{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T14:40:55Z","timestamp":1777560055192,"version":"3.51.4"},"reference-count":45,"publisher":"SAGE Publications","issue":"4","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AIC"],"published-print":{"date-parts":[[2024,9,18]]},"abstract":"<jats:p>Swin Transformers have been designed and used in various image super-resolution (SR) applications. One of the recent image restoration methods is RSTCANet, which combines Swin Transformer with Channel Attention. However, for some channels of images that may carry less useful information or noise, Channel Attention cannot automatically learn the insignificance of these channels. Instead, it tries to enhance their expression capability by adjusting the weights. It may lead to excessive focus on noise information while neglecting more essential features. In this paper, we propose a new image SR method, RSVTCANet, based on an extension of Swin2SR. Specifically, to effectively gather global information for the channel of images, we modify the Residual SwinV2 Transformer blocks in Swin2SR by introducing the coordinate attention for each two successive SwinV2 Transformer Layers (S2TL) and replacing Multi-head Self-Attention (MSA) with Efficient Multi-head Self-Attention version 2 (EMSAv2) to employ the resulting residual SwinV2 Transformer coordinate attention blocks (RSVTCABs) for feature extraction. Additionally, to improve the generalization of RSVTCANet during training, we apply an optimized RandAugment for data augmentation on the training dataset. Extensive experimental results show that RSVTCANet outperforms the recent image SR method regarding visual quality and measures such as PSNR and SSIM.<\/jats:p>","DOI":"10.3233\/aic-230340","type":"journal-article","created":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T10:32:05Z","timestamp":1712658725000},"page":"693-709","source":"Crossref","is-referenced-by-count":3,"title":["Residual SwinV2 transformer coordinate attention network for image super resolution"],"prefix":"10.1177","volume":"37","author":[{"given":"Yushi","family":"Lei","sequence":"first","affiliation":[{"name":"School of Microelectronics and Control Engineering, Changzhou University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengwei","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Microelectronics and Control Engineering, Changzhou University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yilin","family":"Qin","sequence":"additional","affiliation":[{"name":"Changzhou Technical Institute of Tourism and Commerce, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenyang","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Artificial Intelligence, Changzhou University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanping","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Microelectronics and Control Engineering, Changzhou University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","reference":[{"key":"10.3233\/AIC-230340_ref1","doi-asserted-by":"crossref","unstructured":"E.\u00a0Agustsson and R.\u00a0Timofte, Ntire 2017 challenge on single image super-resolution: Dataset and study, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2017, pp.\u00a0126\u2013135.","DOI":"10.1109\/CVPRW.2017.150"},{"key":"10.3233\/AIC-230340_ref2","doi-asserted-by":"crossref","unstructured":"R.\u00a0Atienza, Data augmentation for scene text recognition, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp.\u00a01561\u20131570.","DOI":"10.1109\/ICCVW54120.2021.00181"},{"key":"10.3233\/AIC-230340_ref3","doi-asserted-by":"crossref","unstructured":"M.\u00a0Bevilacqua, A.\u00a0Roumy, C.\u00a0Guillemot and M.L.\u00a0Alberi-Morel, Low-complexity single-image super-resolution based on nonnegative neighbor embedding (2012).","DOI":"10.5244\/C.26.135"},{"key":"10.3233\/AIC-230340_ref4","doi-asserted-by":"crossref","unstructured":"J.\u00a0Cao, J.\u00a0Liang, K.\u00a0Zhang, Y.\u00a0Li, Y.\u00a0Zhang, W.\u00a0Wang and L.V.\u00a0Gool, Reference-based image super-resolution with deformable attention transformer, in: European Conference on Computer Vision, Springer, 2022, pp.\u00a0325\u2013342.","DOI":"10.1007\/978-3-031-19797-0_19"},{"key":"10.3233\/AIC-230340_ref5","doi-asserted-by":"crossref","unstructured":"H.