{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T06:25:29Z","timestamp":1774679129584,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":31,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819698622","type":"print"},{"value":"9789819698639","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-96-9863-9_38","type":"book-chapter","created":{"date-parts":[[2025,7,23]],"date-time":"2025-07-23T14:38:39Z","timestamp":1753281519000},"page":"448-459","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["WSFFormer: LightWeight Wavelet Spatial-Frequency Vision Transformer for Visual Representation Learning"],"prefix":"10.1007","author":[{"given":"Jialin","family":"Guo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min","family":"Zhi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanjun","family":"Yin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiaozhi","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuxin","family":"Xia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,7,24]]},"reference":[{"key":"38_CR1","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"38_CR2","unstructured":"Dosovitskiy, A., et al.: An image is worth 16 \u00d7 16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"38_CR3","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"38_CR4","first-page":"980","volume":"34","author":"Y Rao","year":"2021","unstructured":"Rao, Y., Zhao, W., Zhu, Z., Lu, J., Zhou, J.: Global filter networks for image classification. Adv. Neural. Inf. Process. Syst. 34, 980\u2013993 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"38_CR5","doi-asserted-by":"crossref","unstructured":"Yun, S., Ro, Y.: SHViT: single-head vision transformer with memory efficient macro design. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5756\u20135767 (2024)","DOI":"10.1109\/CVPR52733.2024.00550"},{"key":"38_CR6","doi-asserted-by":"crossref","unstructured":"Lou, M., Zhang, S., Zhou, H.Y., Yang, S., Wu, C., Yu, Y.: TransXNet: learning both global and local dynamics with a dual dynamic token mixer for visual recognition. IEEE Trans. Neural Netw. Learn. Syst. (2025)","DOI":"10.1109\/TNNLS.2025.3550979"},{"key":"38_CR7","unstructured":"Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images (2009)"},{"key":"38_CR8","doi-asserted-by":"crossref","unstructured":"Yang, Y., Yuan, G., Li, J.: SFFNet: a wavelet-based spatial and frequency domain fusion network for remote sensing segmentation. IEEE Trans. Geoscience Remote Sens. (2024)","DOI":"10.1109\/TGRS.2024.3427370"},{"key":"38_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106378","volume":"177","author":"J Li","year":"2024","unstructured":"Li, J., Cheng, B., Chen, Y., Gao, G., Shi, J., Zeng, T.: EWT: efficient wavelet-transformer for single image denoising. Neural Netw. 177, 106378 (2024)","journal-title":"Neural Netw."},{"key":"38_CR10","doi-asserted-by":"crossref","unstructured":"Roy, A., Sarkar, S., Ghosal, S., Kaplun, D., Lyanova, A., Sarkar, R.: A wavelet guided attention module for skin cancer classification with gradient-based feature fusion. In: 2024 IEEE International Symposium on Biomedical Imaging (ISBI), pp. 1\u20134 (2024)","DOI":"10.1109\/ISBI56570.2024.10635704"},{"issue":"3","key":"38_CR11","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1007\/s41095-022-0274-8","volume":"8","author":"W Wang","year":"2022","unstructured":"Wang, W., et al.: PVT v2: improved baselines with pyramid vision transformer. Comput. Vis. Media 8(3), 415\u2013424 (2022)","journal-title":"Comput. Vis. Media"},{"key":"38_CR12","doi-asserted-by":"crossref","unstructured":"Tan, W., Geng, Y., Xie, X.: FMViT: a multiple-frequency mixing vision transformer. In: European Conference on Artificial Intelligence (ECAI) 2024, pp. 97\u2013104. IOS Press (2024)","DOI":"10.3233\/FAIA240476"},{"key":"38_CR13","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. In: International Conference on Machine Learning, pp. 10347\u201310357. PMLR (2021)"},{"key":"38_CR14","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412 (2017)"},{"key":"38_CR15","doi-asserted-by":"crossref","unstructured":"Yun, S., Han, D., Oh, S.J., Chun, S., Choe, J., Yoo, Y.: CutMix: regularization strategy to train strong classifiers with localizable features. