{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T15:33:56Z","timestamp":1778340836597,"version":"3.51.4"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,11,11]],"date-time":"2024-11-11T00:00:00Z","timestamp":1731283200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,11]],"date-time":"2024-11-11T00:00:00Z","timestamp":1731283200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"the Guiyang City Science and Technology Plan Project","award":["NO.[2024]2-22"],"award-info":[{"award-number":["NO.[2024]2-22"]}]},{"name":"the Science and Technology Foundation of Guizhou Province","award":["NO.QKHJC-ZK[2023]012"],"award-info":[{"award-number":["NO.QKHJC-ZK[2023]012"]}]},{"name":"the Scientific Studies of Higher Education Institution, Guizhou Province Education Department","award":["Youth Project, NO.QEJ[2022]307"],"award-info":[{"award-number":["Youth Project, NO.QEJ[2022]307"]}]},{"name":"the Doctoral Research Start-up Fund of Guiyang University","award":["NO.GYU-KY-2022"],"award-info":[{"award-number":["NO.GYU-KY-2022"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1007\/s11227-024-06662-0","type":"journal-article","created":{"date-parts":[[2024,11,11]],"date-time":"2024-11-11T17:39:40Z","timestamp":1731346780000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":26,"title":["RFAConv-CBM-ViT: enhanced vision transformer for metal surface defect detection"],"prefix":"10.1007","volume":"81","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-8216-4451","authenticated-orcid":false,"given":"Hao","family":"Wei","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6502-587X","authenticated-orcid":false,"given":"Linchang","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4560-4916","authenticated-orcid":false,"given":"Ruiping","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,11]]},"reference":[{"key":"6662_CR1","doi-asserted-by":"publisher","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S, Uszkoreit J, Houlsby N (2021) An image is worth 16x16 words: Transformers for image recognition at scale. In: International Conference on Learning Representations (ICLR). https:\/\/doi.org\/10.48550\/arXiv.2010.11929","DOI":"10.48550\/arXiv.2010.11929"},{"key":"6662_CR2","doi-asserted-by":"publisher","unstructured":"Touvron H, Cord M, Douze M, Massa F, Sablayrolles A, Jegou H (2021) Training data-efficient image transformers & distillation through attention. In: International Conference on Machine Learning (ICML). https:\/\/doi.org\/10.48550\/arXiv.2012.12877","DOI":"10.48550\/arXiv.2012.12877"},{"key":"6662_CR3","unstructured":"Zhang T, Liu H, Wang J, et al (2023) RFAConv: Innovating Spatial Attention and Standard Convolutional Operation. arXiv. https:\/\/arxiv.org\/abs\/2304.03198v6"},{"key":"6662_CR4","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/5592878","author":"W Zhao","year":"2021","unstructured":"Zhao W, Chen F, Huang H, Li D, Cheng W (2021) A new steel defect detection algorithm based on deep learning. Comput Intell Neurosci. https:\/\/doi.org\/10.1155\/2021\/5592878","journal-title":"Comput Intell Neurosci"},{"key":"6662_CR5","doi-asserted-by":"publisher","first-page":"47621","DOI":"10.1109\/ACCESS.2021.3068256","volume":"9","author":"H-I Lin","year":"2021","unstructured":"Lin H-I, Wibowo FS (2021) Image data assessment approach for deep learning-based metal surface defect-detection systems. IEEE Access 9:47621\u201347638. https:\/\/doi.org\/10.1109\/ACCESS.2021.3068256","journal-title":"IEEE Access"},{"key":"6662_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2021.3087826","volume":"70","author":"D Tsai","year":"2021","unstructured":"Tsai D, Fan SKS, Chou Y-H (2021) Auto-annotated deep segmentation for surface defect detection. IEEE Trans Instrum Meas 70:1\u201310. https:\/\/doi.org\/10.1109\/TIM.2021.3087826","journal-title":"IEEE Trans Instrum Meas"},{"key":"6662_CR7","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1016\/j.jmsy.2020.03.009","volume":"55","author":"J Yun","year":"2020","unstructured":"Yun J, Shin W, Koo G, Kim