\u00a0Chen, Y.\u00a0Wang, T.\u00a0Guo, C.\u00a0Xu, Y.\u00a0Deng, Z.\u00a0Liu, S.\u00a0Ma, C.\u00a0Xu, C.\u00a0Xu and W.\u00a0Gao, Pre-trained image processing transformer, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp.\u00a012299\u201312310.","DOI":"10.1109\/CVPR46437.2021.01212"},{"key":"10.3233\/AIC-230340_ref6","doi-asserted-by":"crossref","unstructured":"K.\u00a0Chen, L.\u00a0Li, H.\u00a0Liu, Y.\u00a0Li, C.\u00a0Tang and J.\u00a0Chen, SwinFSR: Stereo image super-resolution using SwinIR and frequency domain knowledge, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp.\u00a01764\u20131774.","DOI":"10.1109\/CVPRW59228.2023.00177"},{"key":"10.3233\/AIC-230340_ref7","doi-asserted-by":"crossref","unstructured":"X.\u00a0Chen, X.\u00a0Wang, J.\u00a0Zhou, Y.\u00a0Qiao and C.\u00a0Dong, Activating more pixels in image super-resolution transformer, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp.\u00a022367\u201322377.","DOI":"10.1109\/CVPR52729.2023.02142"},{"key":"10.3233\/AIC-230340_ref8","first-page":"25478","article-title":"Cross aggregation transformer for image restoration","volume":"35","author":"Chen","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.3233\/AIC-230340_ref9","doi-asserted-by":"crossref","unstructured":"H.\u00a0Choi, J.\u00a0Lee and J.\u00a0Yang, N-gram in swin transformers for efficient lightweight image super-resolution, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp.\u00a02071\u20132081.","DOI":"10.1109\/CVPR52729.2023.00206"},{"key":"10.3233\/AIC-230340_ref10","doi-asserted-by":"crossref","unstructured":"M.V.\u00a0Conde, U.-J.\u00a0Choi, M.\u00a0Burchi and R.\u00a0Timofte, Swin2SR: Swinv2 transformer for compressed image super-resolution and restoration, in: European Conference on Computer Vision, Springer, 2022, pp.\u00a0669\u2013687.","DOI":"10.1007\/978-3-031-25063-7_42"},{"key":"10.3233\/AIC-230340_ref11","doi-asserted-by":"crossref","unstructured":"E.D.\u00a0Cubuk, B.\u00a0Zoph, J.\u00a0Shlens and Q.V.\u00a0Le, Randaugment: Practical automated data augmentation with a reduced search space, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020, pp.\u00a0702\u2013703.","DOI":"10.1109\/CVPRW50498.2020.00359"},{"issue":"2","key":"10.3233\/AIC-230340_ref12","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1109\/TPAMI.2015.2439281","article-title":"Image super-resolution using deep convolutional networks","volume":"38","author":"Dong","year":"2015","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"key":"10.3233\/AIC-230340_ref13","doi-asserted-by":"crossref","unstructured":"C.\u00a0Dong, C.C.\u00a0Loy and X.\u00a0Tang, Accelerating the super-resolution convolutional neural network, in: Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, the Netherlands, October 11\u201314, 2016, Proceedings, Part II 14, Springer, Amsterdam, The Netherlands, 2016, pp.\u00a0391\u2013407.","DOI":"10.1007\/978-3-319-46475-6_25"},{"key":"10.3233\/AIC-230340_ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459271"},{"key":"10.3233\/AIC-230340_ref16","doi-asserted-by":"crossref","unstructured":"Q.\u00a0Hou, D.\u00a0Zhou and J.\u00a0Feng, Coordinate attention for efficient mobile network design, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp.\u00a013713\u201313722.","DOI":"10.1109\/CVPR46437.2021.01350"},{"key":"10.3233\/AIC-230340_ref18","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1016\/j.neucom.2022.04.051","article-title":"Swin transformer for fast MRI","volume":"493","author":"Huang","year":"2022","journal-title":"Neurocomputing"},{"key":"10.3233\/AIC-230340_ref19","doi-asserted-by":"crossref","unstructured":"J.-B.\u00a0Huang, A.\u00a0Singh and N.\u00a0Ahuja, Single image super-resolution from transformed self-exemplars, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp.\u00a05197\u20135206.","DOI":"10.1109\/CVPR.2015.7299156"},{"key":"10.3233\/AIC-230340_ref20","first-page":"1","article-title":"Dtsr: Detail-enhanced transformer for image super-resolution","author":"Huang","year":"2023","journal-title":"The Visual Computer"},{"key":"10.3233\/AIC-230340_ref21","first-page":"1","article-title":"Resolution enhancement processing on low quality images using swin transformer based on interval dense connection strategy","author":"Ju","year":"2023","journal-title":"Multimedia Tools and Applications"},{"key":"10.3233\/AIC-230340_ref23","doi-asserted-by":"crossref","unstructured":"W.