{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,7]],"date-time":"2026-06-07T04:06:55Z","timestamp":1780805215464,"version":"3.54.1"},"reference-count":55,"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\/501100002322","name":"Coordination for the improvement of Higher Education Personnel","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002322","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003593","name":"National Council for Scientific and Technological Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003593","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001807","name":"State of Sao Paulo Research Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001807","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.neucom.2026.133852","type":"journal-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T07:08:16Z","timestamp":1777964896000},"page":"133852","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["VORTEX: Challenging CNNs at texture recognition by using vision transformers with orderless and randomized token encodings"],"prefix":"10.1016","volume":"693","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3986-7747","authenticated-orcid":false,"given":"Leonardo","family":"Scabini","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kallil M.","family":"Zielinski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emir","family":"Konuk","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ricardo T.","family":"Fares","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2490-180X","authenticated-orcid":false,"given":"Lucas C.","family":"Ribas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kevin","family":"Smith","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Odemir M.","family":"Bruno","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.133852_bib0005","doi-asserted-by":"crossref","first-page":"222","DOI":"10.1109\/RBME.2021.3115703","article-title":"Texture analysis and its applications in biomedical imaging: a survey","volume":"15","author":"Ghalati","year":"2021","journal-title":"IEEE Rev. Biomed. Eng."},{"issue":"1","key":"10.1016\/j.neucom.2026.133852_bib0010","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1007\/s11263-018-1125-z","article-title":"From BoW to CNN: two decades of texture representation for texture classification","volume":"127","author":"Liu","year":"2019","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.neucom.2026.133852_bib0015","series-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"11007","article-title":"Deep structure-revealed network for texture recognition","author":"Zhai","year":"2020"},{"key":"10.1016\/j.neucom.2026.133852_bib0020","doi-asserted-by":"crossref","first-page":"260","DOI":"10.1016\/j.ins.2020.09.058","article-title":"Analysis of activation maps through global pooling measurements for texture classification","volume":"555","author":"Condori","year":"2021","journal-title":"Inf. Sci."},{"key":"10.1016\/j.neucom.2026.133852_bib0025","series-title":"2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"5227","article-title":"Deep texture recognition via exploiting cross-layer statistical self-similarity\u2021","author":"Chen","year":"2021"},{"key":"10.1016\/j.neucom.2026.133852_bib0030","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2022.118223","article-title":"DFAEN: double-order knowledge fusion and attentional encoding network for texture recognition","volume":"209","author":"Yang","year":"2022","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.neucom.2026.133852_bib0035","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2024.111282","article-title":"A multilevel pooling scheme in convolutional neural networks for texture image recognition","volume":"152","author":"Lyra","year":"2024","journal-title":"Appl. Soft Comput."},{"key":"10.1016\/j.neucom.2026.133852_bib0040","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109802","article-title":"RADAM: texture recognition through randomized aggregated encoding of deep activation maps","author":"Scabini","year":"2023","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.neucom.2026.133852_bib0045","article-title":"Dual-branch network based on transformer for texture recognition","author":"Liu","year":"2024","journal-title":"Digit. Signal Process."},{"key":"10.1016\/j.neucom.2026.133852_bib0050","series-title":"2024 Asia-Pacific Conference on Image Processing, Electronics and Computers (IPEC)","first-page":"535","article-title":"HRNet: local-spatial feature fusion network for texture recognition","author":"Qiu","year":"2024"},{"key":"10.1016\/j.neucom.2026.133852_bib0055","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.122978","article-title":"Fractal pooling: a new strategy for texture recognition using convolutional neural networks","volume":"243","author":"Florindo","year":"2024","journal-title":"Expert Syst. Appl."