{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T20:31:36Z","timestamp":1789245096823,"version":"build-2803163510"},"reference-count":45,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100017533","name":"Ho Chi Minh City University of Technology and Engineering","doi-asserted-by":"publisher","award":["T2026-10"],"award-info":[{"award-number":["T2026-10"]}],"id":[{"id":"10.13039\/100017533","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.neunet.2026.108939","type":"journal-article","created":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:50:07Z","timestamp":1775231407000},"page":"108939","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["Dilated multi-Layer perceptron mixer for faster neural networks"],"prefix":"10.1016","volume":"201","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7554-1707","authenticated-orcid":false,"given":"Van-Dung","family":"Hoang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7411-0697","authenticated-orcid":false,"given":"Xuan-Thuy","family":"Vo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8317-6092","authenticated-orcid":false,"given":"Kang-Hyun","family":"Jo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"12","key":"10.1016\/j.neunet.2026.108939_bib0001","doi-asserted-by":"crossref","first-page":"14284","DOI":"10.1109\/TPAMI.2023.3303397","article-title":"Cyclemlp: A mlp-like architecture for dense visual predictions","volume":"45","author":"Chen","year":"2023","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.108939_bib0002","series-title":"International conference on learning representations","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021"},{"key":"10.1016\/j.neunet.2026.108939_bib0003","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"826","article-title":"Hire-mlp: Vision mlp via hierarchical rearrangement","author":"Guo","year":"2022"},{"key":"10.1016\/j.neunet.2026.108939_bib0004","series-title":"Proceedings of the IEEE international conference on computer vision","first-page":"2961","article-title":"Mask r-cnn","author":"He","year":"2017"},{"key":"10.1016\/j.neunet.2026.108939_bib0005","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.neunet.2026.108939_bib0006","first-page":"1","article-title":"Powering AI-driven car damage identification based on veHIDE dataset","author":"Hoang","year":"2024","journal-title":"Journal of Information and Telecommunication"},{"issue":"4","key":"10.1016\/j.neunet.2026.108939_bib0007","doi-asserted-by":"crossref","first-page":"1923","DOI":"10.1109\/TIP.2018.2878958","article-title":"An augmented linear mixing model to address spectral variability for hyperspectral unmixing","volume":"28","author":"Hong","year":"2018","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.neunet.2026.108939_bib0008","doi-asserted-by":"crossref","DOI":"10.1016\/j.rse.2023.113856","article-title":"Cross-city matters: A multimodal remote sensing benchmark dataset for cross-city semantic segmentation using high-resolution domain adaptation networks","volume":"299","author":"Hong","year":"2023","journal-title":"Remote Sensing of Environment"},{"key":"10.1016\/j.neunet.2026.108939_bib0009","article-title":"SpectralGPT: Spectral remote sensing foundation model","author":"Hong","year":"2024","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.108939_bib0010","unstructured":"Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., & Adam, H. (2017). Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv: 1704.04861."},{"key":"10.1016\/j.neunet.2026.108939_bib0011","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106568","article-title":"Hdconv: Heterogeneous kernel-based dilated convolutions","volume":"179","author":"Hu","year":"2024","journal-title":"Neural Networks"},{"issue":"2","key":"10.1016\/j.neunet.2026.108939_bib0012","doi-asserted-by":"crossref","first-page":"2200","DOI":"10.1109\/TII.2022.3199228","article-title":"Masked swin transformer unet for industrial anomaly detection","volume":"19","author":"Jiang","year":"2023","journal-title":"IEEE Transactions on Industrial Informatics"},{"key":"10.1016\/j.neunet.2026.108939_bib0013","series-title":"Proceedings of the IEEE international conference on computer vision workshops","first-page":"554","article-title":"3D object representations for fine-grained categorization","author":"Krause","year":"2013"},{"key":"10.1016\/j.neunet.2026.108939_bib0014","unstructured":"Krizhevsky, A., Hinton, G. et al. (2009). Learning multiple layers of features from tiny images."