-S.\u00a0Lai, J.-B.\u00a0Huang, N.\u00a0Ahuja and M.-H.\u00a0Yang, Deep Laplacian pyramid networks for fast and accurate super-resolution, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp.\u00a0624\u2013632.","DOI":"10.1109\/CVPR.2017.618"},{"key":"10.3233\/AIC-230340_ref24","doi-asserted-by":"crossref","unstructured":"C.\u00a0Ledig, L.\u00a0Theis, F.\u00a0Husz\u00e1r, J.\u00a0Caballero, A.\u00a0Cunningham, A.\u00a0Acosta, A.\u00a0Aitken, A.\u00a0Tejani, J.\u00a0Totz, Z.\u00a0Wang et al., Photo-realistic single image super-resolution using a generative adversarial network, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp.\u00a04681\u20134690.","DOI":"10.1109\/CVPR.2017.19"},{"key":"10.3233\/AIC-230340_ref25","doi-asserted-by":"crossref","unstructured":"Y.\u00a0Li, Y.\u00a0Fan, X.\u00a0Xiang, D.\u00a0Demandolx, R.\u00a0Ranjan, R.\u00a0Timofte and L.\u00a0Van Gool, Efficient and explicit modelling of image hierarchies for image restoration, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp.\u00a018278\u201318289.","DOI":"10.1109\/CVPR52729.2023.01753"},{"key":"10.3233\/AIC-230340_ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2023.103496"},{"key":"10.3233\/AIC-230340_ref27","doi-asserted-by":"crossref","unstructured":"J.\u00a0Liang, J.\u00a0Cao, G.\u00a0Sun, K.\u00a0Zhang, L.\u00a0Van Gool and R.\u00a0Timofte, Swinir: Image restoration using swin transformer, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp.\u00a01833\u20131844.","DOI":"10.1109\/ICCVW54120.2021.00210"},{"key":"10.3233\/AIC-230340_ref28","doi-asserted-by":"crossref","unstructured":"J.\u00a0Liang, H.\u00a0Zeng and L.\u00a0Zhang, Details or artifacts: A locally discriminative learning approach to realistic image super-resolution, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp.\u00a05657\u20135666.","DOI":"10.1109\/CVPR52688.2022.00557"},{"key":"10.3233\/AIC-230340_ref29","doi-asserted-by":"crossref","unstructured":"Z.\u00a0Liu, H.\u00a0Hu, Y.\u00a0Lin, Z.\u00a0Yao, Z.\u00a0Xie, Y.\u00a0Wei, J.\u00a0Ning, Y.\u00a0Cao, Z.\u00a0Zhang, L.\u00a0Dong et al., Swin transformer v2: Scaling up capacity and resolution, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp.\u00a012009\u201312019.","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"10.3233\/AIC-230340_ref30","doi-asserted-by":"crossref","unstructured":"Z.\u00a0Liu, Y.\u00a0Lin, Y.\u00a0Cao, H.\u00a0Hu, Y.\u00a0Wei, Z.\u00a0Zhang, S.\u00a0Lin and B.\u00a0Guo, Swin transformer: Hierarchical vision transformer using shifted windows, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp.\u00a010012\u201310022.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"10.3233\/AIC-230340_ref31","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1016\/j.aej.2023.11.044","article-title":"Asymmetric convolution Swin Transformer for medical image super-resolution","volume":"85","author":"Lu","year":"2023","journal-title":"Alexandria Engineering Journal"},{"key":"10.3233\/AIC-230340_ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2001.937655"},{"key":"10.3233\/AIC-230340_ref33","doi-asserted-by":"publisher","first-page":"21811","DOI":"10.1007\/s11042-016-4020-z","article-title":"Sketch-based manga retrieval using manga109 dataset","volume":"76","author":"Matsui","year":"2017","journal-title":"Multimedia Tools and Applications"},{"key":"10.3233\/AIC-230340_ref34","doi-asserted-by":"crossref","unstructured":"Y.\u00a0Mei, Y.\u00a0Fan and Y.\u00a0Zhou, Image super-resolution with non-local sparse attention, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp.\u00a03517\u20133526.","DOI":"10.1109\/CVPR46437.2021.00352"},{"key":"10.3233\/AIC-230340_ref36","doi-asserted-by":"crossref","unstructured":"S.H.\u00a0Park, Y.S.\u00a0Moon and N.I.\u00a0Cho, Perception-oriented single image super-resolution using optimal objective estimation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp.\u00a01725\u20131735.","DOI":"10.1109\/CVPR52729.2023.00172"},{"key":"10.3233\/AIC-230340_ref37","doi-asserted-by":"crossref","unstructured":"W.