisserman . 2016 . Synthetic Data for Text Localisation in Natural Images. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2315--2324 . https:\/\/doi.org\/10.1109\/CVPR. 2016 .254 10.1109\/CVPR.2016.254 A. Gupta, A. Vedaldi, and A. Zisserman. 2016. Synthetic Data for Text Localisation in Natural Images. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2315--2324. https:\/\/doi.org\/10.1109\/CVPR.2016.254"},{"key":"e_1_3_2_1_9_1","volume-title":"Deep Residual Learning for Image Recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 770--778","author":"He K.","year":"2016","unstructured":"K. He , X. Zhang , S. Ren , and J. Sun . 2016 . Deep Residual Learning for Image Recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 770--778 . https:\/\/doi.org\/10.1109\/CVPR. 2016 .90 10.1109\/CVPR.2016.90 K. He, X. Zhang, S. Ren, and J. Sun. 2016. Deep Residual Learning for Image Recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 770--778. https:\/\/doi.org\/10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_10_1","volume-title":"An End-to-End TextSpotter with Explicit Alignment and Attention. In 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 5020--5029","author":"He T.","year":"2018","unstructured":"T. He , Z. Tian , and W. Huang . 2018 . An End-to-End TextSpotter with Explicit Alignment and Attention. In 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 5020--5029 . https:\/\/doi.org\/10.1109\/CVPR. 2018 .00527 10.1109\/CVPR.2018.00527 T. He, Z. Tian, and W. Huang. 2018. An End-to-End TextSpotter with Explicit Alignment and Attention. In 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 5020--5029. https:\/\/doi.org\/10.1109\/CVPR.2018.00527"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2913372"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0823-z"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126402"},{"key":"e_1_3_2_1_14_1","volume-title":"ICDAR 2015 competition on Robust Reading. In 2015 13th International Conference on Document Analysis and Recognition (ICDAR). 1156--1160","author":"Karatzas D.","year":"2015","unstructured":"D. Karatzas , L. Gomez-Bigorda , and A. Nicolaou . 2015 . ICDAR 2015 competition on Robust Reading. In 2015 13th International Conference on Document Analysis and Recognition (ICDAR). 1156--1160 . https:\/\/doi.org\/10.1109\/ICDAR. 2015 .7333942 10.1109\/ICDAR.2015.7333942 D. Karatzas, L. Gomez-Bigorda, and A. Nicolaou. 2015. ICDAR 2015 competition on Robust Reading. In 2015 13th International Conference on Document Analysis and Recognition (ICDAR). 1156--1160. https:\/\/doi.org\/10.1109\/ICDAR.2015.7333942"},{"key":"e_1_3_2_1_15_1","volume-title":"ICDAR 2013 Robust Reading Competition. In 2013 12th International Conference on Document Analysis and Recognition. 1484--1493","author":"Karatzas D.","year":"2013","unstructured":"D. Karatzas , F. Shafait , and S. Uchida . 2013 . ICDAR 2013 Robust Reading Competition. In 2013 12th International Conference on Document Analysis and Recognition. 1484--1493 . https:\/\/doi.org\/10.1109\/ICDAR. 2013 .221 10.1109\/ICDAR.2013.221 D. Karatzas, F. Shafait, and S. Uchida. 2013. ICDAR 2013 Robust Reading Competition. In 2013 12th International Conference on Document Analysis and Recognition. 1484--1493. https:\/\/doi.org\/10.1109\/ICDAR.2013.221"},{"key":"e_1_3_2_1_16_1","volume-title":"Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition. Proceedings of the AAAI Conference on Artificial Intelligence","volume":"33","author":"Li Hui","year":"2019","unstructured":"Hui Li , Peng Wang , and Chunhua Shen . 