{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:04:16Z","timestamp":1750309456042,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":24,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Applied Basic Research Project of Liaoning Province award","award":["2023JH2\/101300185"],"award-info":[{"award-number":["2023JH2\/101300185"]}]},{"name":"Key Technologies Research and Development Program of Liaoning Province in China award","award":["2021JH1\/10400079"],"award-info":[{"award-number":["2021JH1\/10400079"]}]},{"name":"Natural Science Foundation of Liaoning Provincial Department of Science and Technology award","award":["2022-KF-11-04"],"award-info":[{"award-number":["2022-KF-11-04"]}]},{"name":"Fundamental Research Funds for the Central Universities award","award":["2024GFZD03"],"award-info":[{"award-number":["2024GFZD03"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,12,3]]},"DOI":"10.1145\/3696409.3700222","type":"proceedings-article","created":{"date-parts":[[2024,12,28]],"date-time":"2024-12-28T09:55:23Z","timestamp":1735379723000},"page":"1-7","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A Multi-angle Text Recognition Algorithm"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-8276-0912","authenticated-orcid":false,"given":"Jie","family":"Wang","sequence":"first","affiliation":[{"name":"Software College of Northeastern University, ShenYang, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6730-7471","authenticated-orcid":false,"given":"Huilin","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Engineering, Computing and Cybernetics, Australian National University, Canberra, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7139-4916","authenticated-orcid":false,"given":"Wandong","family":"Xue","sequence":"additional","affiliation":[{"name":"Northeastern University, ShenYang, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7863-1230","authenticated-orcid":false,"given":"Dongming","family":"Chen","sequence":"additional","affiliation":[{"name":"Software College of Northeastern University, ShenYang, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2572-7658","authenticated-orcid":false,"given":"Dongqi","family":"Wang","sequence":"additional","affiliation":[{"name":"Northeastern University, ShenYang, China"}]}],"member":"320","published-online":{"date-parts":[[2024,12,28]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"crossref","unstructured":"Yang Xiaomeng Zhi Qiao Jin Wei Yu ZHOU Ye Yuan Zhilong Ji Dongbao Yang and Weiping Wang. Masked and Permuted Implicit Context Learning for Scene Text Recognition. IEEE Signal Processing Letters 31. 2023: 964-968.","DOI":"10.1109\/LSP.2024.3381893"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"crossref","unstructured":"Fujitake Masato. DTrOCR: Decoder-only Transformer for Optical Character Recognition. IEEE\/CVF Winter Conference on Applications of Computer Vision. 2023: 8010-8020.","DOI":"10.1109\/WACV57701.2024.00784"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"crossref","unstructured":"Graves A Fern\u00e1ndez S Gomez F et al. Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. Proceedings of the 23rd international conference on Machine learning. 2006: 369-376.","DOI":"10.1145\/1143844.1143891"},{"key":"e_1_3_3_1_5_2","unstructured":"Vaswani A Shazeer N Parmar N et al. Attention is all you need. Advances in neural information processing systems 2017 30."},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"crossref","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. IEEE transactions on pattern analysis and machine intelligence 2016 39(11): 2298-2304.","DOI":"10.1109\/TPAMI.2016.2646371"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"crossref","unstructured":"Shi B Wang X Lyu P et al. Robust scene text recognition with automatic rectification. Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 4168-4176.","DOI":"10.1109\/CVPR.2016.452"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"crossref","unstructured":"Yu D Li X Zhang C et al. Towards accurate scene text recognition with semantic reasoning networks. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2020: 12113-12122.","DOI":"10.1109\/CVPR42600.2020.01213"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"crossref","unstructured":"Sheng F Chen Z Xu B. NRTR: A no-recurrence sequence-to-sequence model for scene text recognition. 2019 International conference on document analysis and recognition. IEEE 2019: 781-786.","DOI":"10.1109\/ICDAR.2019.00130"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"crossref","unstructured":"Wang X F He Z H Wang K et al. A survey of text detection and recognition algorithms based on deep learning technology. Neurocomputing 2023 556: 126702.","DOI":"10.1016\/j.neucom.2023.126702"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"crossref","unstructured":"Jiang Q. Wang J. Peng D. Liu C. & Jin L. Revisiting scene text recognition: A data perspective. In Proceedings of the IEEE\/CVF international conference on computer vision. 