{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T19:54:38Z","timestamp":1769457278545,"version":"3.49.0"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["6207246"],"award-info":[{"award-number":["6207246"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Circuits Syst Signal Process"],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1007\/s00034-024-02867-z","type":"journal-article","created":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T16:01:49Z","timestamp":1727798509000},"page":"1075-1102","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["MDA-GAN: Multi-dimensional Attention Guided Concurrent-Single-Image-GAN"],"prefix":"10.1007","volume":"44","author":[{"given":"Boyang","family":"Gu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xueqin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weifeng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9910-7884","authenticated-orcid":false,"given":"Yanjiang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,1]]},"reference":[{"issue":"1","key":"2867_CR1","doi-asserted-by":"publisher","first-page":"241","DOI":"10.46300\/91011.2022.16.30","volume":"16","author":"AK Aggarwal","year":"2022","unstructured":"A.K. Aggarwal, Biological tomato leaf disease classification using deep learning framework. Int. J. Biol. Biomed. Eng. 16(1), 241\u2013244 (2022)","journal-title":"Int. J. Biol. Biomed. Eng."},{"key":"2867_CR2","unstructured":"A. Almahairi, N. Ballas, T. Cooijmans, Y. Zheng, H. Larochelle, A.C. Courville, Dynamic capacity networks, in International Conference on Machine Learning (2015). https:\/\/api.semanticscholar.org\/CorpusID:818973"},{"key":"2867_CR3","doi-asserted-by":"crossref","unstructured":"J. Deng, W. Dong, R. Socher, L.J. Li, K. Li, L. Fei-Fei, Imagenet: A large-scale hierarchical image database, in 2009 IEEE Conference on Computer Vision and Pattern Recognition (2009). p. 248\u2013255. https:\/\/api.semanticscholar.org\/CorpusID:57246310","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"2867_CR4","doi-asserted-by":"publisher","first-page":"560","DOI":"10.1007\/s10489-020-01803-3","volume":"51","author":"C Ding","year":"2020","unstructured":"C. Ding, K. Liu, F. Cheng, E. Belyaev, Spatio-temporal attention on manifold space for 3d human action recognition. Appl. Intell. 51, 560\u2013570 (2020)","journal-title":"Appl. Intell."},{"key":"2867_CR5","doi-asserted-by":"crossref","unstructured":"I.J. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A.C. Courville, Y. Bengio, Generative adversarial networks, in Other Conferences (2021). https:\/\/api.semanticscholar.org\/CorpusID:1033682","DOI":"10.1145\/3422622"},{"key":"2867_CR6","doi-asserted-by":"crossref","unstructured":"T. Hinz, M. Fisher, O. Wang, S. Wermter, Improved techniques for training single-image gans, in 2021 IEEE Winter Conference on Applications of Computer Vision (WACV) (2020). p. 1299\u20131308. https:\/\/api.semanticscholar.org\/CorpusID:214641222","DOI":"10.1109\/WACV48630.2021.00134"},{"key":"2867_CR7","doi-asserted-by":"crossref","unstructured":"Y. Hong, L. Niu, J. Zhang, W. Zhao, C. Fu, L. Zhang, F2gan: Fusing-and-filling gan for few-shot image generation, in Proceedings of the 28th ACM International Conference on Multimedia (2020). https:\/\/api.semanticscholar.org\/CorpusID:220968925","DOI":"10.1145\/3394171.3413561"},{"key":"2867_CR8","doi-asserted-by":"crossref","unstructured":"J. Hu, L. Shen, S. Albanie, G. Sun, E. Wu, Squeeze-and-excitation networks, in 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2017). p. 7132\u20137141. https:\/\/api.semanticscholar.org\/CorpusID:140309863","DOI":"10.1109\/CVPR.2018.00745"},{"key":"2867_CR9","unstructured":"M. Jaderberg, K. Simonyan, A. Zisserman, K. Kavukcuoglu, Spatial transformer networks. arXiv:1506.02025 (2015). https:\/\/api.semanticscholar.org\/CorpusID:6099034"},{"key":"2867_CR10","doi-asserted-by":"crossref","unstructured":"M. Kang, J.Y. Zhu, R. Zhang, J. Park, E. Shechtman, S. Paris, T. Park, Scaling