{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T00:12:10Z","timestamp":1789085530804,"version":"build-2803163510"},"reference-count":64,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,7]],"date-time":"2026-06-07T00:00:00Z","timestamp":1780790400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002241","name":"Japan Science and Technology Agency","doi-asserted-by":"publisher","award":["JPMJSP2128"],"award-info":[{"award-number":["JPMJSP2128"]}],"id":[{"id":"10.13039\/501100002241","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["24K15018"],"award-info":[{"award-number":["24K15018"]}],"id":[{"id":"10.13039\/501100001691","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":[[2026,12]]},"DOI":"10.1016\/j.neunet.2026.109234","type":"journal-article","created":{"date-parts":[[2026,6,7]],"date-time":"2026-06-07T14:29:19Z","timestamp":1780842559000},"page":"109234","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["FracNeXt: Enhancing visual representation learning in sequence models with fractal wavelets"],"prefix":"10.1016","volume":"204","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-1009-8220","authenticated-orcid":false,"given":"Pengfeng","family":"Lu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1496-2417","authenticated-orcid":false,"given":"Sei-ichiro","family":"Kamata","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7928-0753","authenticated-orcid":false,"given":"Mengyunqiu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.109234_bib0001","series-title":"2023\u202fIEEE\/CVF International conference on computer vision (ICCV)","first-page":"5762","article-title":"Fastvit: A fast hybrid vision transformer using structural reparameterization","author":"Anasosalu Vasu","year":"2023"},{"issue":"1","key":"10.1016\/j.neunet.2026.109234_bib0002","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1109\/83.481666","article-title":"Image compression using wavelet transform and multiresolution decomposition","volume":"5","author":"Averbuch","year":"1996","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.neunet.2026.109234_bib0003","unstructured":"Bagnall, A., Dau, H. A., Lines, J., Flynn, M., Large, J., Bostrom, A., Southam, P., & Keogh, E. (2018). The UEA multivariate time series classification archive. arXiv: 1811.00075."},{"key":"10.1016\/j.neunet.2026.109234_bib0004","series-title":"International conference on machine learning","first-page":"342","article-title":"The shattered gradients problem: If resnets are the answer, then what is the question?","author":"Balduzzi","year":"2017"},{"issue":"4","key":"10.1016\/j.neunet.2026.109234_bib0005","doi-asserted-by":"crossref","first-page":"1408","DOI":"10.1137\/S1064827500383123","article-title":"Wavelet algorithms for high-resolution image reconstruction","volume":"24","author":"Chan","year":"2003","journal-title":"SIAM Journal on Scientific Computing"},{"key":"10.1016\/j.neunet.2026.109234_bib0006","unstructured":"Chen, K., Wang, J., Pang, J., Cao, Y., Xiong, Y., Li, X., Sun, S., Feng, W., Liu, Z., Xu, J., Zhang, Z., Cheng, D., Zhu, C., Cheng, T., Zhao, Q., Li, B., Lu, X., Zhu, R., Wu, Y., Dai, J., Wang, J., Shi, J., Ouyang, W., Loy, C. C., & Lin, D. (2019). MMDetection: Open mmlab detection toolbox and benchmark. arXiv: 1906.07155."},{"key":"10.1016\/j.neunet.2026.109234_bib0007","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1016\/j.cviu.2017.01.006","article-title":"Enhancing textural differences using wavelet-based texture characteristics morphological component analysis: A preprocessing method for improving image segmentation","volume":"158","author":"Chi","year":"2017","journal-title":"Computer Vision and Image Understanding"},{"key":"10.1016\/j.neunet.2026.109234_bib0008","unstructured":"Clanuwat, T., Bober-Irizar, M., Kitamoto, A., Lamb, A., Yamamoto, K., & Ha, D. (2018). Deep learning for classical Japanese literature. arXiv: 1812.01718."},{"key":"10.1016\/j.neunet.2026.109234_bib0009","unstructured":"C. for Open Data in the Humanities (CODH) (2019). Kuzushiji dataset. http:\/\/codh.rois.ac.jp\/char-shape\/book\/."},{"key":"10.1016\/j.neunet.2026.109234_bib0010","unstructured":"Dagli, R. (2023). Astroformer: More data might not be all you need for classification. arXiv: 2304.05350."