},{"key":"10.1016\/j.neunet.2026.108939_bib0015","series-title":"Ijcai","first-page":"999","article-title":"RaMLP: Vision MLP via region-aware mixing","author":"Lai","year":"2023"},{"key":"10.1016\/j.neunet.2026.108939_bib0016","series-title":"International conference on learning representations (ICLR)","article-title":"As-mlp: An axial shifted mlp architecture for vision","author":"Lian","year":"2022"},{"key":"10.1016\/j.neunet.2026.108939_bib0017","series-title":"Proceedings of the IEEE international conference on computer vision","first-page":"2980","article-title":"Focal loss for dense object detection","author":"Lin","year":"2017"},{"key":"10.1016\/j.neunet.2026.108939_bib0018","first-page":"9204","article-title":"Pay attention to mlps","volume":"34","author":"Liu","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108939_bib0019","series-title":"Computer vision\u2013ECCV 2016: 14th european conference, amsterdam, the netherlands, october 11\u201314, 2016, proceedings, part i 14","first-page":"21","article-title":"Ssd: Single shot multibox detector","author":"Liu","year":"2016"},{"key":"10.1016\/j.neunet.2026.108939_bib0020","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"10012","article-title":"Swin transformer: Hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"key":"10.1016\/j.neunet.2026.108939_bib0021","series-title":"International conference on learning representations","article-title":"Mobilevit: Light-weight, general-purpose, and mobile-friendly vision transformer","author":"Mehta","year":"2022"},{"key":"10.1016\/j.neunet.2026.108939_bib0022","article-title":"Separable self-attention for mobile vision transformers","author":"Mehta","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"issue":"7","key":"10.1016\/j.neunet.2026.108939_bib0023","doi-asserted-by":"crossref","first-page":"8104","DOI":"10.1109\/TII.2022.3217120","article-title":"Joint EEG feature transfer and semisupervised cross-subject emotion recognition","volume":"19","author":"Peng","year":"2023","journal-title":"IEEE Transactions on Industrial Informatics"},{"key":"10.1016\/j.neunet.2026.108939_bib0024","first-page":"1","article-title":"Chest x-ray image classification using transfer learning and hyperparameter customization for lung disease diagnosis","author":"Pham","year":"2024","journal-title":"Journal of Information and Telecommunication"},{"issue":"1","key":"10.1016\/j.neunet.2026.108939_bib0025","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-021-96707-8","article-title":"Ai outperformed every dermatologist in dermoscopic melanoma diagnosis, using an optimized deep-cnn architecture with custom mini-batch logic and loss function","volume":"11","author":"Pham","year":"2021","journal-title":"Scientific Reports"},{"key":"10.1016\/j.neunet.2026.108939_bib0026","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"4510","article-title":"Mobilenetv2: Inverted residuals and linear bottlenecks","author":"Sandler","year":"2018"},{"issue":"3","key":"10.1016\/j.neunet.2026.108939_bib0027","doi-asserted-by":"crossref","first-page":"1327","DOI":"10.1007\/s00371-023-02851-9","article-title":"Maim: A mixer mlp architecture for image matching","volume":"40","author":"Shen","year":"2024","journal-title":"The Visual Computer"},{"key":"10.1016\/j.neunet.2026.108939_bib0028","unstructured":"Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv: 1409.1556."},{"key":"10.1016\/j.neunet.2026.108939_bib0029","first-page":"24261","article-title":"Mlp-mixer: An all-mlp architecture for vision","volume":"34","author":"Tolstikhin","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"4","key":"10.1016\/j.neunet.2026.108939_bib0030","doi-asserted-by":"crossref","first-page":"5314","DOI":"10.1109\/TPAMI.2022.3206148","article-title":"Resmlp: Feedforward networks for image classification with data-efficient training","volume":"45","author":"Touvron","year":"2022","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.108939_bib0031","series-title":"International conference on machine learning","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","author":"Touvron","year":"2021"},{"key":"10.1016\/j.neunet.2026.108939_bib0032","series-title":"European conference on