up gans for text-to-image synthesis, in 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023). pp. 10124\u201310134. https:\/\/api.semanticscholar.org\/CorpusID:257427461","DOI":"10.1109\/CVPR52729.2023.00976"},{"key":"2867_CR11","unstructured":"T. Karras, T. Aila, S. Laine, J. Lehtinen, Progressive growing of gans for improved quality, stability, and variation. arXiv:1710.10196 (2017). https:\/\/api.semanticscholar.org\/CorpusID:3568073"},{"key":"2867_CR12","doi-asserted-by":"crossref","unstructured":"D.W. Kim, J. Chung, S. Jung, Grdn:grouped residual dense network for real image denoising and gan-based real-world noise modeling, in 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (2019). pp. 2086\u20132094. https:\/\/api.semanticscholar.org\/CorpusID:166228003","DOI":"10.1109\/CVPRW.2019.00261"},{"key":"2867_CR13","doi-asserted-by":"crossref","unstructured":"J. Korhonen, J. You, Peak signal-to-noise ratio revisited: Is simple beautiful? in 2012 Fourth International Workshop on Quality of Multimedia Experience. IEEE (2012). pp. 37\u201338","DOI":"10.1109\/QoMEX.2012.6263880"},{"key":"2867_CR14","unstructured":"J. Li, D. Li, C. Xiong, S.C.H. Hoi, Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation, in International Conference on Machine Learning (2022). https:\/\/api.semanticscholar.org\/CorpusID:246411402"},{"key":"2867_CR15","doi-asserted-by":"crossref","unstructured":"Y. Li, H. Liu, Q. Wu, F. Mu, J. Yang, J. Gao, C. Li, Y.J. Lee, Gligen: Open-set grounded text-to-image generation, in 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023). pp. 22511\u201322521. https:\/\/api.semanticscholar.org\/CorpusID:255942528","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"2867_CR16","doi-asserted-by":"crossref","unstructured":"H. Liu, Z. Wan, W. Huang, Y. Song, X. Han, J. Liao, Pd-gan: Probabilistic diverse gan for image inpainting, in 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021). pp. 9367\u20139376. https:\/\/api.semanticscholar.org\/CorpusID:233739687","DOI":"10.1109\/CVPR46437.2021.00925"},{"key":"2867_CR17","doi-asserted-by":"crossref","unstructured":"J. Liu, J. Shang, R. Liu, X. Fan, Attention-guided global-local adversarial learning for detail-preserving multi-exposure image fusion, in IEEE Transactions on Circuits and Systems for Video Technology vol. 32, (2022). pp. 5026\u20135040. https:\/\/api.semanticscholar.org\/CorpusID:246058993","DOI":"10.1109\/TCSVT.2022.3144455"},{"key":"2867_CR18","doi-asserted-by":"publisher","first-page":"108146","DOI":"10.1016\/j.knosys.2022.108146","volume":"240","author":"Y Liu","year":"2022","unstructured":"Y. Liu, H. Zhang, D. Xu, K. He, Graph transformer network with temporal kernel attention for skeleton-based action recognition. Knowl. Based Syst. 240, 108146 (2022)","journal-title":"Knowl. Based Syst."},{"key":"2867_CR19","unstructured":"Y. Liu, Z. Shao, Y. Teng, N. Hoffmann, NAM: Normalization-based attention module. arXiv:2111.12419 (2021). https:\/\/api.semanticscholar.org\/CorpusID:244527360"},{"key":"2867_CR20","unstructured":"J. Park, S. Woo, J.Y. Lee, I.S. Kweon, BAM: Bottleneck attention module. arXiv:1807.06514 (2018). https:\/\/api.semanticscholar.org\/CorpusID:49864419"},{"key":"2867_CR21","unstructured":"I. Perez, R. Reinauer, The topological bert: Transforming attention into topology for natural language processing. arXiv:2206.15195. https:\/\/api.semanticscholar.org\/CorpusID:250144371 (2022)"},{"key":"2867_CR22","doi-asserted-by":"publisher","first-page":"102926","DOI":"10.1016\/j.ipm.2022.102926","volume":"59","author":"Z Qin","year":"2022","unstructured":"Z. Qin, Q. Chen, Y. Ding, T. Zhuang, Z.Q. Qin, K.R. Choo, Segmentation mask and feature similarity loss guided GAN for object-oriented image-to-image translation. Inf. Process. Manag. 59, 102926 (2022)","journal-title":"Inf. Process. Manag."