},{"issue":"11","key":"10.1016\/j.neucom.2026.133852_bib0060","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"LeCun","year":"1998","journal-title":"Proc. IEEE"},{"issue":"6","key":"10.1016\/j.neucom.2026.133852_bib0065","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1145\/3065386","article-title":"Imagenet classification with deep convolutional neural networks","volume":"60","author":"Krizhevsky","year":"2017","journal-title":"Commun. ACM"},{"key":"10.1016\/j.neucom.2026.133852_bib0070","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1016\/j.ins.2019.11.042","article-title":"Spatio-spectral networks for color-texture analysis","volume":"515","author":"Scabini","year":"2020","journal-title":"Inf. Sci."},{"key":"10.1016\/j.neucom.2026.133852_bib0075","first-page":"1","article-title":"DGPDL: domain-guided prompt distribution learning for generalizable face anti-spoofing","author":"Liu","year":"2026","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2026.133852_bib0080","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"222","article-title":"CFPL-FAS: class free prompt learning for generalizable face anti-spoofing","author":"Liu","year":"2024"},{"key":"10.1016\/j.neucom.2026.133852_bib0085","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"ICLR"},{"issue":"10s","key":"10.1016\/j.neucom.2026.133852_bib0090","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3505244","article-title":"Transformers in vision: a survey","volume":"54","author":"Khan","year":"2022","journal-title":"ACM Comput. Surv."},{"issue":"9","key":"10.1016\/j.neucom.2026.133852_bib0095","doi-asserted-by":"crossref","first-page":"304","DOI":"10.3390\/jimaging11090304","article-title":"A comparative survey of vision transformers for feature extraction in texture analysis","volume":"11","author":"Scabini","year":"2025","journal-title":"J. Imaging"},{"issue":"6","key":"10.1016\/j.neucom.2026.133852_bib0100","doi-asserted-by":"crossref","first-page":"610","DOI":"10.1109\/TSMC.1973.4309314","article-title":"Textural features for image classification","volume":"SMC-3","author":"Haralick","year":"1973","journal-title":"IEEE Trans. Syst. Man Cybern."},{"issue":"8","key":"10.1016\/j.neucom.2026.133852_bib0105","doi-asserted-by":"crossref","first-page":"837","DOI":"10.1109\/34.531803","article-title":"Texture features for browsing and retrieval of image data","volume":"18","author":"Manjunath","year":"1996","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"7","key":"10.1016\/j.neucom.2026.133852_bib0110","doi-asserted-by":"crossref","first-page":"971","DOI":"10.1109\/TPAMI.2002.1017623","article-title":"Multiresolution gray-scale and rotation invariant texture classification with local binary patterns","volume":"24","author":"Ojala","year":"2002","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2026.133852_bib0115","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"3606","article-title":"Describing textures in the wild","author":"Cimpoi","year":"2014"},{"key":"10.1016\/j.neucom.2026.133852_bib0120","series-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS\u201917","first-page":"6000","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.neucom.2026.133852_bib0125","series-title":"2021 IEEE International Conference on Electro Information Technology (EIT)","first-page":"1","article-title":"Material texture recognition using ultrasonic images with transformer neural networks","author":"Zhang","year":"2021"},{"key":"10.1016\/j.neucom.2026.133852_bib0130","author":"Soleymani"},{"key":"10.1016\/j.neucom.2026.133852_bib0135","series-title":"2021 IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"548","article-title":"Pyramid vision transformer: a versatile backbone for dense prediction without convolutions","author":"Wang","year":"2021"},{"key":"10.1016\/j.neucom.2026.133852_bib0140","series-title":"2021 IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"9992","article-title":"Swin transformer: hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"issue":"21","key":"10.1016\/j.neucom.2026.133852_bib0145","doi-asserted-by":"crossref","first-page":"5379","DOI":"10.3390\/rs14215379","article-title":"MFATNet: multi-scale feature aggregation via transformer for remote sensing image change detection","volume":"14","author":"Mao","year":"2022","journal-title":"Remote Sens."},{"key":"10.1016\/j.neucom.2026.133852_bib0150","series-title":"2023 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","first-page":"4945","article-title":"Enriched CNN-transformer feature aggregation networks for super-resolution","author":"Yoo","year":"2023"},{"key":"10.1016\/j.neucom.2026.133852_bib0155","first-page":"1","article-title":"ViTALnet: anomaly on industrial textured surfaces with hybrid transformer","volume":"72","author":"Tao","year":"2023","journal-title":"IEEE Trans. Instrum. Meas."},{"issue":"1","key":"10.1016\/j.neucom.2026.133852_bib0160","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1007\/s00371-025-04209-9","article-title":"Hybrid CNN-transformer framework with dynamic feature fusion for enhanced passport background texture classification: M. Tian et al.","volume":"42","author":"Tian","year":"2026","journal-title":"Vis. Comput."