M, Lee C, Lee S (2020) Automated defect inspection system for metal surfaces based on deep learning and data augmentation. J Manuf Syst 55:317\u2013324. https:\/\/doi.org\/10.1016\/j.jmsy.2020.03.009","journal-title":"J Manuf Syst"},{"key":"6662_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/j.optlaseng.2019.01.011","author":"H Di","year":"2019","unstructured":"Di H, Ke X, Peng Z, Zhou D (2019) Surface defect classification of steels with a new semi-supervised learning method. Opt Laser Eng. https:\/\/doi.org\/10.1016\/j.optlaseng.2019.01.011","journal-title":"Opt Laser Eng"},{"issue":"10","key":"6662_CR9","doi-asserted-by":"publisher","first-page":"12131","DOI":"10.1007\/s10462-023-10475-7","volume":"56","author":"Y Liu","year":"2023","unstructured":"Liu Y, Zhang CS, Dong XJ (2023) A survey of real-time surface defect inspection methods based on deep learning. Artif Intell Rev 56(10):12131\u201312170. https:\/\/doi.org\/10.1007\/s10462-023-10475-7","journal-title":"Artif Intell Rev"},{"key":"6662_CR10","doi-asserted-by":"publisher","unstructured":"Fang J, Tan X, Wang Y (2021) ACRM: Attention Cascade R-CNN with Mix-NMS for Metallic Surface Defect Detection. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp 423\u2013430. https:\/\/doi.org\/10.1109\/ICPR48806.2021.9412424","DOI":"10.1109\/ICPR48806.2021.9412424"},{"key":"6662_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2021.3127648","volume":"71","author":"W Wang","year":"2022","unstructured":"Wang W, Mi C, Wu Z, Lu K, Long H, Pan B, Li D, Zhang J, Chen P, Wang B (2022) A real-time steel surface defect detection approach with high accuracy. IEEE Trans Instrum Meas 71:1\u201310. https:\/\/doi.org\/10.1109\/TIM.2021.3127648","journal-title":"IEEE Trans Instrum Meas"},{"key":"6662_CR12","doi-asserted-by":"publisher","DOI":"10.3390\/machines10050327","author":"I Konovalenko","year":"2022","unstructured":"Konovalenko I, Maruschak P, Brezinov\u00e1 J, Prentkovskis O, B\u0159ezina J (2022) Research of U-Net-based CNN architectures for metal surface defect detection. Machines. https:\/\/doi.org\/10.3390\/machines10050327","journal-title":"Machines"},{"key":"6662_CR13","doi-asserted-by":"publisher","first-page":"49783","DOI":"10.3390\/s22249783","volume":"22","author":"Y-C Huang","year":"2022","unstructured":"Huang Y-C, Hung K-C, Lin J-C (2022) Automated machine learning system for defect detection on cylindrical metal surfaces. Sensors (Basel) 22:49783. https:\/\/doi.org\/10.3390\/s22249783","journal-title":"Sensors (Basel)"},{"key":"6662_CR14","doi-asserted-by":"publisher","DOI":"10.3390\/app12168070","author":"F Chen","year":"2022","unstructured":"Chen F, Deng M, Gao H, Yang X, Zhang D (2022) ACA-Net: an adaptive convolution and anchor network for metallic surface defect detection. Appl Sci. https:\/\/doi.org\/10.3390\/app12168070","journal-title":"Appl Sci"},{"issue":"3","key":"6662_CR15","doi-asserted-by":"publisher","first-page":"388","DOI":"10.3390\/MET11030388","volume":"11","author":"S Wang","year":"2021","unstructured":"Wang S, Xia X, Ye L, Yang B (2021) Automatic detection and classification of steel surface defect using deep convolutional neural networks. Metals 11(3):388. https:\/\/doi.org\/10.3390\/MET11030388","journal-title":"Metals"},{"key":"6662_CR16","doi-asserted-by":"publisher","first-page":"3248722","DOI":"10.1155\/2022\/3248722","volume":"2022","author":"B Xia","year":"2022","unstructured":"Xia B, Luo H, Shi S (2022) Improved Faster R-CNN based surface defect detection algorithm for plates. Comput Intell Neurosci 2022:3248722. https:\/\/doi.org\/10.1155\/2022\/3248722","journal-title":"Comput Intell Neurosci"},{"key":"6662_CR17","doi-asserted-by":"publisher","first-page":"107541","DOI":"10.1016\/j.ymssp.2020.107541","volume":"153","author":"S Zhang","year":"2021","unstructured":"Zhang S, Zhang Q, Gu J, Su L, Li K, Pecht MG (2021) Visual inspection of steel surface defects based on domain adaptation and adaptive convolutional neural network. Mech Syst Signal Process 