},{"key":"10.1016\/j.neunet.2026.109234_bib0011","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"13733","article-title":"Repvgg: Making vgg-style convnets great again","author":"Ding","year":"2021"},{"key":"10.1016\/j.neunet.2026.109234_bib0012","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S. et al. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv: 2010.11929."},{"issue":"1","key":"10.1016\/j.neunet.2026.109234_bib0013","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1007\/s11263-006-8894-5","article-title":"Image analysis and reconstruction using a wavelet transform constructed from a reducible representation of the euclidean motion group","volume":"72","author":"Duits","year":"2007","journal-title":"International Journal of Computer Vision"},{"issue":"2","key":"10.1016\/j.neunet.2026.109234_bib0014","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","article-title":"The pascal visual object classes (voc) challenge","volume":"88","author":"Everingham","year":"2010","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.neunet.2026.109234_bib0015","series-title":"International conference on machine learning","first-page":"7616","article-title":"It\u2019s raw! audio generation with state-space models","author":"Goel","year":"2022"},{"key":"10.1016\/j.neunet.2026.109234_bib0016","series-title":"Digital image processing","author":"Gonzalez","year":"2018"},{"key":"10.1016\/j.neunet.2026.109234_bib0017","unstructured":"Gu, A., & Dao, T. (2023). Mamba: Linear-time sequence modeling with selective state spaces. arXiv: 2312.00752."},{"key":"10.1016\/j.neunet.2026.109234_bib0018","series-title":"International conference on learning representations","article-title":"Efficiently modeling long sequences with structured state spaces","author":"Gu","year":"2022"},{"key":"10.1016\/j.neunet.2026.109234_bib0019","series-title":"Advances in neural information processing systems","article-title":"Combining recurrent, convolutional, and continuous-time models with linear state space layers","author":"Gu","year":"2021"},{"key":"10.1016\/j.neunet.2026.109234_bib0020","doi-asserted-by":"crossref","first-page":"58869","DOI":"10.1109\/ACCESS.2022.3179517","article-title":"A review of wavelet analysis and its applications: Challenges and opportunities","volume":"10","author":"Guo","year":"2022","journal-title":"IEEE Access"},{"key":"10.1016\/j.neunet.2026.109234_bib0021","unstructured":"Gupta, S., & Tan, M. (2019). Efficientnet-edgeTPU: Creating accelerator-optimized neural networks with autoML. https:\/\/ai.googleblog.com\/2019\/08\/efficientnet-edgetpu-creating.html."},{"key":"10.1016\/j.neunet.2026.109234_bib0022","series-title":"2016\u202fIEEE Conference on computer vision and pattern recognition (CVPR)","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.neunet.2026.109234_bib0023","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: 1704.04861."},{"key":"10.1016\/j.neunet.2026.109234_bib0024","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"7132","article-title":"Squeeze-and-excitation networks","author":"Hu","year":"2018"},{"issue":"6","key":"10.1016\/j.neunet.2026.109234_bib0025","doi-asserted-by":"crossref","first-page":"1936","DOI":"10.1007\/s10618-020-00710-y","article-title":"Inceptiontime: Finding alexnet for time series classification","volume":"34","author":"Ismail Fawaz","year":"2020","journal-title":"Data Mining and Knowledge Discovery"},{"key":"10.1016\/j.neunet.2026.109234_bib0026","unstructured":"Krizhevsky, A. (2009). Learning multiple layers of features from tiny images. University of Toronto."},{"issue":"3","key":"10.1016\/j.neunet.2026.109234_bib0027","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1007\/s42979-020-00186-z","article-title":"Kuronet: Regularized residual u-nets for end-to-end kuzushiji character recognition","volume":"1","author":"Lamb","year":"2020","journal-title":"SN Computer Science"},{"key":"10.1016\/j.neunet.2026.109234_bib0028","unstructured":"Larsson, G., Maire, M., & Shakhnarovich, G. (2017). Fractalnet: Ultra-deep neural networks without residuals. arXiv: 1605.07648."