2019 . Show , Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition. Proceedings of the AAAI Conference on Artificial Intelligence , Vol. 33 , 01 (Jul. 2019), 8610--8617. https:\/\/doi.org\/10.1609\/aaai.v33i01.33018610 10.1609\/aaai.v33i01.33018610 Hui Li, Peng Wang, and Chunhua Shen. 2019. Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition. Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 33, 01 (Jul. 2019), 8610--8617. https:\/\/doi.org\/10.1609\/aaai.v33i01.33018610"},{"key":"e_1_3_2_1_17_1","volume-title":"SCATTER: Selective Context Attentional Scene Text Recognizer.","author":"Litman Ron","year":"2020","unstructured":"Ron Litman , Oron Anschel , and Shahar Tsiper . 2020 . SCATTER: Selective Context Attentional Scene Text Recognizer. (2020). Ron Litman, Oron Anschel, and Shahar Tsiper. 2020. SCATTER: Selective Context Attentional Scene Text Recognizer. (2020)."},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, (AAAI-18)","author":"Liu Wei","year":"2018","unstructured":"Wei Liu , Chaofeng Chen , and Kwan-Yee K. Wong . 2018. Char-Net: A Character-Aware Neural Network for Distorted Scene Text Recognition . In Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, (AAAI-18) , the 30th innovative Applications of Artificial Intelligence (IAAI-18), and the 8th AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI-18), New Orleans, Louisiana, USA, February 2--7 , 2018 , Sheila A. McIlraith and Kilian Q. Weinberger (Eds.). AAAI Press, 7154--7161. https:\/\/www.aaai.org\/ocs\/index.php\/AAAI\/AAAI18\/paper\/view\/16327 Wei Liu, Chaofeng Chen, and Kwan-Yee K. Wong. 2018. Char-Net: A Character-Aware Neural Network for Distorted Scene Text Recognition. In Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, (AAAI-18), the 30th innovative Applications of Artificial Intelligence (IAAI-18), and the 8th AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI-18), New Orleans, Louisiana, USA, February 2--7, 2018, Sheila A. McIlraith and Kilian Q. Weinberger (Eds.). AAAI Press, 7154--7161. https:\/\/www.aaai.org\/ocs\/index.php\/AAAI\/AAAI18\/paper\/view\/16327"},{"key":"e_1_3_2_1_19_1","volume-title":"MASTER: Multi-Aspect Non-local Network for Scene Text Recognition.","author":"Lu Ning","year":"2019","unstructured":"Ning Lu , Wenwen Yu , and Xianbiao Qi . 2019 . MASTER: Multi-Aspect Non-local Network for Scene Text Recognition. (2019). Ning Lu, Wenwen Yu, and Xianbiao Qi. 2019. MASTER: Multi-Aspect Non-local Network for Scene Text Recognition. (2019)."},{"key":"e_1_3_2_1_20_1","volume-title":"ICDAR 2003 Robust Reading Competitions: Entries, Results and Future Directions. IJDAR","volume":"7","author":"Lucas Simon","year":"2005","unstructured":"Simon Lucas , Alexandros Panaretos , and Luis Sosa . 2005 . ICDAR 2003 Robust Reading Competitions: Entries, Results and Future Directions. IJDAR , Vol. 7 (07 2005), 105--122. https:\/\/doi.org\/10.1007\/s10032-004-0134--3 10.1007\/s10032-004-0134--3 Simon Lucas, Alexandros Panaretos, and Luis Sosa. 2005. ICDAR 2003 Robust Reading Competitions: Entries, Results and Future Directions. IJDAR, Vol. 7 (07 2005), 105--122. https:\/\/doi.org\/10.1007\/s10032-004-0134--3"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.01.020"},{"volume-title":"BMVC - British Machine Vision Conference. BMVA","author":"Mishra Anand","key":"e_1_3_2_1_22_1","unstructured":"Anand Mishra , Karteek Alahari , and C.V. Jawahar . 2012. Scene Text Recognition using Higher Order Language Priors . In BMVC - British Machine Vision Conference. BMVA , Surrey, United Kingdom. https:\/\/doi.org\/10.5244\/C.26.127 10.5244\/C.26.127 Anand Mishra, Karteek Alahari, and C.V. Jawahar. 