153:107541. https:\/\/doi.org\/10.1016\/j.ymssp.2020.107541","journal-title":"Mech Syst Signal Process"},{"key":"6662_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/tim.2022.3165287","volume":"71","author":"Y Liu","year":"2022","unstructured":"Liu Y, Xiao H, Xu J, Zhao J (2022) A rail surface defect detection method based on pyramid feature and lightweight convolutional neural network. IEEE Trans Instrum Meas 71:1\u201310. https:\/\/doi.org\/10.1109\/tim.2022.3165287","journal-title":"IEEE Trans Instrum Meas"},{"key":"6662_CR19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2023.3290965","volume":"72","author":"WQ Cui","year":"2023","unstructured":"Cui WQ, Song KC, Feng H et al (2023) Autocorrelation-aware aggregation network for salient object detection of strip steel surface defects. IEEE Trans Instrum Meas 72:1. https:\/\/doi.org\/10.1109\/TIM.2023.3290965","journal-title":"IEEE Trans Instrum Meas"},{"issue":"13","key":"6662_CR20","doi-asserted-by":"publisher","first-page":"18919","DOI":"10.1007\/s11227-024-06248-w","volume":"80","author":"ZL Lv","year":"2024","unstructured":"Lv ZL, Zhao ZQ, Xia KW et al (2024) Steel surface defect detection based on MobileViTv2 and YOLOv8. J Supercomput 80(13):18919\u201318941. https:\/\/doi.org\/10.1007\/s11227-024-06248-w","journal-title":"J Supercomput"},{"key":"6662_CR21","doi-asserted-by":"publisher","unstructured":"Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, Lin S, Guo B (2021) Swin Transformer: Hierarchical Vision Transformer using Shifted Windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 9992\u201310002. https:\/\/doi.org\/10.1109\/ICCV48922.2021.00986","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"6662_CR22","doi-asserted-by":"publisher","first-page":"19966","DOI":"10.1109\/cvprw53098.2021.00198","volume":"34","author":"W Xu","year":"2021","unstructured":"Xu W, Zhang J, Zhang Y et al (2021) ViTAE: vision transformer advanced by exploring intrinsic inductive bias. Adv Neural Inf Process Syst 34:19966\u201319980. https:\/\/doi.org\/10.1109\/cvprw53098.2021.00198","journal-title":"Adv Neural Inf Process Syst"},{"key":"6662_CR23","doi-asserted-by":"publisher","unstructured":"Heo B, Yun S, Han D, Chun S, Choe J, Oh S (2021) Rethinking spatial dimensions of vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 11916\u201311925. https:\/\/doi.org\/10.1109\/ICCV48922.2021.01172","DOI":"10.1109\/ICCV48922.2021.01172"},{"key":"6662_CR24","doi-asserted-by":"publisher","unstructured":"Wu H, Xiao B, Codella N, Liu M, Dai X, Yuan L, Zhang L (2021) CvT: Introducing convolutions to vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp 22\u201331. https:\/\/doi.org\/10.1109\/ICCV48922.2021.00009","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"6662_CR25","doi-asserted-by":"publisher","unstructured":"Guo J, Han K, Wu H, Xu C, Tang Y, Xu C, Wang Y (2021) CMT: Convolutional neural networks meet vision transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 12165\u201312175. https:\/\/doi.org\/10.1109\/CVPR52688.2022.01186","DOI":"10.1109\/CVPR52688.2022.01186"},{"key":"6662_CR26","doi-asserted-by":"publisher","unstructured":"Mehta S, Rastegari M (2021) MobileViT: Light-weight, general-purpose, and mobile-friendly vision transformer. arXiv preprint arXiv:2110.02178. https:\/\/doi.org\/10.48550\/arXiv.2110.02178","DOI":"10.48550\/arXiv.2110.02178"},{"key":"6662_CR27","doi-asserted-by":"publisher","unstructured":"Li G, Lin H, Zhu L, et al (2023) Next-ViT: Next generation vision transformer for efficient deployment in realistic industrial scenarios. arXiv preprint arXiv:2301.01234. https:\/\/doi.org\/10.48550\/arXiv.2301.01234","DOI":"10.48550\/arXiv.2301.01234"},{"key":"6662_CR28","doi-asserted-by":"publisher","unstructured":"Devlin J, Chang M, Lee K, Toutanova K (2019) BERT: Pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pp 4171\u20134186. https:\/\/doi.org\/10.18653\/v1\/N19-1423","DOI":"10.18653\/v1\/N19-1423"},{"key":"6662_CR29","doi-asserted-by":"publisher","first-page":"5807","DOI":"10.1109\/ICCV.2023.12345","volume":"2023","author":"S Kim","year":"2023","unstructured":"Kim S, Nam H, Heo B, Han D, Oh SJ, Oh TH (2023) Scratching visual transformer\u2019s back with uniform attention. Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) 2023:5807\u20135818. https:\/\/doi.org\/10.1109\/ICCV.2023.12345","journal-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)"},{"key":"6662_CR30","doi-asserted-by":"publisher","unstructured":"Bello I, Zoph B, Vaswani A, Shlens J, Le QV (2019) Attention augmented convolutional networks. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 3286\u20133295. https:\/\/doi.org\/10.1109\/ICCV.2019.00336","DOI":"10.1109\/ICCV.2019.00336"},{"key":"6662_CR31","doi-asserted-by":"publisher","unstructured":"Srinivas A, Lin TY, Parmar N, et al. (2021) Bottleneck Transformers for Visual Recognition. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 16519\u201316529.https:\/\/doi.org\/10.1109\/CVPR46437.2021.01624","DOI":"10.1109\/CVPR46437.2021.01624"},{"key":"6662_CR32","doi-asserted-by":"publisher","unstructured":"Guo J, Han K, Wu H, et al. (2022) Scaling Local Self-Attention for Parameter Efficient Visual Backbones. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 12595\u201312605. https:\/\/doi.org\/10.1109\/CVPR52688.2022.01225","DOI":"10.1109\/CVPR52688.2022.01225"},{"issue":"2","key":"6662_CR33","doi-asserted-by":"publisher","first-page":"1489","DOI":"10.1109\/TPAMI.2022.3164083","volume":"45","author":"YH Li","year":"2023","unstructured":"Li YH, Yao T, Pan YW, Mei T (2023) Contextual transformer networks for visual recognition. IEEE Trans Pattern Anal Mach Intell 45(2):1489\u20131500. https:\/\/doi.org\/10.1109\/TPAMI.2022.3164083","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"6662_CR34","doi-asserted-by":"publisher","unstructured":"Lin TY, Goyal P, Girshick R, He K, Doll\u00e1r P (2017) Focal Loss for Dense Object Detection. In Proceedings of the IEEE International Conference on Computer Vision (ICCV) (pp. 2999\u20133007). IEEE. https:\/\/doi.org\/10.1109\/ICCV.2017.324","DOI":"10.1109\/ICCV.2017.324"},{"key":"6662_CR35","doi-asserted-by":"publisher","unstructured":"Loshchilov I, Hutter F (2019) Decoupled Weight Decay Regularization. International Conference on Learning Representations (ICLR). https:\/\/doi.org\/10.48550\/arXiv.1711.05101","DOI":"10.48550\/arXiv.1711.05101"},{"key":"6662_CR36","doi-asserted-by":"publisher","unstructured":"Loshchilov I, Hutter F (2017) Stochastic Gradient Descent with Warm Restarts. International Conference on Learning Representations (ICLR). https:\/\/doi.org\/10.48550\/arXiv.1608.03983","DOI":"10.48550\/arXiv.1608.03983"},{"key":"6662_CR37","doi-asserted-by":"crossref","unstructured":"Yuan L, Chen Y, Wang T, Yu W, Shi Y, Jiang Z, Tay FE, Feng J, Yan S (2021) Tokens-to-Token ViT: training vision transformers from scratch on ImageNet. arXiv preprint arXiv:2101.11986. https:\/\/arxiv.org\/abs\/2101.11986","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"6662_CR38","doi-asserted-by":"publisher","first-page":"1328","DOI":"10.1109\/TPAMI.2022.3145427","volume":"45","author":"Q Hou","year":"2021","unstructured":"Hou Q, Jiang Z, Yuan L, Cheng M, Yan S, Feng J (2021) Vision permutator: a permutable MLP-like architecture for visual recognition. IEEE Trans Pattern Anal Mach Intell 45:1328\u20131334. https:\/\/doi.org\/10.1109\/TPAMI.2022.3145427","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"6662_CR39","doi-asserted-by":"publisher","first-page":"1241","DOI":"10.1109\/TMI.2022.3191974","volume":"42","author":"J Pang","year":"2022","unstructured":"Pang J, Jiang C, Chen Y, Chang J, Feng M, Wang R, Yao J (2022) 3D shuffle-mixer: an efficient context-aware vision learner of transformer-MLP paradigm for dense prediction in medical volume. IEEE Trans Med Imaging 42:1241\u20131253. https:\/\/doi.org\/10.1109\/TMI.2022.3191974","journal-title":"IEEE Trans Med Imaging"},{"key":"6662_CR40","doi-asserted-by":"publisher","first-page":"3386","DOI":"10.1109\/TIP.2021.3139234","volume":"31","author":"G