{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:13:29Z","timestamp":1750220009819,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,11,25]],"date-time":"2022-11-25T00:00:00Z","timestamp":1669334400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,11,25]]},"DOI":"10.1145\/3577164.3577165","type":"proceedings-article","created":{"date-parts":[[2023,4,4]],"date-time":"2023-04-04T22:10:10Z","timestamp":1680646210000},"page":"1-6","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Text Detection and Recognition in Natural Scenes Based on TWO-DIMENSIONAL Attention"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2755-2687","authenticated-orcid":false,"given":"Baicun","family":"Guo","sequence":"first","affiliation":[{"name":"Computer Science, North China Electric Power University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,4,4]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/0031-3203(95)00030-4"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1142\/S0218001495000043"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540041"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.371"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.01.023"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_4"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10593-2_33"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11196"},{"key":"e_1_3_2_1_9_1","volume-title":"Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition.. arXiv:1811.00751v2","author":"Li H","year":"2019","unstructured":"Li H, Wang P, Shen C H, Zhang G Y.Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition.. arXiv:1811.00751v2, 2019. 3"},{"key":"e_1_3_2_1_10_1","volume-title":"The Research Progress and Prospects of Artificial Neural Networks[J]","author":"Zhu D Q","year":"2004","unstructured":"Zhu D Q . The Research Progress and Prospects of Artificial Neural Networks[J]. Journal of Southern Yangtze University(Natural Science Edition), 2004, 3(1): 103-110"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Tian S Pan Y Huang C et al.Text flow: A unified tet detection system in natural scene images[C]\/\/Proceedings of the IEEE International Conference on Computer Vision.2015:4651-4659","DOI":"10.1109\/ICCV.2015.528"},{"key":"e_1_3_2_1_12_1","first-page":"761","article-title":"wide-baseline stereo from maximally stable extremal regions[J].","volume":"2004","author":"Matas J.","unstructured":"Matas J. Chum O.,Urban M., Pajdla T..Robust wide-baseline stereo from maximally stable extremal regions[J].Image and Vision Computing,2004,22(10):761-767.","journal-title":"Image and Vision Computing"},{"key":"e_1_3_2_1_13_1","first-page":"681","article-title":"text detection via stroke width[C]\/\/Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012).","volume":"2012","author":"Li Y","unstructured":"Li Y,Lu H.Scene text detection via stroke width[C]\/\/Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012).IEEE,2012:681-684","journal-title":"IEEE"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.27063\/d.cnki.ghlgu.2021.000407"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2825107]"},{"key":"e_1_3_2_1_16_1","volume-title":"Rotation-sensitive regression for oriented scene text detection. arXiv:1803.05265","author":"Liao M","year":"2018","unstructured":"Liao M, Zhu Z, Shi B, Xia G, Bai X. Rotation-sensitive regression for oriented scene text detection. arXiv:1803.05265, 2018."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Liu Y Jin L.Deep matching prior network: Toward tighter multi-oriented text detection[C]\/\/Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017:1962-1969","DOI":"10.1109\/CVPR.2017.368"},{"key":"e_1_3_2_1_18_1","volume-title":"TextMountain: Accurate scene text detection via instance segmentation. arXiv:1811.12786","author":"Zhu Y","year":"2018","unstructured":"Zhu Y, Du J. TextMountain: Accurate scene text detection via instance segmentation. arXiv:1811.12786, 2018."},{"key":"e_1_3_2_1_19_1","volume-title":"Shape robust text detection with progressive scale expansion network. arXiv","author":"Li X","year":"1903","unstructured":"Li X, Wang W, Hou W, Liu R, Lu T, Yang J. Shape robust text detection with progressive scale expansion network. arXiv: 1903.12473v2, 2018."