{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,3]],"date-time":"2025-06-03T06:25:10Z","timestamp":1748931910802},"reference-count":52,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2022,5,9]],"date-time":"2022-05-09T00:00:00Z","timestamp":1652054400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,5,9]],"date-time":"2022-05-09T00:00:00Z","timestamp":1652054400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Major National Science and Technology Projects","award":["2017ZX07108-001"],"award-info":[{"award-number":["2017ZX07108-001"]}]},{"name":"The Wuhan Frontier Project on Applied Foundations","award":["2020020601012266"],"award-info":[{"award-number":["2020020601012266"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2023,7]]},"DOI":"10.1007\/s00371-022-02501-6","type":"journal-article","created":{"date-parts":[[2022,5,9]],"date-time":"2022-05-09T05:02:44Z","timestamp":1652072564000},"page":"2933-2952","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["A two-stage image process for water level recognition via dual-attention CornerNet and CTransformer"],"prefix":"10.1007","volume":"39","author":[{"given":"Run","family":"Qiu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaohui","family":"Cai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhuoqing","family":"Chang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shubo","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guoqing","family":"Tu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,5,9]]},"reference":[{"key":"2501_CR1","doi-asserted-by":"crossref","unstructured":"AshifuddinMondal, M., Rehena, Z.: Iot based intelligent agriculture field monitoring system. In: 2018 8th International Conference on Cloud Computing, Data Science & Engineering (Confluence), pp. 625\u2013629. IEEE (2018)","DOI":"10.1109\/CONFLUENCE.2018.8442535"},{"key":"2501_CR2","doi-asserted-by":"crossref","unstructured":"Gupta, S., Malhotra, V., Vashisht, V.: Water irrigation and flood prevention using IOT. In: 2020 10th International Conference on Cloud Computing, Data Science & Engineering (Confluence), pp. 260\u2013265. IEEE (2020)","DOI":"10.1109\/Confluence47617.2020.9057842"},{"issue":"11","key":"2501_CR3","doi-asserted-by":"publisher","first-page":"4621","DOI":"10.5194\/hess-23-4621-2019","volume":"23","author":"M Moy de Vitry","year":"2019","unstructured":"Moy de Vitry, M., Kramer, S., Wegner, J.D., Leit\u00e3o, J.P.: Scalable flood level trend monitoring with surveillance cameras using a deep convolutional neural network. Hydrol. Earth Syst. Sci. 23(11), 4621\u20134634 (2019)","journal-title":"Hydrol. Earth Syst. Sci."},{"key":"2501_CR4","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1016\/j.patcog.2018.01.020","volume":"79","author":"Z Tu","year":"2018","unstructured":"Tu, Z., Xie, W., Qin, Q., Poppe, R., Veltkamp, R.C., Li, B., Yuan, J.: Multi-stream CNN: learning representations based on human-related regions for action recognition. Pattern Recognit. 79, 32\u201343 (2018)","journal-title":"Pattern Recognit."},{"issue":"22","key":"2501_CR5","doi-asserted-by":"publisher","first-page":"4365","DOI":"10.1002\/hyp.13864","volume":"34","author":"S Etter","year":"2020","unstructured":"Etter, S., Strobl, B., van Meerveld, I., Seibert, J.: Quality and timing of crowd-based water level class observations. Hydrol. Process. 34(22), 4365\u20134378 (2020)","journal-title":"Hydrol. Process."},{"issue":"1","key":"2501_CR6","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1007\/s11760-020-01719-y","volume":"15","author":"G Chen","year":"2021","unstructured":"Chen, G., Bai, K., Lin, Z., Liao, X., Liu, S., Lin, Z., Zhang, Q., Jia, X.: Method on water level ruler reading recognition based on image processing. Signal Image Video Process. 15(1), 33\u201341 (2021)","journal-title":"Signal Image Video Process."