\u00a0Shi, J.\u00a0Caballero, F.\u00a0Husz\u00e1r, J.\u00a0Totz, A.P.\u00a0Aitken, R.\u00a0Bishop, D.\u00a0Rueckert and Z.\u00a0Wang, Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp.\u00a01874\u20131883.","DOI":"10.1109\/CVPR.2016.207"},{"key":"10.3233\/AIC-230340_ref38","unstructured":"A.\u00a0Vaswani, N.\u00a0Shazeer, N.\u00a0Parmar, J.\u00a0Uszkoreit, L.\u00a0Jones, A.N.\u00a0Gomez, \u0141.\u00a0Kaiser and I.\u00a0Polosukhin, Attention is all you need, Advances in neural information processing systems, 30 (2017)."},{"key":"10.3233\/AIC-230340_ref39","doi-asserted-by":"crossref","unstructured":"X.\u00a0Wang, L.\u00a0Xie, C.\u00a0Dong and Y.\u00a0Shan, Real-esrgan: Training real-world blind super-resolution with pure synthetic data, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp.\u00a01905\u20131914.","DOI":"10.1109\/ICCVW54120.2021.00217"},{"key":"10.3233\/AIC-230340_ref40","doi-asserted-by":"crossref","unstructured":"X.\u00a0Wang, K.\u00a0Yu, S.\u00a0Wu, J.\u00a0Gu, Y.\u00a0Liu, C.\u00a0Dong, Y.\u00a0Qiao and C.\u00a0Change Loy, Esrgan: Enhanced super-resolution generative adversarial networks, in: Proceedings of the European Conference on Computer Vision (ECCV) Workshops, 2018.","DOI":"10.1007\/978-3-030-11021-5_5"},{"issue":"4","key":"10.3233\/AIC-230340_ref41","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image quality assessment: From error visibility to structural similarity","volume":"13","author":"Wang","year":"2004","journal-title":"IEEE transactions on image processing"},{"key":"10.3233\/AIC-230340_ref42","doi-asserted-by":"crossref","unstructured":"W.\u00a0Xing and K.\u00a0Egiazarian, Residual swin transformer channel attention network for image demosaicing, in: 2022 10th European Workshop on Visual Information Processing (EUVIP), IEEE, 2022, pp.\u00a01\u20136.","DOI":"10.1109\/EUVIP53989.2022.9922679"},{"issue":"8","key":"10.3233\/AIC-230340_ref43","doi-asserted-by":"publisher","first-page":"3467","DOI":"10.1007\/s00371-023-03017-3","article-title":"Rt-swinir: An improved digital wallchart image super-resolution with attention-based learned text loss","volume":"39","author":"Xue","year":"2023","journal-title":"The Visual Computer"},{"key":"10.3233\/AIC-230340_ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27413-8_47"},{"key":"10.3233\/AIC-230340_ref48","first-page":"15475","article-title":"Rest: An efficient transformer for visual recognition","volume":"34","author":"Zhang","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"10.3233\/AIC-230340_ref49","first-page":"36440","article-title":"Rest v2: Simpler, faster and stronger","volume":"35","author":"Zhang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.3233\/AIC-230340_ref50","doi-asserted-by":"crossref","unstructured":"Y.\u00a0Zhang, K.\u00a0Li, K.\u00a0Li, L.\u00a0Wang, B.\u00a0Zhong and Y.\u00a0Fu, Image super-resolution using very deep residual channel attention networks, in: Proceedings of the European Conference on Computer Vision (ECCV), 2018, pp.\u00a0286\u2013301.","DOI":"10.1007\/978-3-030-01234-2_18"},{"key":"10.3233\/AIC-230340_ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2024.120223"},{"issue":"3","key":"10.3233\/AIC-230340_ref54","doi-asserted-by":"publisher","first-page":"768","DOI":"10.1016\/j.ejrs.2023.07.015","article-title":"A double transformer residual super-resolution network for cross-resolution person re-identification","volume":"26","author":"Zhu","year":"2023","journal-title":"The Egyptian Journal of Remote Sensing and Space Science"}],"container-title":["AI Communications"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/AIC-230340","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T18:28:18Z","timestamp":1777400898000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.medra.org\/servlet\/aliasResolver?alias=iospress&doi=10.3233\/AIC-230340"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,18]]},"references-count":45,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.3233\/aic-230340","relation":{},"ISSN":["1875-8452","0921-7126"],"issn-type":[{"value":"1875-8452","type":"electronic"},{"value":"0921-7126","type":"print"}],"subject":[],"published":{"date-parts":[[2024,9,18]]}}}