},{"key":"2867_CR23","unstructured":"A. Radford, L. Metz, S. Chintala, Unsupervised representation learning with deep convolutional generative adversarial networks. https:\/\/arxiv.org\/abs\/1511.06434. https:\/\/api.semanticscholar.org\/CorpusID:11758569 (2015)"},{"key":"2867_CR24","doi-asserted-by":"crossref","unstructured":"T.R. Shaham, T. Dekel, T. Michaeli, SinGAN: Learning a generative model from a single natural image, in 2019 IEEE\/CVF International Conference on Computer Vision (ICCV) (2019). pp. 4569\u20134579. https:\/\/api.semanticscholar.org\/CorpusID:145052179","DOI":"10.1109\/ICCV.2019.00467"},{"key":"2867_CR25","doi-asserted-by":"crossref","unstructured":"A. Shocher, S. Bagon, P. Isola, M. Irani, InGAN: Capturing and retargeting the \u201cDNA\u201d of a natural image, in 2019 IEEE\/CVF International Conference on Computer Vision (ICCV) (2019). pp. 4491\u20134500. https:\/\/api.semanticscholar.org\/CorpusID:208002447","DOI":"10.1109\/ICCV.2019.00459"},{"key":"2867_CR26","first-page":"1","volume":"20","author":"Y Song","year":"2023","unstructured":"Y. Song, J. Li, Z. Hu, L. Cheng, DBSAGAN: Dual branch split attention generative adversarial network for super-resolution reconstruction in remote sensing images. IEEE Geosci. Remote Sens. Lett. 20, 1\u20135 (2023)","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"2867_CR27","doi-asserted-by":"publisher","first-page":"063017","DOI":"10.1117\/1.JEI.30.6.063017","volume":"30","author":"Y Tian","year":"2021","unstructured":"Y. Tian, X. li Chai, Z. Gan, Y. Lu, Y. Zhang, S. Song, Swdgan: GAN-based sampling and whole image denoising network for compressed sensing image reconstruction. J. Electron. Imaging 30, 063017\u2013063017 (2021)","journal-title":"J. Electron. Imaging"},{"key":"2867_CR28","unstructured":"O. Vinyals, C. Blundell, T.P. Lillicrap, K. Kavukcuoglu, D. Wierstra, Matching networks for one shot learning, in Neural Information Processing Systems (2016). https:\/\/api.semanticscholar.org\/CorpusID:8909022"},{"key":"2867_CR29","doi-asserted-by":"publisher","first-page":"108636","DOI":"10.1016\/j.patcog.2022.108636","volume":"127","author":"K Wang","year":"2022","unstructured":"K. Wang, X. Zhang, X. Zhang, Y. Lu, S. Huang, D. Yang, Eanet: Iterative edge attention network for medical image segmentation. Pattern Recognit. 127, 108636 (2022)","journal-title":"Pattern Recognit."},{"key":"2867_CR30","doi-asserted-by":"crossref","unstructured":"X. Wang, L. Sun, A. Chehri, Y. Song, A review of gan-based super-resolution reconstruction for optical remote sensing images. Remote Sensing (2023). https:\/\/api.semanticscholar.org\/CorpusID:264409549","DOI":"10.3390\/rs15205062"},{"key":"2867_CR31","doi-asserted-by":"crossref","unstructured":"X. Wang, W. Jiang, L. Zhao, B. Liu, Y. Wang, Ccasingan: Cascaded channel attention guided single-image GANS, in 2022 16th IEEE International Conference on Signal Processing (ICSP), vol. 1 (2022). pp. 61\u201365. https:\/\/api.semanticscholar.org\/CorpusID:254153101","DOI":"10.1109\/ICSP56322.2022.9965227"},{"key":"2867_CR32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2022.3216413","volume":"71","author":"Z Wang","year":"2022","unstructured":"Z. Wang, Y. Wu, J. Wang, J. Xu, W. Shao, Res2fusion: infrared and visible image fusion based on dense res2net and double nonlocal attention models. IEEE Trans. Instrum. Meas. 71, 1\u201312 (2022)","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"2867_CR33","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Z. Wang, A.C. Bovik, H.R. Sheikh, E.P. Simoncelli, Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13, 600\u2013612 (2004)","journal-title":"IEEE Trans. Image Process."