},{"key":"10.1016\/j.neunet.2026.109234_bib0029","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"7287","article-title":"Mpvit: Multi-path vision transformer for dense prediction","author":"Lee","year":"2022"},{"key":"10.1016\/j.neunet.2026.109234_bib0030","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"3243","article-title":"Flow guided recurrent neural encoder for video salient object detection","author":"Li","year":"2018"},{"key":"10.1016\/j.neunet.2026.109234_bib0031","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106378","article-title":"Ewt: Efficient wavelet-transformer for single image denoising","volume":"177","author":"Li","year":"2024","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109234_bib0032","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.2026.109234_bib0033","series-title":"Computer vision \u2013 ECCV 2014","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.neunet.2026.109234_bib0034","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106577","article-title":"Fpwt: Filter pruning via wavelet transform for cnns","volume":"179","author":"Liu","year":"2024","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109234_bib0035","doi-asserted-by":"crossref","first-page":"103031","DOI":"10.52202\/079017-3273","article-title":"Vmamba: Visual state space model","volume":"37","author":"Liu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109234_bib0036","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"12009","article-title":"Swin transformer v2: Scaling up capacity and resolution","author":"Liu","year":"2022"},{"key":"10.1016\/j.neunet.2026.109234_bib0037","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision (ICCV)","first-page":"10012","article-title":"Swin transformer: Hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"key":"10.1016\/j.neunet.2026.109234_bib0038","series-title":"2022\u202fIEEE\/CVF Conference on computer vision and pattern recognition (CVPR)","first-page":"11966","article-title":"A convnet for the 2020s","author":"Liu","year":"2022"},{"key":"10.1016\/j.neunet.2026.109234_bib0039","series-title":"International conference on learning representations","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019"},{"key":"10.1016\/j.neunet.2026.109234_bib0040","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2026.133396","article-title":"Fnwp: A fractal network with wavelet propagation for robust deep learning","volume":"681","author":"Lu","year":"2026","journal-title":"Neurocomputing"},{"issue":"9","key":"10.1016\/j.neunet.2026.109234_bib0041","doi-asserted-by":"crossref","first-page":"5961","DOI":"10.1109\/TNNLS.2021.3131813","article-title":"Why is everyone training very deep neural network with skip connections?","volume":"34","author":"Oyedotun","year":"2022","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.neunet.2026.109234_bib0042","series-title":"The tenth international conference on learning representations, ICLR 2022, Virtual Event, April 25\u201329, 2022","article-title":"How do vision transformers work?","author":"Park","year":"2022"},{"key":"10.1016\/j.neunet.2026.109234_bib0043","series-title":"European conference on computer vision","first-page":"78","article-title":"Mobilenetv4: Universal models for the mobile ecosystem","author":"Qin","year":"2024"},{"issue":"3","key":"10.1016\/j.neunet.2026.109234_bib0044","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"ImageNet large scale visual recognition challenge","volume":"115","author":"Russakovsky","year":"2015","journal-title":"International Journal of Computer Vision (IJCV)"},{"key":"10.1016\/j.neunet.2026.109234_bib0045","series-title":"2022\u202fIEEE International conference on big data (big data)","first-page":"1107","article-title":"Wavenets: Wavelet channel attention networks","author":"Salman","year":"2022"},{"key":"10.1016\/j.neunet.2026.109234_bib0046","series-title":"Icassp 2023-2023 IEEE international conference on acoustics, speech and signal processing (icassp)","first-page":"1","article-title":"Diagonal state space augmented transformers for speech recognition","author":"Saon","year":"2023"},{"key":"10.1016\/j.neunet.2026.109234_bib0047","series-title":"International conference on machine learning","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","author":"Tan","year":"2019"},{"key":"10.1016\/j.neunet.2026.109234_bib0048","series-title":"Advances in neural information processing systems","article-title":"Attention is all you need","volume":"Vol. 30","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.neunet.2026.109234_bib0049","first-page":"550","article-title":"Residual networks behave like