{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T01:50:48Z","timestamp":1772502648444,"version":"3.50.1"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2025,3,17]],"date-time":"2025-03-17T00:00:00Z","timestamp":1742169600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,3,17]],"date-time":"2025-03-17T00:00:00Z","timestamp":1742169600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["51974276"],"award-info":[{"award-number":["51974276"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Russian Academic of Science","award":["FFZF-2025-0016"],"award-info":[{"award-number":["FFZF-2025-0016"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Complex Intell. Syst."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1007\/s40747-025-01842-8","type":"journal-article","created":{"date-parts":[[2025,3,17]],"date-time":"2025-03-17T16:33:02Z","timestamp":1742229182000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["A lightweight vision transformer with weighted global average pooling: implications for IoMT applications"],"prefix":"10.1007","volume":"11","author":[{"given":"Huiyao","family":"Dong","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6859-7120","authenticated-orcid":false,"given":"Igor","family":"Kotenko","sequence":"additional","affiliation":[]},{"given":"Shimin","family":"Dong","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,3,17]]},"reference":[{"key":"1842_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2019.104863","volume":"28","author":"W Al-Dhabyani","year":"2019","unstructured":"Al-Dhabyani W, Gomaa M, Khaled H, Fahmy A (2019) Dataset of breast ultrasound images. Data Br 28:104863. https:\/\/doi.org\/10.1016\/j.dib.2019.104863","journal-title":"Data Br"},{"key":"1842_CR2","doi-asserted-by":"publisher","unstructured":"Alshareef MS, Alturki B, Jaber M (2022) A transformer-based model for effective and exportable iomt-based stress detection. In: GLOBECOM 2022\u20142022 IEEE global communications conference. Rio de Janeiro, Brazil, pp 1158\u20131163. https:\/\/doi.org\/10.1109\/GLOBECOM48099.2022.10001083","DOI":"10.1109\/GLOBECOM48099.2022.10001083"},{"key":"1842_CR3","unstructured":"Bakhtiarnia A, Zhang Q, Iosifidis A (2021) Multi-exit vision transformer for dynamic inference. In: British machine vision conference"},{"key":"1842_CR4","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCOUTCOMES.118.005122","author":"B Beaulieu-Jones","year":"2019","unstructured":"Beaulieu-Jones B, Wu Z, Williams C, Lee R, Bhavnani S, Byrd J, Greene C (2019) Privacy-preserving generative deep neural networks support clinical data sharing. Circ Cardiovasc Qual Outcomes. https:\/\/doi.org\/10.1161\/CIRCOUTCOMES.118.005122","journal-title":"Circ Cardiovasc Qual Outcomes"},{"key":"1842_CR5","doi-asserted-by":"publisher","unstructured":"Chollet F (2017) Xception: deep learning with depthwise separable convolutions. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR). Honolulu, HI, USA pp 1800\u20131807. https:\/\/doi.org\/10.1109\/CVPR.2017.195","DOI":"10.1109\/CVPR.2017.195"},{"key":"1842_CR6","unstructured":"Chu X, Tian Z, Zhang B, Wang X, Shen C (2022) Conditional positional encodings for vision transformers. In: The eleventh international conference on learning representations"},{"key":"1842_CR7","unstructured":"( ICLR 2023), Kigali, Rwanda"},{"key":"1842_CR8","doi-asserted-by":"publisher","first-page":"14871","DOI":"10.1007\/s11042-019-07856-y","volume":"79","author":"H Ding","year":"2020","unstructured":"Ding H, Wei B, Gu Z, Yu Z, Zheng H, Zheng B, Li J (2020) Ka-ensemble: towards imbalanced image classification ensembling under-sampling and over-sampling. Multimed Tools Appl 79:14871\u201314888","journal-title":"Multimed Tools