},{"key":"2867_CR34","doi-asserted-by":"crossref","unstructured":"S. Woo, J. Park, J.Y. Lee, I.S. Kweon, CBAM: Convolutional block attention module (2018). arXiv:1807.06521. https:\/\/api.semanticscholar.org\/CorpusID:49867180","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"2867_CR35","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1016\/j.neucom.2021.06.009","volume":"458","author":"B Yang","year":"2021","unstructured":"B. Yang, L. Wang, D.F. Wong, S. Shi, Z. Tu, Context-aware self-attention networks for natural language processing. Neurocomputing 458, 157\u2013169 (2021)","journal-title":"Neurocomputing"},{"key":"2867_CR36","unstructured":"L. Yang, R.Y. Zhang, L. Li, X. Xie, Simam: A simple, parameter-free attention module for convolutional neural networks, in International Conference on Machine Learning (2021). https:\/\/api.semanticscholar.org\/CorpusID:235825945"},{"key":"2867_CR37","unstructured":"F. Yu, Y. Zhang, S. Song, A. Seff, J. Xiao, LSUN: Construction of a large-scale image dataset using deep learning with humans in the loop. arXiv:1506.03365 (2015). https:\/\/api.semanticscholar.org\/CorpusID:8317437"},{"key":"2867_CR38","doi-asserted-by":"publisher","first-page":"151103","DOI":"10.1109\/ACCESS.2019.2946461","volume":"7","author":"W Zhang","year":"2019","unstructured":"W. Zhang, Generating adversarial examples in one shot with image-to-image translation GAN. IEEE Access 7, 151103\u2013151119 (2019)","journal-title":"IEEE Access"},{"key":"2867_CR39","doi-asserted-by":"crossref","unstructured":"B. Zhou, A. Khosla, \u00c0. Lapedriza, A. Oliva, A. Torralba, Learning deep features for discriminative localization, in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015). pp. 2921\u20132929. https:\/\/api.semanticscholar.org\/CorpusID:6789015","DOI":"10.1109\/CVPR.2016.319"},{"key":"2867_CR40","unstructured":"B. Zhou, \u00c0. Lapedriza, J. Xiao, A. Torralba, A. Oliva, Learning deep features for scene recognition using places database, in Neural Information Processing Systems (2014). https:\/\/api.semanticscholar.org\/CorpusID:1849990"},{"key":"2867_CR41","doi-asserted-by":"crossref","unstructured":"J. Zhu, C. Yang, Y. Shen, Z. Shi, D. Zhao, Q. Chen, Linkgan: Linking GAN latents to pixels for controllable image synthesis. arXiv:2301.04604 (2023). https:\/\/api.semanticscholar.org\/CorpusID:255595751","DOI":"10.1109\/ICCV51070.2023.00704"},{"key":"2867_CR42","doi-asserted-by":"crossref","unstructured":"J.Y. Zhu, T. Park, P. Isola, A.A. Efros, Unpaired image-to-image translation using cycle-consistent adversarial networks, in 2017 IEEE International Conference on Computer Vision (ICCV) (2017). pp. 2242\u20132251. https:\/\/api.semanticscholar.org\/CorpusID:206770979","DOI":"10.1109\/ICCV.2017.244"},{"key":"2867_CR43","first-page":"1","volume":"61","author":"Y Zhu","year":"2023","unstructured":"Y. Zhu, S. Chen, X. Lu, J. Chen, Cross-view image synthesis from a single image with progressive parallel GAN. IEEE Trans. Geosci. Remote Sens. 61, 1\u201313 (2023)","journal-title":"IEEE Trans. Geosci. Remote Sens."}],"container-title":["Circuits, Systems, and Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-024-02867-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00034-024-02867-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-024-02867-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,2]],"date-time":"2025-02-02T21:16:46Z","timestamp":1738531006000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00034-024-02867-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,1]]},"references-count":43,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,2]]}},"alternative-id":["2867"],"URL":"https:\/\/doi.org\/10.1007\/s00034-024-02867-z","relation":{},"ISSN":["0278-081X","1531-5878"],"issn-type":[{"value":"0278-081X","type":"print"},{"value":"1531-5878","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,1]]},"assertion":[{"value":"10 December 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 September 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 September 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 October 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no relevant financial or non-financial interests to disclose.Authors declare no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}