ensembles of relatively shallow networks","volume":"29","author":"Veit","year":"2016","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109234_bib0050","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"5277","article-title":"Rvos: End-to-end recurrent network for video object segmentation","author":"Ventura","year":"2019"},{"issue":"5","key":"10.1016\/j.neunet.2026.109234_bib0051","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1109\/79.952805","article-title":"Wavelets, approximation, and compression","volume":"18","author":"Vetterli","year":"2001","journal-title":"IEEE Signal Processing Magazine"},{"key":"10.1016\/j.neunet.2026.109234_bib0052","doi-asserted-by":"crossref","DOI":"10.7717\/peerj.453","article-title":"Scikit-image: Image processing in Python","volume":"2","author":"Van der Walt","year":"2014","journal-title":"PeerJ"},{"key":"10.1016\/j.neunet.2026.109234_bib0053","series-title":"Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining","first-page":"2437","article-title":"Multilevel wavelet decomposition network for interpretable time series analysis","author":"Wang","year":"2018"},{"key":"10.1016\/j.neunet.2026.109234_bib0054","series-title":"2021\u202fIEEE\/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"},{"issue":"3","key":"10.1016\/j.neunet.2026.109234_bib0055","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.2026.109234_bib0056","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"16133","article-title":"Convnext v2: Co-designing and scaling convnets with masked autoencoders","author":"Woo","year":"2023"},{"key":"10.1016\/j.neunet.2026.109234_bib0057","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109819","article-title":"Haar wavelet downsampling: A simple but effective downsampling module for semantic segmentation","volume":"143","author":"Xu","year":"2023","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.neunet.2026.109234_bib0058","first-page":"1305","article-title":"Condconv: Conditionally parameterized convolutions for efficient inference","volume":"32","author":"Yang","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109234_bib0059","first-page":"30008","article-title":"Focal attention for long-range interactions in vision transformers","volume":"34","author":"Yang","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109234_bib0060","series-title":"Proceedings of the computer vision and pattern recognition conference","first-page":"4484","article-title":"Mambaout: Do we really need mamba for vision?","author":"Yu","year":"2025"},{"key":"10.1016\/j.neunet.2026.109234_bib0061","doi-asserted-by":"crossref","first-page":"162","DOI":"10.1016\/j.neunet.2023.07.005","article-title":"A super-resolution network for medical imaging via transformation analysis of wavelet multi-resolution","volume":"166","author":"Yu","year":"2023","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109234_bib0062","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"6023","article-title":"Cutmix: Regularization strategy to train strong classifiers with localizable features","author":"Yun","year":"2019"},{"key":"10.1016\/j.neunet.2026.109234_bib0063","series-title":"Proceedings of the 27th ACM SIGKDD conference on knowledge discovery & data mining","first-page":"2114","article-title":"A transformer-based framework for multivariate time series representation learning","author":"Zerveas","year":"2021"},{"key":"10.1016\/j.neunet.2026.109234_bib0064","series-title":"Proceedings of the 41st international conference on machine learning","article-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","author":"Zhu","year":"2024"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026006957?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026006957?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T23:45:40Z","timestamp":1789083940000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026006957"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":64,"alternative-id":["S0893608026006957"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109234","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"FracNeXt: Enhancing visual representation learning in sequence models with fractal wavelets","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109234","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"109234"}}