Appl"},{"key":"1842_CR9","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 16 x 16 words: transformers for image recognition at scale. ICLR"},{"key":"1842_CR10","doi-asserted-by":"crossref","unstructured":"d\u2019Ascoli S, Touvron H, Leavitt ML, Morcos AS, Biroli G, Sagun L (2021) Convit: improving vision transformers with soft convolutional inductive biases. In: International conference on machine learning. PMLR, pp 2286\u20132296","DOI":"10.1088\/1742-5468\/ac9830"},{"key":"1842_CR11","doi-asserted-by":"crossref","unstructured":"Fayyaz M, Abbasi Kouhpayegani S, Rezaei Jafari F, Sommerlade E, Vaezi Joze HR, Pirsiavash H, Gall J (2022) Adaptive token sampling for efficient vision transformers. European conference on computer vision (ECCV) Tel Aviv, Israel","DOI":"10.1007\/978-3-031-20083-0_24"},{"key":"1842_CR12","unstructured":"Glorot X, Bengio Y (2010) Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics. Proceedings of machine learning research, vol.\u00a09. Chia Laguna Resort, Sardinia, pp 249\u2013256 (13\u201315 May 2010)"},{"key":"1842_CR13","doi-asserted-by":"crossref","unstructured":"Grainger R, Paniagua T, Song X, Cuntoor N, Lee MW, Wu T (2023) Paca-vit: learning patch-to-cluster attention in vision transformers. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. Vancouver, Canada pp. 18568\u201318578","DOI":"10.1109\/CVPR52729.2023.01781"},{"key":"1842_CR14","unstructured":"Guo J, Deng J, Lattas A, Zafeiriou S (2022) Sample and computation redistribution for efficient face detection. In: International conference on learning representations"},{"key":"1842_CR15","unstructured":"Hatamizadeh A, Yin H, Heinrich G, Kautz J, Molchanov P (2023) Global context vision transformers. In: International conference on machine learning. PMLR, pp 12633\u201312646"},{"issue":"1","key":"1842_CR16","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1016\/j.imed.2022.07.002","volume":"3","author":"K He","year":"2023","unstructured":"He K, Gan C, Li Z, Rekik I, Yin Z, Ji W, Gao Y, Wang Q, Zhang J, Shen D (2023) Transformers in medical image analysis. Intell Med 3(1):59\u201378. https:\/\/doi.org\/10.1016\/j.imed.2022.07.002","journal-title":"Intell Med"},{"key":"1842_CR17","doi-asserted-by":"crossref","unstructured":"He T, Zhang Z, Zhang H, Zhang Z, Xie J, Li M (2019) Bag of tricks for image classification with con-volutional neural networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp 558\u2013567","DOI":"10.1109\/CVPR.2019.00065"},{"key":"1842_CR18","unstructured":"Jaegle A, Gimeno F, Brock A, Vinyals O, Zisserman A, Carreira J (2021) Perceiver: general perception with iterative attention. In: International conference on machine learning. pp 4651\u20134664"},{"issue":"10s","key":"1842_CR19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3505244","volume":"54","author":"S Khan","year":"2022","unstructured":"Khan S, Naseer M, Hayat M, Zamir SW, Khan FS, Shah M (2022) Transformers in vision: a survey. ACM Comput Surv 54(10s):1\u201341","journal-title":"ACM Comput Surv"},{"key":"1842_CR20","doi-asserted-by":"publisher","unstructured":"Li W, Lu X, Qian S, Lu J (2023) On efficient transformer-based image pre-training for low-level vision. In: Proceedings of the thirty-second international joint conference on artificial intelligence, IJCAI-23. pp. 1089\u20131097. International joint conferences on artificial intelligence organization. https:\/\/doi.org\/10.24963\/ijcai.2023\/121 (main Track)","DOI":"10.24963\/ijcai.2023\/121"},{"key":"1842_CR21","unstructured":"Liu L, Jiang H, He P, Chen W, Liu X, Gao J, Han J (2020) On the variance of the adaptive learning rate and beyond. In: International conference on learning representations"},{"key":"1842_CR22","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.107268","volume":"164","author":"Z