},{"issue":"22","key":"10.1016\/j.neucom.2026.133852_bib0165","doi-asserted-by":"crossref","first-page":"4467","DOI":"10.3390\/electronics13224467","article-title":"Hybrid-DC: a hybrid framework using ResNet-50 and vision transformer for steel surface defect classification in the rolling process","volume":"13","author":"Jeong","year":"2024","journal-title":"Electronics"},{"key":"10.1016\/j.neucom.2026.133852_bib0170","series-title":"European Conference on Computer Vision","first-page":"516","article-title":"Deit III: revenge of the VIT","author":"Touvron","year":"2022"},{"key":"10.1016\/j.neucom.2026.133852_bib0175","first-page":"31","article-title":"Representational learning with ELMs for big data","volume":"28","author":"Kasun","year":"2013","journal-title":"IEEE Intell. Syst."},{"key":"10.1016\/j.neucom.2026.133852_bib0180","author":"Saxe"},{"key":"10.1016\/j.neucom.2026.133852_bib0185","series-title":"Proceedings of 16th International Conference on Pattern Recognition","article-title":"Outex - new framework for empirical evaluation of texture analysis algorithms","volume":"vol. 1","author":"Huovinen","year":"2002"},{"key":"10.1016\/j.neucom.2026.133852_bib0190","doi-asserted-by":"crossref","first-page":"784","DOI":"10.1167\/9.8.784","article-title":"Material perception: what can you see in a brief glance?","volume":"9","author":"Sharan","year":"2010","journal-title":"J. Vision"},{"key":"10.1016\/j.neucom.2026.133852_bib0195","series-title":"Tenth IEEE International Conference on Computer Vision (ICCV\u201905) Volume 1","first-page":"1597","article-title":"Class-specific material categorisation","volume":"vol. 2","author":"Caputo","year":"2005"},{"key":"10.1016\/j.neucom.2026.133852_bib0200","article-title":"Differential viewpoints for ground terrain material recognition","author":"Xue","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell. PP"},{"key":"10.1016\/j.neucom.2026.133852_bib0205","series-title":"2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","article-title":"Deep texture manifold for ground terrain recognition","author":"Xue","year":"2018"},{"key":"10.1016\/j.neucom.2026.133852_bib0210","series-title":"2009 IEEE Conference on Computer Vision and Pattern Recognition","first-page":"248","article-title":"Imagenet: a large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"10.1016\/j.neucom.2026.133852_bib0215","article-title":"How to train your ViT? Data, augmentation, and regularization in vision transformers","author":"Steiner","year":"2021","journal-title":"Trans. Mach. Learn. Res."},{"key":"10.1016\/j.neucom.2026.133852_bib0220","author":"Peng"},{"key":"10.1016\/j.neucom.2026.133852_bib0225","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"12954","article-title":"ViTamin: designing scalable vision models in the vision-language era","author":"Chen","year":"2024"},{"key":"10.1016\/j.neucom.2026.133852_bib0230","article-title":"Datacomp: in search of the next generation of multimodal datasets","volume":"36","author":"Gadre","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.133852_bib0235","article-title":"Openclip","author":"Ilharco","year":"2021","journal-title":"Zenodo"},{"key":"10.1016\/j.neucom.2026.133852_bib0240","series-title":"Thirty-Sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track","article-title":"LAION-5B: an open large-scale dataset for training next generation image-text models","author":"Schuhmann","year":"2022"},{"key":"10.1016\/j.neucom.2026.133852_bib0245","series-title":"Pattern Recognition and Neural Networks","author":"Ripley","year":"2007"},{"key":"10.1016\/j.neucom.2026.133852_bib0250","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1023\/A:1022627411411","article-title":"Support vector networks","volume":"20","author":"Cortes","year":"1995","journal-title":"Mach. Learn."},{"issue":"8","key":"10.1016\/j.neucom.2026.133852_bib0255","doi-asserted-by":"crossref","first-page":"5806","DOI":"10.1007\/s11263-025-02450-2","article-title":"Bamboo: building mega-scale vision dataset continually with human\u2013machine synergy","volume":"133","author":"Zhang","year":"2025","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.neucom.2026.133852_bib0260","series-title":"European Conference on Computer Vision","first-page":"428","article-title":"Multi-label cluster discrimination for visual representation learning","author":"An","year":"2025"},{"key":"10.1016\/j.neucom.2026.133852_bib0265","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.neucom.2026.133852_bib0270","author":"Gesmundo"},{"key":"10.1016\/j.neucom.2026.133852_bib0275","article-title":"DINOv2: learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"TMLR","ISSN":"https:\/\/id.crossref.org\/issn\/2835-8856","issn-type":"print"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S092523122601249X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S092523122601249X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T14:38:27Z","timestamp":1780670307000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S092523122601249X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":55,"alternative-id":["S092523122601249X"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133852","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"VORTEX: Challenging CNNs at texture recognition by using vision transformers with orderless and randomized token encodings","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133852","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"133852"}}