{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:02:28Z","timestamp":1750309348576,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":31,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,7,12]],"date-time":"2024-07-12T00:00:00Z","timestamp":1720742400000},"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":[[2024,7,12]]},"DOI":"10.1145\/3686490.3686517","type":"proceedings-article","created":{"date-parts":[[2024,10,11]],"date-time":"2024-10-11T16:29:37Z","timestamp":1728664177000},"page":"183-189","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Arbitrary-shape Scene Text Detection via Spatial Relationship Module and Subspace Attention Module"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5039-5723","authenticated-orcid":false,"given":"Manli","family":"Wang","sequence":"first","affiliation":[{"name":"Institute of Physics and Electronic Information, Henan Polytechnic University, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5035-1863","authenticated-orcid":false,"given":"Zeya","family":"Dou","sequence":"additional","affiliation":[{"name":"Institute of Physics and Electronic Information, Henan Polytechnic University, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6010-670X","authenticated-orcid":false,"given":"Chen","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute of Physics and Electronic Information, Henan Polytechnic University, China"}]}],"member":"320","published-online":{"date-parts":[[2024,10,11]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"48","article-title":"A Survey of Scene Text Detection Methods Based on Deep Learning [J]","volume":"2024","author":"Jing SUN","unstructured":"ZHANG Jing, SUN Qiaoyu, LIU Zhenbing. A Survey of Scene Text Detection Methods Based on Deep Learning [J]. Intelligent Computer and Applications,2024,14(02):48-54.","journal-title":"Intelligent Computer and Applications"},{"key":"e_1_3_2_1_2_1","volume-title":"Natural scene text detection based on deep learning review [J]. Computer engineering","author":"Zhe YIN","year":"2024","unstructured":"LIAN Zhe, YIN Yanjun, YUN Fei, Natural scene text detection based on deep learning review [J]. Computer engineering, 2024, 50 (3): 16-27. DOI: 10.19678 \/ j.i SSN. 1000-3428.0067427."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2642789"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2916104"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2011.2154317"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"He P Huang W He T Single shot text detector with regional attention[C]\/\/Proceedings of the IEEE international conference on computer vision. 2017: 3047-3055.","DOI":"10.1109\/ICCV.2017.331"},{"key":"e_1_3_2_1_7_1","volume-title":"A single-shot oriented scene text detector[J]","author":"Liao M","year":"2018","unstructured":"Liao M, Shi B, Bai X. Textboxes++: A single-shot oriented scene text detector[J]. IEEE transactions on image processing, 2018, 27(8): 3676-3690."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Lyu P Liao M Yao C Mask textspotter: An end-to-end trainable neural network for spotting text with arbitrary shapes[C]\/\/Proceedings of the European conference on computer vision (ECCV). 2018: 67-83.","DOI":"10.1007\/978-3-030-01264-9_5"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2443556"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Lin T Y Doll\u00e1r P Girshick R Feature pyramid networks for object detection[C]\/\/Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 2117-2125.","DOI":"10.1109\/CVPR.2017.106"},{"key":"e_1_3_2_1_11_1","first-page":"21","volume-title":"Proceedings, Part I 14","author":"Liu W","year":"2016","unstructured":"Liu W, Anguelov D, Erhan D, Ssd: Single shot multibox detector[C]\/\/Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part I 14. Springer International Publishing, 2016: 21-37."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Lyu P Yao C Wu W Multi-oriented scene text detection via corner localization and region segmentation[C]\/\/Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 7553-7563.","DOI":"10.1109\/CVPR.2018.00788"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Liao M Zhu Z Shi B Rotation-sensitive regression for oriented scene text detection[C]\/\/Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 5909-5918.","DOI":"10.1109\/CVPR.2018.00619"},{"key":"e_1_3_2_1_14_1","volume-title":"Deng Y","author":"Huang L","year":"2015","unstructured":"Huang L, Yang Y, Deng Y, Densebox: Unifying landmark localization with end to end object detection[J]. arXiv preprint arXiv:1509.04874, 2015."},{"key":"e_1_3_2_1_15_1","volume-title":"Ba J. Adam: A method for stochastic optimization[J]. arXiv preprint arXiv:1412.6980","author":"Kingma D P","year":"2014","unstructured":"Kingma D P, Ba J. Adam: A method for stochastic optimization[J]. arXiv preprint arXiv:1412.6980, 2014."},{"key":"e_1_3_2_1_16_1","volume-title":"Chen L C","author":"Chen K","year":"2015","unstructured":"Chen K, Wang J, Chen L C, Abc-cnn: An attention based convolutional neural network for visual question answering[J]. arXiv preprint arXiv:1511.05960, 2015."