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6023\u20136032 (2019)","DOI":"10.1109\/ICCV.2019.00612"},{"key":"38_CR16","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Mane, D., Vasudevan, V., Le, Q.V.: AutoAugment: learning augmentation strategies from data. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 113\u2013123 (2019)","DOI":"10.1109\/CVPR.2019.00020"},{"key":"38_CR17","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"38_CR18","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: A deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"38_CR19","doi-asserted-by":"crossref","unstructured":"Zagoruyko, S., Komodakis, N.: Wide residual networks. arXiv preprint arXiv:1605.07146 (2016)","DOI":"10.5244\/C.30.87"},{"key":"38_CR20","unstructured":"Larsson, G., Maire, M., Shakhnarovich, G.: FractalNet: ultra-deep neural networks without residuals. arXiv preprint arXiv:1605.07648 (2016)"},{"key":"38_CR21","doi-asserted-by":"crossref","unstructured":"Han, D., Kim, J., Kim, J.: Deep pyramidal residual networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5927\u20135935 (2017)","DOI":"10.1109\/CVPR.2017.668"},{"key":"38_CR22","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Pyramid vision transformer: a versatile backbone for dense prediction without convolutions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 568\u2013578 (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"38_CR23","doi-asserted-by":"crossref","unstructured":"Guo, J., et al.: CMT: convolutional neural networks meet vision transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12175\u201312185 (2022)","DOI":"10.1109\/CVPR52688.2022.01186"},{"key":"38_CR24","doi-asserted-by":"crossref","unstructured":"d\u2019Ascoli, S., Touvron, H., Leavitt, M.L., Morcos, A.S., Biroli, G. Sagun, L.: ConViT: improving vision transformers with soft convolutional inductive biases. In: International Conference on Machine Learning, pp. 2286\u20132296 (2021)","DOI":"10.1088\/1742-5468\/ac9830"},{"key":"38_CR25","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1492\u20131500 (2017)","DOI":"10.1109\/CVPR.2017.634"},{"key":"38_CR26","first-page":"3965","volume":"34","author":"Z Dai","year":"2021","unstructured":"Dai, Z., Liu, H., Le, Q.V., Tan, M.: CoAtNet: marrying convolution and attention for all data sizes. Adv. Neural. Inf. Process. Syst. 34, 3965\u20133977 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"38_CR27","doi-asserted-by":"crossref","unstructured":"Graham, B., et al.: LeViT: a vision transformer in VonvNet\u2019s clothing for faster inference. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12259\u201312269 (2021)","DOI":"10.1109\/ICCV48922.2021.01204"},{"key":"38_CR28","doi-asserted-by":"crossref","unstructured":"Kong, L., Dong, J., Ge, J., Li, M., Pan, J.: Efficient frequency domain-based transformers for high-quality image deblurring. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5886\u20135895 (2023)","DOI":"10.1109\/CVPR52729.2023.00570"},{"key":"38_CR29","doi-asserted-by":"crossref","unstructured":"Peng, Z., et al.: Conformer: Local features coupling global representations for visual recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 367\u2013376 (2021)","DOI":"10.1109\/ICCV48922.2021.00042"},{"key":"38_CR30","unstructured":"Dauphin, Y.N., Fan, A., Auli, M., Grangier, D.: Language modeling with gated convolutional networks. In: International Conference on Machine Learning, pp. 933\u2013941. PMLR (2017)"},{"key":"38_CR31","unstructured":"Shazeer, N.: GLU variants improve transformer. arXiv preprint arXiv:2002.05202 (2020)"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-9863-9_38","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T04:10:41Z","timestamp":1774671041000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-9863-9_38"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819698622","9789819698639"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-9863-9_38","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"24 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ningbo","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/icg\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}