Liu","year":"2023","unstructured":"Liu Z, Lv Q, Yang Z, Li Y, Lee CH, Shen L (2023) Recent progress in transformer-based medical image analysis. Comput Biol Med 164:107268. https:\/\/doi.org\/10.1016\/j.compbiomed.2023.107268","journal-title":"Comput Biol Med"},{"issue":"10","key":"1842_CR23","doi-asserted-by":"publisher","first-page":"8828","DOI":"10.1609\/aaai.v35i10.17069","volume":"35","author":"J Ma","year":"2021","unstructured":"Ma J, Yarats D (2021) On the adequacy of untuned warmup for adaptive optimization. Proc AAAI Conf Artif Intell 35(10):8828\u20138836. https:\/\/doi.org\/10.1609\/aaai.v35i10.17069","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"1842_CR24","unstructured":"Mehta S, Rastegari M (2022) Mobilevit: light-weight, general-purpose, and mobile-friendly vision transformer. In: International conference on learning representations"},{"key":"1842_CR25","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.107791","volume":"131","author":"H Naveed","year":"2024","unstructured":"Naveed H, Anwar S, Hayat M, Javed K, Mian A (2024) Survey: image mixing and deleting for data augmentation. Eng Appl Artif Intell 131:107791","journal-title":"Eng Appl Artif Intell"},{"key":"1842_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10489-024-05644-2","volume":"54","author":"YJ Park","year":"2024","unstructured":"Park YJ, Cheng KY (2024) A cluster impurity-based hybrid resampling for imbalanced classification problems. Appl Intell 54:1\u201314","journal-title":"Appl Intell"},{"key":"1842_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102007","volume":"101","author":"Z Qin","year":"2024","unstructured":"Qin Z, Zhang Y, Li J, Li D, Mo Y, Wang L, Qian P, Feng L (2024) A reconstruction and convolution operations enabled variant vision transformer with gastroscopic images for automatic locating of polyps in internet of medical things. Inf Fusion 101:102007. https:\/\/doi.org\/10.1016\/j.inffus.2023.102007","journal-title":"Inf Fusion"},{"key":"1842_CR28","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1038\/s41597-021-00815-z","volume":"8","author":"V Rotemberg","year":"2021","unstructured":"Rotemberg V, Kurtansky N, Betz-Stablein B, Caffery L, Chousakos E, Codella N, Combalia M, Dusza S, Guitera P, Gutman D, Halpern A, Helba B, Kittler H, Kose K, Langer S, Lioprys K, Malvehy J, Musthaq S, Nanda J, Soyer P (2021) A patient-centric dataset of images and metadata for identifying melanomas using clinical context. Sci Data 8:34. https:\/\/doi.org\/10.1038\/s41597-021-00815-z","journal-title":"Sci Data"},{"issue":"3","key":"1842_CR29","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M, Berg AC, Fei-Fei L (2015) Imagenet large scale visual recognition challenge. Int J Comput Vis (IJCV) 115(3):211\u2013252","journal-title":"Int J Comput Vis (IJCV)"},{"key":"1842_CR30","doi-asserted-by":"publisher","unstructured":"Sinha D, El-Sharkawy M (2019) Thin mobilenet: an enhanced mobilenet architecture. In: 2019 IEEE 10th annual ubiquitous computing, electronics and mobile communication conference (UEMCON). pp 0280\u20130285. https:\/\/doi.org\/10.1109\/UEMCON47517.2019.8993089","DOI":"10.1109\/UEMCON47517.2019.8993089"},{"issue":"11","key":"1842_CR31","doi-asserted-by":"publisher","first-page":"769","DOI":"10.1109\/TSMC.1976.4309452","volume":"SMC\u20136","author":"I Tomek","year":"1976","unstructured":"Tomek I (1976) Two modifications of cnn. IEEE Trans Syst Man Cybern SMC\u20136(11):769\u2013772. https:\/\/doi.org\/10.1109\/TSMC.1976.4309452","journal-title":"IEEE Trans Syst Man Cybern"},{"key":"1842_CR32","unstructured":"Wang S, Li BZ, Khabsa M, Fang H, Ma H (2020) Linformer: self-attention with linear complexity"},{"key":"1842_CR33","doi-asserted-by":"crossref","unstructured":"Wilson