},{"key":"e_1_3_2_1_17_1","volume-title":"attend and answer: Exploring question-guided spatial attention for visual question answering[C]\/\/Computer Vision\u2013ECCV 2016: 14th European Conference","author":"Xu H","year":"2016","unstructured":"Xu H, Saenko K. Ask, attend and answer: Exploring question-guided spatial attention for visual question answering[C]\/\/Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, the Netherlands, October 11\u201314, 2016, Proceedings, Part VII 14. Springer International Publishing, 2016: 451-466."},{"key":"e_1_3_2_1_18_1","volume-title":"Control of goal-directed and stimulus-driven attention in the brain[J]. Nature reviews neuroscience","author":"Corbetta M","year":"2002","unstructured":"Corbetta M, Shulman G L. Control of goal-directed and stimulus-driven attention in the brain[J]. Nature reviews neuroscience, 2002, 3(3): 201-215."},{"issue":"03","key":"e_1_3_2_1_19_1","first-page":"356","volume":"41","author":"Wenjie","year":"2012","unstructured":"HU Wenjie, Wu Xiaobo, Li Bo, Industrial Defect Sample Image Generation Based on Single-sample ConSinGAN Model with Self-Attention [J]. Journal of South-Central University for Nationalities (Natural Science Edition), 2012,41(03):356-364.","journal-title":"Journal of South-Central University for Nationalities (Natural Science Edition)"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2678539"},{"issue":"3","key":"e_1_3_2_1_21_1","first-page":"668","volume":"2019","author":"Yasheng","unstructured":"SUN Yasheng, Jiang Qi, Hu Jie, Pedestrian Trajectory Prediction Generation Model Based on Attention Mechanism [J]. Application of Computers, 2019 (3): 668-674.","journal-title":"Application of Computers"},{"key":"e_1_3_2_1_22_1","volume-title":"Xiao J","author":"Chen L","year":"2017","unstructured":"Chen L, Zhang H, Xiao J, Sca-cnn: Spatial and channel-wise attention in convolutional networks for image captioning[C]\/\/Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 5659-5667."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"He K Zhang X Ren S Deep residual learning for image recognition[C]\/\/Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 770-778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Wang F Jiang M Qian C Residual attention network for image classification[C]\/\/Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 3156-3164.","DOI":"10.1109\/CVPR.2017.683"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Fu J Liu J Tian H Dual attention network for scene segmentation[C]\/\/Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2019: 3146-3154.","DOI":"10.1109\/CVPR.2019.00326"},{"key":"e_1_3_2_1_27_1","volume-title":"Learning markov clustering networks for scene text detection[J]. arXiv preprint arXiv:1805.08365","author":"Liu Z","year":"2018","unstructured":"Liu Z, Lin G, Yang S, Learning markov clustering networks for scene text detection[J]. arXiv preprint arXiv:1805.08365, 2018."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Zhang C Liang B Huang Z Look more than once: An accurate detector for text of arbitrary shapes[C]\/\/Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2019: 10552-10561.","DOI":"10.1109\/CVPR.2019.01080"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","unstructured":"Liu Z Lin G Yang S Towards robust curve text detection with conditional spatial expansion[C]\/\/proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2019: 7269-7278.","DOI":"10.1109\/CVPR.2019.00744"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Long S Ruan J Zhang W Textsnake: A flexible representation for detecting text of arbitrary shapes[C]\/\/Proceedings of the European conference on computer vision (ECCV). 2018: 20-36.","DOI":"10.1007\/978-3-030-01216-8_2"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"Wang W Xie E Li X Shape robust text detection with progressive scale expansion network[C]\/\/Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2019: 9336-9345.","DOI":"10.1109\/CVPR.2019.00956"}],"event":{"name":"SPML 2024: 2024 7th International Conference on Signal Processing and Machine Learning","acronym":"SPML 2024","location":"Qingdao China"},"container-title":["Proceedings of the 2024 7th International Conference on Signal Processing and Machine Learning"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3686490.3686517","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3686490.3686517","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:05:39Z","timestamp":1750291539000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3686490.3686517"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,12]]},"references-count":31,"alternative-id":["10.1145\/3686490.3686517","10.1145\/3686490"],"URL":"https:\/\/doi.org\/10.1145\/3686490.3686517","relation":{},"subject":[],"published":{"date-parts":[[2024,7,12]]},"assertion":[{"value":"2024-10-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}