2012. Scene Text Recognition using Higher Order Language Priors. In BMVC - British Machine Vision Conference. BMVA, Surrey, United Kingdom. https:\/\/doi.org\/10.5244\/C.26.127"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2016.01.002"},{"volume-title":"PyTorch: An Imperative Style","author":"Paszke Adam","key":"e_1_3_2_1_24_1","unstructured":"Adam Paszke , Sam Gross , and Francisco Massa . 2019. PyTorch: An Imperative Style , High-Performance Deep Learning Library . In Advances in Neural Information Processing Systems, H. Wallach, H. Larochelle, A. Beygelzimer, F. dtextquotesingle Alch\u00e9-Buc, E. Fox, and R. Garnett (Eds.), Vol. 32. Curran Associates, Inc., 8026--8037. https:\/\/proceedings.neurips.cc\/paper\/2019\/file\/bdbca288fee7f92f2bfa9f7012727740-Paper.pdf Adam Paszke, Sam Gross, and Francisco Massa. 2019. PyTorch: An Imperative Style, High-Performance Deep Learning Library. In Advances in Neural Information Processing Systems, H. Wallach, H. Larochelle, A. Beygelzimer, F. dtextquotesingle Alch\u00e9-Buc, E. Fox, and R. Garnett (Eds.), Vol. 32. Curran Associates, Inc., 8026--8037. https:\/\/proceedings.neurips.cc\/paper\/2019\/file\/bdbca288fee7f92f2bfa9f7012727740-Paper.pdf"},{"key":"e_1_3_2_1_25_1","volume-title":"Recognizing Text with Perspective Distortion in Natural Scenes. In 2013 IEEE International Conference on Computer Vision. 569--576","author":"Phan T. Q.","year":"2013","unstructured":"T. Q. Phan , P. Shivakumara , S. Tian , and C. L. Tan . 2013 . Recognizing Text with Perspective Distortion in Natural Scenes. In 2013 IEEE International Conference on Computer Vision. 569--576 . https:\/\/doi.org\/10.1109\/ICCV. 2013 .76 10.1109\/ICCV.2013.76 T. Q. Phan, P. Shivakumara, S. Tian, and C. L. Tan. 2013. Recognizing Text with Perspective Distortion in Natural Scenes. In 2013 IEEE International Conference on Computer Vision. 569--576. https:\/\/doi.org\/10.1109\/ICCV.2013.76"},{"key":"e_1_3_2_1_26_1","volume-title":"Gaussian Constrained Attention Network for Scene Text Recognition. ArXiv","author":"Qiao Zhi","year":"2020","unstructured":"Zhi Qiao , Xugong Qin , and Yin qing Zhou . 2020. Gaussian Constrained Attention Network for Scene Text Recognition. ArXiv , Vol. abs\/ 2010 .09169 ( 2020 ). Zhi Qiao, Xugong Qin, and Yin qing Zhou. 2020. Gaussian Constrained Attention Network for Scene Text Recognition. ArXiv, Vol. abs\/2010.09169 (2020)."},{"key":"e_1_3_2_1_27_1","volume-title":"SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition. arXiv e-prints, Article arXiv:2005.10977 (May","author":"Qiao Zhi","year":"2020","unstructured":"Zhi Qiao , Yu Zhou , and Dongbao Yang . 2020 . SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition. arXiv e-prints, Article arXiv:2005.10977 (May 2020), arXiv:2005.10977 pages.arxiv: 2005.10977 [cs.CV] Zhi Qiao, Yu Zhou, and Dongbao Yang. 2020. SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition. arXiv e-prints, Article arXiv:2005.10977 (May 2020), arXiv:2005.10977 pages.arxiv: 2005.10977 [cs.CV]"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2014.07.008"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2646371"},{"key":"e_1_3_2_1_30_1","volume-title":"Robust Scene Text Recognition with Automatic Rectification. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 4168--4176","author":"Shi B.","year":"2016","unstructured":"B. Shi , X. Wang , and P. Lyu . 2016 . Robust Scene Text Recognition with Automatic Rectification. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 4168--4176 . https:\/\/doi.org\/10.1109\/CVPR. 2016 .452 10.1109\/CVPR.2016.452 B. Shi, X. Wang, and P. Lyu. 2016. Robust Scene Text Recognition with Automatic Rectification. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 4168--4176. https:\/\/doi.org\/10.1109\/CVPR.2016.452"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2848939"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.5555\/1886063.1886108"},{"key":"e_1_3_2_1_34_1","volume-title":"Proceedings of the 32nd International Conference on International Conference on Machine Learning -","volume":"37","author":"Xu Kelvin","year":"2015","unstructured":"Kelvin Xu , Jimmy Lei Ba , and Ryan Kiros . 2015 . Show, Attend and Tell: Neural Image Caption Generation with Visual Attention . In Proceedings of the 32nd International Conference on International Conference on Machine Learning - Volume 37 (Lille, France) (ICML'15). JMLR.org , 2048--2057. Kelvin Xu, Jimmy Lei Ba, and Ryan Kiros. 2015. Show, Attend and Tell: Neural Image Caption Generation with Visual Attention. In Proceedings of the 32nd International Conference on International Conference on Machine Learning - Volume 37 (Lille, France) (ICML'15). JMLR.org, 2048--2057."},{"key":"e_1_3_2_1_35_1","volume-title":"Article arXiv:1908.01957 (Aug.","author":"Yang MingKun","year":"2019","unstructured":"MingKun Yang , Yushuo Guan , and Minghui Liao . 2019. Symmetry-constrained Rectification Network for Scene Text Recognition. arXiv e-prints , Article arXiv:1908.01957 (Aug. 2019 ), arXiv:1908.01957 pages.arxiv: 1908.01957 [cs.CV] MingKun Yang, Yushuo Guan, and Minghui Liao. 2019. Symmetry-constrained Rectification Network for Scene Text Recognition. arXiv e-prints, Article arXiv:1908.01957 (Aug. 2019), arXiv:1908.01957 pages.arxiv: 1908.01957 [cs.CV]"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/458"},{"key":"e_1_3_2_1_37_1","volume-title":"Strokelets: A Learned Multi-scale Representation for Scene Text Recognition. In 2014 IEEE Conference on Computer Vision and Pattern Recognition. 4042--4049","author":"Yao C.","year":"2014","unstructured":"C. Yao , X. Bai , and B. Shi . 2014 . Strokelets: A Learned Multi-scale Representation for Scene Text Recognition. In 2014 IEEE Conference on Computer Vision and Pattern Recognition. 4042--4049 . https:\/\/doi.org\/10.1109\/CVPR. 2014 .515 10.1109\/CVPR.2014.515 C. Yao, X. Bai, and B. Shi. 2014. Strokelets: A Learned Multi-scale Representation for Scene Text Recognition. In 2014 IEEE Conference on Computer Vision and Pattern Recognition. 4042--4049. https:\/\/doi.org\/10.1109\/CVPR.2014.515"},{"key":"e_1_3_2_1_38_1","volume-title":"ADADELTA: An adaptive learning rate method.","author":"Zeiler Matthew","year":"2012","unstructured":"Matthew Zeiler . 2012 . ADADELTA: An adaptive learning rate method. , Vol. 1212 (12 2012). Matthew Zeiler. 2012. ADADELTA: An adaptive learning rate method., Vol. 1212 (12 2012)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00216"}],"event":{"name":"ICMR '21: International Conference on Multimedia Retrieval","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Taipei Taiwan","acronym":"ICMR '21"},"container-title":["Proceedings of the 2021 International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3460426.3463623","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3460426.3463623","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:17:03Z","timestamp":1750191423000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3460426.3463623"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,24]]},"references-count":39,"alternative-id":["10.1145\/3460426.3463623","10.1145\/3460426"],"URL":"https:\/\/doi.org\/10.1145\/3460426.3463623","relation":{},"subject":[],"published":{"date-parts":[[2021,8,24]]},"assertion":[{"value":"2021-09-01","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}