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-019-00335-y]"},{"key":"e_1_3_2_1_21_1","volume-title":"Zhou X. Pixel-anchor: A fast oriented scene text detector with combined networks. arXiv:1811.07432v1","author":"Li Y","year":"2018","unstructured":"Li Y, Yu Y, Li Z, Lin Y, Xu M, Li J, Zhou X. Pixel-anchor: A fast oriented scene text detector with combined networks. arXiv:1811.07432v1, 2018."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.11834\/jig.210044"},{"key":"e_1_3_2_1_23_1","first-page":"1465","article-title":"Review of natural scene text detection and recognition based on deep learning","volume":"2020","author":"Wang J X","unstructured":"Wang J X,Wang Z Y,Tian X. Review of natural scene text detection and recognition based on deep learning. Ruan Jian Xue Bao\/Journal of Software,2020,31(5):1465-1496(in Chinese).","journal-title":"Ruan Jian Xue Bao\/Journal of Software"},{"key":"e_1_3_2_1_24_1","first-page":"52","article-title":"Application of Scene Text Recognition Technology Based on Deep Learning","volume":"20222","author":"Liu Y J","unstructured":"Liu Y J,Yi X H,Li Y G,Zhang H Y,Liu Y Z. Application of Scene Text Recognition Technology Based on Deep Learning: A Survey. Computer Engineering and Applications,20222,58(4):52-58","journal-title":"A Survey. Computer Engineering and Applications"},{"key":"e_1_3_2_1_25_1","first-page":"2298","article-title":"end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition[J].","volume":"2016","author":"Shi B","unstructured":"Shi B,Bai X,Yao C.An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2016,39(11):2298-2304.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_3_2_1_27_1","volume-title":"ImageNet Classification with Deep Convolutional Neural Networks[J]. Advances in neural information processing systems","author":"Krizhevsky A","year":"2012","unstructured":"Krizhevsky A , Sutskever I , Hinton G . ImageNet Classification with Deep Convolutional Neural Networks[J]. Advances in neural information processing systems, 2012, 25(2)."},{"key":"e_1_3_2_1_28_1","volume-title":"Monocular Depth Estimation with Self-supervised Instance Adaptation. \u00a0arXiv:2004.05821v1","author":"Mccraith R","year":"2020","unstructured":"Mccraith R, Neumann L, Zisserman A, Vedaldi A. Monocular Depth Estimation with Self-supervised Instance Adaptation. \u00a0arXiv:2004.05821v1, 2020.4"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","unstructured":"Szegedy C Liu W Jia Y Q Sermanet P Rabinovich A. Going Deeper with Convolutions arXiv:1409.4842v1 2014.9","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_31_1","unstructured":"Tang C.Review and prospect of convolutional neural networks[J]. China New Telecommunications 2022 22(23)"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2646371"},{"key":"e_1_3_2_1_33_1","first-page":"1","article-title":"Research on recurrent neural network.","volume":"2018","author":"Yang L","unstructured":"Yang L, Wu Y X,Wang J L,Liu Y L. Research on recurrent neural network.Journal of Computer Applications.2018,38(S2),1-6+26","journal-title":"Journal of Computer Applications"},{"volume-title":"Proc. Int. Conf. Learn. Representations.","author":"Kingma D.","key":"e_1_3_2_1_34_1","unstructured":"Kingma, D., and Ba, J. 2014. Adam: A method for stochastic optimization. In Proc. Int. Conf. Learn. Representations."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","unstructured":"liuch37\/sar-pytorch: Implementation of Show Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition published in AAAI 2019 in PyTorch (github.com)","DOI":"10.1609\/aaai.v33i01.33018610"}],"event":{"name":"VSIP 2022: 2022 4th International Conference on Video, Signal and Image Processing","acronym":"VSIP 2022","location":"Shanghai China"},"container-title":["Proceedings of the 2022 4th International Conference on Video, Signal and Image Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3577164.3577165","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3577164.3577165","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:51:10Z","timestamp":1750182670000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3577164.3577165"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,25]]},"references-count":35,"alternative-id":["10.1145\/3577164.3577165","10.1145\/3577164"],"URL":"https:\/\/doi.org\/10.1145\/3577164.3577165","relation":{},"subject":[],"published":{"date-parts":[[2022,11,25]]},"assertion":[{"value":"2023-04-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}