DL (1972) Asymptotic properties of nearest neighbor rules using edited data. IEEE Trans Syst Man Cybern 3:408\u2013421","DOI":"10.1109\/TSMC.1972.4309137"},{"key":"1842_CR34","doi-asserted-by":"crossref","unstructured":"Wu K, Peng H, Chen M, Fu J, Chao H (2021) Rethinking and improving relative position encoding for vision transformer. In: Proceedings of the IEEE\/CVF international conference on computer vision (ICCV). pp 10033\u201310041","DOI":"10.1109\/ICCV48922.2021.00988"},{"key":"1842_CR35","doi-asserted-by":"crossref","unstructured":"Xie Y, Zhang J, Shen C, Xia Y (2021) Cotr: Efficiently bridging cnn and transformer for 3d medical image segmentation. In: Medical image computing and computer assisted intervention\u2014MICCAI 2021: 24th international conference, Strasbourg, France, September 27\u2013October 1, 2021, Proceedings, Part III 24. Springer, pp 171\u2013180","DOI":"10.1007\/978-3-030-87199-4_16"},{"issue":"11","key":"1842_CR36","doi-asserted-by":"publisher","first-page":"3677","DOI":"10.1109\/JSAC.2023.3310096","volume":"41","author":"L Xing","year":"2023","unstructured":"Xing L, Liu W, Liu X, Li X (2023) An enhanced vision transformer model in digital twins powered internet of medical things for pneumonia diagnosis. IEEE J Sel Areas Commun 41(11):3677\u20133689. https:\/\/doi.org\/10.1109\/JSAC.2023.3310096","journal-title":"IEEE J Sel Areas Commun"},{"issue":"16","key":"1842_CR37","doi-asserted-by":"publisher","first-page":"14138","DOI":"10.1609\/aaai.v35i16.17664","volume":"35","author":"Y Xiong","year":"2021","unstructured":"Xiong Y, Zeng Z, Chakraborty R, Tan M, Fung G, Li Y, Singh V (2021) Nystr\u00f6mformer: a nystr\u00f6m-based algorithm for approximating self-attention. Proc AAAI Conf Artif Intell 35(16):14138\u201314148. https:\/\/doi.org\/10.1609\/aaai.v35i16.17664","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"1842_CR38","doi-asserted-by":"crossref","unstructured":"Xu Z, Liu R, Yang S, Chai Z, Yuan C (2023) Learning imbalanced data with vision transformers. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp 15793\u201315803","DOI":"10.1109\/CVPR52729.2023.01516"},{"key":"1842_CR39","doi-asserted-by":"crossref","unstructured":"Yun S, Han D, Oh SJ, Chun S, Choe J, Yoo Y (2019) Cutmix: regularization strategy to train strong classifiers with localizable features. In: Proceedings of the IEEE\/CVF international conference on computer vision. pp 6023\u20136032","DOI":"10.1109\/ICCV.2019.00612"},{"key":"1842_CR40","unstructured":"Zhang X, Tian Y, Xie L, Huang W, Dai Q, Ye Q, Tian Q (2023) Hivit: a simpler and more efficient design of hierarchical vision transformer. In: The eleventh international conference on learning representations"}],"container-title":["Complex & Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-025-01842-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s40747-025-01842-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-025-01842-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,29]],"date-time":"2025-04-29T10:36:07Z","timestamp":1745922967000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s40747-025-01842-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,17]]},"references-count":40,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,5]]}},"alternative-id":["1842"],"URL":"https:\/\/doi.org\/10.1007\/s40747-025-01842-8","relation":{},"ISSN":["2199-4536","2198-6053"],"issn-type":[{"value":"2199-4536","type":"print"},{"value":"2198-6053","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,17]]},"assertion":[{"value":"27 August 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 February 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 March 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"215"}}