Luo","year":"2022","unstructured":"Luo G, Zhou Y, Sun X, Wang Y, Cao L, Wu Y, Huang F, Ji R (2022) Towards lightweight transformer via group-wise transformation for vision-and-language tasks. IEEE Trans Image Process 31:3386\u20133398","journal-title":"IEEE Trans Image Process"},{"key":"6662_CR41","doi-asserted-by":"publisher","unstructured":"Hendrycks D, Gimpel K (2016) Gaussian Error Linear Units (GELUs). arXiv preprint arXiv:1606.08415. https:\/\/doi.org\/10.48550\/arXiv.1606.08415","DOI":"10.48550\/arXiv.1606.08415"},{"key":"6662_CR42","doi-asserted-by":"publisher","unstructured":"Selvaraju RR, Cogswell M, Das A, et al (2016) Visual Explanations from Deep Networks via Gradient-Based Localization. arXiv preprint arXiv:1610.02391. https:\/\/doi.org\/10.48550\/arXiv.1610.02391","DOI":"10.48550\/arXiv.1610.02391"},{"key":"6662_CR43","doi-asserted-by":"publisher","first-page":"770","DOI":"10.1109\/CVPR.2016.90","volume":"2016","author":"K He","year":"2016","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. IEEE Conf Comput Vis Pattern Recognit 2016:770\u2013778. https:\/\/doi.org\/10.1109\/CVPR.2016.90","journal-title":"IEEE Conf Comput Vis Pattern Recognit"},{"key":"6662_CR44","doi-asserted-by":"publisher","unstructured":"Woo S, Debnath S, Hu R, Chen X, Liu Z, Kweon IS, Xie S (2023) ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders. CVPR 2023. https:\/\/doi.org\/10.48550\/arXiv.2301.00808","DOI":"10.48550\/arXiv.2301.00808"},{"key":"6662_CR45","doi-asserted-by":"publisher","unstructured":"Liu Z, Hu H, Lin Y, Yao Z, Xie Z, Wei Y, Ning J, Cao Y, Zhang Z, Dong L, Wei F, Guo B (2022) Swin Transformer V2: Scaling up Capacity and Resolution. CVPR 2022. https:\/\/doi.org\/10.48550\/arXiv.2111.09883","DOI":"10.48550\/arXiv.2111.09883"},{"key":"6662_CR46","doi-asserted-by":"publisher","unstructured":"Vasu PKA, Gabriel J, Zhu J, Tuzel O, Ranjan A (2023) FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization. ICCV 2023. https:\/\/doi.org\/10.1109\/ICCV51070.2023.00532","DOI":"10.1109\/ICCV51070.2023.00532"},{"key":"6662_CR47","doi-asserted-by":"publisher","unstructured":"Liu X, Peng H, Zheng N, Yang Y, Hu H, Yuan Y (2023) EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention. CVPR 2023. https:\/\/doi.org\/10.1109\/CVPR52729.2023.01386","DOI":"10.1109\/CVPR52729.2023.01386"},{"key":"6662_CR48","doi-asserted-by":"publisher","unstructured":"Zhu L, Liao B, Zhang Q, Wang X, Liu W, Wang X (2024) Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model. ICML 2024. https:\/\/doi.org\/10.48550\/arXiv.2401.09417","DOI":"10.48550\/arXiv.2401.09417"},{"key":"6662_CR49","doi-asserted-by":"publisher","unstructured":"Zhu L, Liao B, Zhang Q, Wang X, Liu W, Wang X (2024) VMamba: Visual State Space Model. NeurIPS 2024. https:\/\/doi.org\/10.48550\/arXiv.2401.10166","DOI":"10.48550\/arXiv.2401.10166"},{"key":"6662_CR50","doi-asserted-by":"publisher","unstructured":"Hatamizadeh A, Kautz J (2024) MambaVision: A Hybrid Mamba-Transformer Vision Backbone. arXiv preprint. https:\/\/doi.org\/10.48550\/arXiv.2407.08083","DOI":"10.48550\/arXiv.2407.08083"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-024-06662-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-024-06662-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-024-06662-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,11]],"date-time":"2024-11-11T18:06:15Z","timestamp":1731348375000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-024-06662-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,11]]},"references-count":50,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["6662"],"URL":"https:\/\/doi.org\/10.1007\/s11227-024-06662-0","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"value":"0920-8542","type":"print"},{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,11]]},"assertion":[{"value":"27 October 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 November 2024","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 competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}}],"article-number":"155"}}