},{"issue":"3","key":"2501_CR7","first-page":"28","volume":"37","author":"L Huayong","year":"2015","unstructured":"Huayong, L., Hua, Y.: Research on application of the scale extraction of water-level ruler based on image recognition technology. Yellow River 37(3), 28\u201330 (2015)","journal-title":"Yellow River"},{"key":"2501_CR8","doi-asserted-by":"crossref","unstructured":"Lyu, P., Yao, C., Wu, W., Yan, S., Bai, X.: Multi-oriented scene text detection via corner localization and region segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7553\u20137563 (2018)","DOI":"10.1109\/CVPR.2018.00788"},{"issue":"11","key":"2501_CR9","doi-asserted-by":"publisher","first-page":"2298","DOI":"10.1109\/TPAMI.2016.2646371","volume":"39","author":"B Shi","year":"2016","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 Trans. Pattern Anal. Mach. Intell. 39(11), 2298\u20132304 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2501_CR10","unstructured":"A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A.N. Gomez, \u0141. Kaiser, I. Polosukhin, Attention is all you need, in: Advances in neural information processing systems, 2017, pp. 5998\u20136008."},{"key":"2501_CR11","doi-asserted-by":"publisher","first-page":"2799","DOI":"10.1109\/TIP.2018.2890749","volume":"28","author":"Z Tu","year":"2019","unstructured":"Tu, Z., Li, H., Zhang, D., Dauwels, J., Li, B., Yuan, J.: Action-stage emphasized spatiotemporal VLAD for video action recognition. IEEE Trans. on Image Process. 28, 2799\u20132812 (2019)","journal-title":"IEEE Trans. on Image Process."},{"key":"2501_CR12","doi-asserted-by":"crossref","unstructured":"Chen, Y., Tu, Z., Ge, L., Zhang, D., Chen, R., Yuan, J.: So-handnet: self-organizing network for 3d hand pose estimation with semi-supervised learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6961\u20136970 (2019)","DOI":"10.1109\/ICCV.2019.00706"},{"key":"2501_CR13","doi-asserted-by":"publisher","DOI":"10.2112\/JCR-SI105-039.1","author":"F Lin","year":"2020","unstructured":"Lin, F., Yu, Z., Jin, Q., You, A.: Semantic segmentation and scale recognition\u2013based water-level monitoring algorithm. J. Coast. Res. (2020). https:\/\/doi.org\/10.2112\/JCR-SI105-039.1","journal-title":"J. Coast. Res."},{"key":"2501_CR14","doi-asserted-by":"crossref","unstructured":"Liao, M., Shi, M., Bai, X., Wang, X., Liu, W.: Textboxes: a fast text detector with a single deep neural network. In: Proceedings of the AAAI Conference on Artificial Intelligence (2017)","DOI":"10.1609\/aaai.v31i1.11196"},{"key":"2501_CR15","doi-asserted-by":"crossref","unstructured":"Zhou, X., Yao, C., Wen, H., Wang, Y., Zhou, S., He, W., Liang, J.: East: an efficient and accurate scene text detector. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5551\u20135560 (2017)","DOI":"10.1109\/CVPR.2017.283"},{"key":"2501_CR16","doi-asserted-by":"publisher","first-page":"1423","DOI":"10.1109\/TCSVT.2018.2830102","volume":"29","author":"Z Tu","year":"2018","unstructured":"Tu, Z., Xie, W., Dauwels, J., Li, B., Yuan, J.: Semantic cues enhanced multimodality multistream CNN for action recognition. IEEE Trans. Circuits Syst. Video Technol. 29, 1423\u20131437 (2018)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"2501_CR17","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"2501_CR18","doi-asserted-by":"crossref","unstructured":"Deng, D., Liu, H., Li, X., Cai, D.: Pixellink: detecting scene text via instance segmentation. In: Proceedings of the AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.12269"},{"key":"2501_CR19","doi-asserted-by":"crossref","unstructured":"Wang, W., Xie, E., Song, X., Zang, Y., Wang, W., Lu, T., Yu, G., Shen, C.: Efficient and accurate arbitrary-shaped text detection with pixel aggregation network. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8440\u20138449 (2019)","DOI":"10.1109\/ICCV.2019.00853"},{"key":"2501_CR20","doi-asserted-by":"crossref","unstructured":"He, P., Huang, W., He, T., Zhu, Q., Qiao, Y., Li, X.: Single shot text detector with regional attention. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3047\u20133055 (2017)","DOI":"10.1109\/ICCV.2017.331"},{"key":"2501_CR21","unstructured":"Wang, X., Chen, K., Huang, Z., Yao, C., Liu, W.: Point linking network for object detection (2017)"},{"key":"2501_CR22","unstructured":"Fu, C.