2023 pp. 20543-20554.","DOI":"10.1109\/ICCV51070.2023.01878"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"crossref","unstructured":"Ranjbarzadeh R. Jafarzadeh Ghoushchi S. Anari S. Safavi S. Tataei Sarshar N. Babaee Tirkolaee E. & Bendechache M. A deep learning approach for robust multi-oriented and curved text detection. Cognitive computation. 2024 16(4) 1979-1991.","DOI":"10.1007\/s12559-022-10072-w"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"crossref","unstructured":"Hu J Shen L Sun G. Squeeze-and-excitation networks. Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 7132-7141.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"crossref","unstructured":"Mukhopadhyay P Chaudhuri B B. A survey of Hough Transform. Pattern Recognition 2015 48(3): 993-1010.","DOI":"10.1016\/j.patcog.2014.08.027"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"crossref","unstructured":"He K. Zhang X. Ren S. & Sun J. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition. 2016 pp. 770-778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"crossref","unstructured":"Du Y Chen Z Jia C et al. Svtr: Scene text recognition with a single visual model. Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence. 2022: 884-890.","DOI":"10.24963\/ijcai.2022\/124"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"crossref","unstructured":"Liu R Jiang D Zhang L et al. Deep depthwise separable convolutional network for change detection in optical aerial images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2020 13: 1109-1118.","DOI":"10.1109\/JSTARS.2020.2974276"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"crossref","unstructured":"Mao X Qi G Chen Y et al. Towards robust vision transformer. Proceedings of the IEEE\/CVF conference on Computer Vision and Pattern Recognition. 2022: 12042-12051.","DOI":"10.1109\/CVPR52688.2022.01173"},{"key":"e_1_3_3_1_19_2","unstructured":"Fang Shancheng Hongtao Xie Yuxin Wang Zhendong Mao and Yongdong Zhang. ABINet: A Bidirectional Attention Network for Scene Text Recognition. Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2021 pp. 7098\u20137107."},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"crossref","unstructured":"Shi Baoguang Mingkun Yang Xinggang Wang Pengyuan Lyu Cong Yao and Xiang Bai. ASTER: An Attentional Scene Text Recognizer with Flexible Rectification. IEEE Transactions on Pattern Analysis and Machine Intelligence vol. 41 no. 9 2019 pp. 2035\u20132048.","DOI":"10.1109\/TPAMI.2018.2848939"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"crossref","unstructured":"Li Hui Peng Wang Chunhua Shen and Guyu Zhang. Show Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition. Proceedings of the 33rd AAAI Conference on Artificial Intelligence 2019 pp. 8610\u20138617.","DOI":"10.1609\/aaai.v33i01.33018610"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"crossref","unstructured":"Cheng Z. Xu Y. Bai F. Niu Y. Pu S. & Zhou S. AON: Towards Arbitrarily-Oriented Text Recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018 pp. 5571-5579.","DOI":"10.1109\/CVPR.2018.00584"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"crossref","unstructured":"Zhang M. Ma M. & Wang P. Hierarchical Refined Attention for Scene Text Recognition. In ICASSP 2021 - 2021 IEEE International Conference on Acoustics Speech and Signal Processing. 2021 pp. 4175-4179.","DOI":"10.1109\/ICASSP39728.2021.9413534"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"crossref","unstructured":"Ron Litman Oron Anschel Shahar Tsiper Roee Litman Shai Mazor R. Manmatha. SCATTER: Selective Context Attentional Scene Text Recognizer. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2020 pp. 11962-11972.","DOI":"10.1109\/CVPR42600.2020.01198"},{"key":"e_1_3_3_1_25_2","unstructured":"Bai X Xu Y Wang W et al. VST: A Versatile Scene Text Detector with Vector-Structured Stack Hourglass Network. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2020 pp. 7156-7165."}],"event":{"name":"MMAsia '24: ACM Multimedia Asia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Auckland New Zealand","acronym":"MMAsia '24"},"container-title":["Proceedings of the 6th ACM International Conference on Multimedia in Asia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696409.3700222","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3696409.3700222","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:10:15Z","timestamp":1750295415000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696409.3700222"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"references-count":24,"alternative-id":["10.1145\/3696409.3700222","10.1145\/3696409"],"URL":"https:\/\/doi.org\/10.1145\/3696409.3700222","relation":{},"subject":[],"published":{"date-parts":[[2024,12,3]]},"assertion":[{"value":"2024-12-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}