computer vision","first-page":"459","article-title":"Maxvit: Multi-axis vision transformer","author":"Tu","year":"2022"},{"key":"10.1016\/j.neunet.2026.108939_bib0033","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.129166","article-title":"A compact version of efficientnet for skin disease diagnosis application","volume":"620","author":"Van Thanh","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neunet.2026.108939_bib0034","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"568","article-title":"Pyramid vision transformer: A versatile backbone for dense prediction without convolutions","author":"Wang","year":"2021"},{"issue":"3","key":"10.1016\/j.neunet.2026.108939_bib0035","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1007\/s41095-022-0274-8","article-title":"Pvt v2: Improved baselines with pyramid vision transformer","volume":"8","author":"Wang","year":"2022","journal-title":"Computational Visual Media"},{"key":"10.1016\/j.neunet.2026.108939_bib0036","series-title":"International conference on machine learning","first-page":"22691","article-title":"Dynamixer: A vision mlp architecture with dynamic mixing","author":"Wang","year":"2022"},{"key":"10.1016\/j.neunet.2026.108939_bib0037","doi-asserted-by":"crossref","first-page":"364","DOI":"10.1109\/TIP.2022.3228497","article-title":"Uiu-net: U-net in u-net for infrared small object detection","volume":"32","author":"Wu","year":"2022","journal-title":"IEEE Transactions on Image Processing"},{"issue":"1","key":"10.1016\/j.neunet.2026.108939_bib0038","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1109\/TII.2023.3256400","article-title":"Cross-modal fusion convolutional neural networks with online soft-label training strategy for mechanical fault diagnosis","volume":"20","author":"Xu","year":"2024","journal-title":"IEEE Transactions on Industrial Informatics"},{"key":"10.1016\/j.neunet.2026.108939_bib0039","doi-asserted-by":"crossref","DOI":"10.1109\/TII.2024.3413322","article-title":"Prior normality prompt transformer for multi-class industrial image anomaly detection","author":"Yao","year":"2024","journal-title":"IEEE Transactions on Industrial Informatics"},{"key":"10.1016\/j.neunet.2026.108939_bib0040","series-title":"Proceedings of the IEEE\/CVF winter conference on applications of computer vision","first-page":"297","article-title":"S2-Mlp: Spatial-shift mlp architecture for vision","author":"Yu","year":"2022"},{"key":"10.1016\/j.neunet.2026.108939_bib0041","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"10819","article-title":"Metaformer is actually what you need for vision","author":"Yu","year":"2022"},{"key":"10.1016\/j.neunet.2026.108939_bib0042","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2022.109792","article-title":"Multi-scale MLP-mixer for image classification","volume":"258","author":"Zhang","year":"2022","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.neunet.2026.108939_bib0043","article-title":"Spatial-wise dynamic distillation for MLP-like efficient visual fault detection of freight trains","author":"Zhang","year":"2024","journal-title":"IEEE Transactions on Industrial Electronics"},{"key":"10.1016\/j.neunet.2026.108939_bib0044","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106141","article-title":"Msdcnn: A multiscale dilated convolution neural network for fine-grained 3d shape classification","volume":"172","author":"Zhou","year":"2024","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.108939_bib0045","article-title":"Dimensional transformation mixer for ultra-high-definition industrial camera dehazing","author":"Zhuang","year":"2024","journal-title":"IEEE Transactions on Industrial Informatics"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026004004?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026004004?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T12:31:53Z","timestamp":1787920313000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026004004"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":45,"alternative-id":["S0893608026004004"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108939","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Dilated multi-Layer perceptron mixer for faster neural networks","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108939","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"108939"}}