-Y., Liu, W., Ranga, A., Tyagi, A., Berg, A.C.: Dssd: deconvolutional single shot detector (2017)"},{"key":"2501_CR23","doi-asserted-by":"crossref","unstructured":"Zhang, J., Zhu, Y., Du, J., Dai, L.: Radical analysis network for zero-shot learning in printed Chinese character recognition. In: 2018 IEEE International Conference on Multimedia and Expo (ICME), pp. 1\u20136. IEEE (2018)","DOI":"10.1109\/ICME.2018.8486456"},{"key":"2501_CR24","unstructured":"Jaderberg, M., Simonyan, K., Vedaldi, A., Zisserman, A.: Synthetic data and artificial neural networks for natural scene text recognition (2014)"},{"key":"2501_CR25","doi-asserted-by":"crossref","unstructured":"Lee, C.-Y., Osindero, S.: Recursive recurrent nets with attention modeling for ocr in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2231\u20132239 (2016)","DOI":"10.1109\/CVPR.2016.245"},{"key":"2501_CR26","first-page":"2035","volume":"414","author":"B Shi","year":"2018","unstructured":"Shi, B., Yang, M., Wang, X., Lyu, P., Yao, C., Bai, X.: Aster: an attentional scene text recognizer with flexible rectification. IEEE Trans. Pattern Anal. Mach. Intell. 414, 2035\u20132048 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2501_CR27","doi-asserted-by":"crossref","unstructured":"Qiao, Z., Zhou, Y., Yang, D., Zhou, Y., Wang, W.: Seed: semantics enhanced encoder-decoder framework for scene text recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13528\u201313537 (2020)","DOI":"10.1109\/CVPR42600.2020.01354"},{"key":"2501_CR28","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need (2017)"},{"key":"2501_CR29","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S.: An image is worth 16x16 words: transformers for image recognition at scale (2020)"},{"key":"2501_CR30","doi-asserted-by":"crossref","unstructured":"Milletari, F., Navab, N., Ahmadi, S.-A.: V-net: fully convolutional neural networks for volumetric medical image segmentation. In: 2016 fourth international conference on 3D vision (3DV), pp. 565\u2013571. IEEE (2016)","DOI":"10.1109\/3DV.2016.79"},{"key":"2501_CR31","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., Berg, A.C.: Ssd: single shot multibox detector. In: European Conference on Computer Vision, pp. 21\u201337. Springer (2016)","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"2501_CR32","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: towards real-time object detection with region proposal networks (2015)"},{"key":"2501_CR33","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, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"2501_CR34","unstructured":"Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding (2018)"},{"key":"2501_CR35","doi-asserted-by":"crossref","unstructured":"Graves, A., Fern\u00e1ndez, S., Gomez, F., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: Proceedings of the 23rd International Conference on Machine Learning, pp. 369\u2013376 (2006)","DOI":"10.1145\/1143844.1143891"},{"key":"2501_CR36","doi-asserted-by":"publisher","first-page":"13849","DOI":"10.1109\/JIOT.2021.3088875","volume":"8","author":"Z Chang","year":"2021","unstructured":"Chang, Z., Liu, S., Xiong, X., Cai, Z., Tu, G.: A survey of recent advances in edge-computing-powered artificial intelligence of things. IEEE Internet Things J. 8, 13849\u201313875 (2021)","journal-title":"IEEE Internet Things J."},{"key":"2501_CR37","doi-asserted-by":"crossref","unstructured":"Gupta, A., Vedaldi, A., Zisserman, A.: Synthetic data for text localisation in natural images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2315\u20132324 (2016)","DOI":"10.1109\/CVPR.2016.254"},{"key":"2501_CR38","doi-asserted-by":"crossref","unstructured":"Karatzas, D., Shafait, F., Uchida, S., Iwamura, M., i Bigorda, L.G., Mestre, S.R., Mas, J., Mota, D.F., Almazan, J.A., De Las Heras, L.P.: ICDAR 2013 robust reading competition. In: 2013 12th International Conference on Document Analysis and Recognition, pp. 1484\u20131493. IEEE (2013)","DOI":"10.1109\/ICDAR.2013.221"},{"key":"2501_CR39","doi-asserted-by":"crossref","unstructured":"Karatzas, D., Gomez-Bigorda, L., Nicolaou, A., Ghosh, S., Bagdanov, A., Iwamura, M., Matas, J., Neumann, L., Chandrasekhar, V.R., Lu, S.: ICDAR 2015 competition on robust reading. In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR), pp. 1156\u20131160. IEEE (2015)","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"2501_CR40","unstructured":"Yao, C., Bai, X., Liu, W., Ma, Y., Tu, Z.: Detecting texts of arbitrary orientations in natural images. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1083\u20131090. IEEE (2012)"},{"key":"2501_CR41","doi-asserted-by":"crossref","unstructured":"Yao, C., Bai, X., Liu, W.: A unified framework for multioriented text detection and recognition (2014)","DOI":"10.1109\/TIP.2014.2353813"},{"key":"2501_CR42","doi-asserted-by":"crossref","unstructured":"He, M., Liu, Y., Yang, Z., Zhang, S., Luo, C., Gao, F., Zheng, Q., Wang, Y., Zhang, X., Jin, L.: ICPR2018 contest on robust reading for multi-type web images. In: 2018 24th International Conference on Pattern Recognition (ICPR), pp. 7\u201312. IEEE (2018)","DOI":"10.1109\/ICPR.2018.8546143"},{"key":"2501_CR43","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization (2014)"},{"key":"2501_CR44","unstructured":"Yao, C., Bai, X., Sang, N., Zhou, X., Zhou, S., Cao, Z.: Scene text detection via holistic, multi-channel prediction (2016)"},{"key":"2501_CR45","doi-asserted-by":"crossref","unstructured":"Shi, B., Bai, X., Belongie, S.: Detecting oriented text in natural images by linking segments. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2550\u20132558 (2017)","DOI":"10.1109\/CVPR.2017.371"},{"key":"2501_CR46","doi-asserted-by":"crossref","unstructured":"Liu, X., Liang, D., Yan, S., Chen, D., Qiao, Y., Yan, J.: Fots: fast oriented text spotting with a unified network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5676\u20135685 (2018)","DOI":"10.1109\/CVPR.2018.00595"},{"key":"2501_CR47","doi-asserted-by":"crossref","unstructured":"Tian, Z., Huang, W., He, T., He, P., Qiao, Y.: Detecting text in natural image with connectionist text proposal network. In: European Conference on Computer Vision, pp. 56\u201372. Springer (2016)","DOI":"10.1007\/978-3-319-46484-8_4"},{"key":"2501_CR48","doi-asserted-by":"crossref","unstructured":"Long, S., Ruan, J., Zhang, W., He, X., Wu, W., Yao, C.: Textsnake: a flexible representation for detecting text of arbitrary shapes. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 20\u201336 (2018)","DOI":"10.1007\/978-3-030-01216-8_2"},{"key":"2501_CR49","doi-asserted-by":"crossref","unstructured":"Shi, B., Wang, X., Lyu, P., Yao, C., Bai, X.: Robust scene text recognition with automatic rectification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4168\u20134176 (2016)","DOI":"10.1109\/CVPR.2016.452"},{"key":"2501_CR50","doi-asserted-by":"crossref","unstructured":"Jobson, D.J., Rahman, Z., Woodell, G.A.: A multiscale retinex for bridging the gap between color images and the human observation of scenes (1997)","DOI":"10.1109\/83.597272"},{"key":"2501_CR51","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-021-02222-2","author":"DK Das","year":"2021","unstructured":"Das, D.K., Shit, S., Ray, D.N., Majumder, S.: CGAN: closure-guided attention network for salient object detection. Vis. Comput. (2021). https:\/\/doi.org\/10.1007\/s00371-021-02222-2","journal-title":"Vis. Comput."},{"key":"2501_CR52","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-022-02404-6","author":"Y Zhang","year":"2022","unstructured":"Zhang, Y., Han, S., Zhang, Z., Wang, J., Bi, H.: CF-GAN: cross-domain feature fusion generative adversarial network for text-to-image synthesis. Vis. Comput. (2022). https:\/\/doi.org\/10.1007\/s00371-022-02404-6","journal-title":"Vis. Comput."}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-022-02501-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-022-02501-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-022-02501-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,29]],"date-time":"2023-06-29T10:10:02Z","timestamp":1688033402000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-022-02501-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,9]]},"references-count":52,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2023,7]]}},"alternative-id":["2501"],"URL":"https:\/\/doi.org\/10.1007\/s00371-022-02501-6","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,5,9]]},"assertion":[{"value":"10 April 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 May 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}