{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,18]],"date-time":"2026-01-18T20:31:03Z","timestamp":1768768263137,"version":"3.49.0"},"publisher-location":"Cham","reference-count":57,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031442094","type":"print"},{"value":"9783031442100","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-44210-0_36","type":"book-chapter","created":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T08:02:34Z","timestamp":1695283354000},"page":"446-456","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["MC-MLP: A Multiple Coordinate Frames MLP-Like Architecture for Vision"],"prefix":"10.1007","author":[{"given":"Zhimin","family":"Zhu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianguo","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tong","family":"Mu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuliang","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengyu","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,9,22]]},"reference":[{"key":"36_CR1","doi-asserted-by":"crossref","unstructured":"Ahmed, N., Rao, K.R., Bars, R., et al.: Orthogonal transform for digital signal processing. In: ICASSP (1976)","DOI":"10.1007\/978-3-642-45450-9"},{"key":"36_CR2","unstructured":"Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images (2009)"},{"key":"36_CR3","unstructured":"Dosovitskiy, A., et al.: An image is Worth 16\u00d716 words: transformers for image recognition at scale. arXiv:2010.11929 (2020)"},{"key":"36_CR4","unstructured":"Wu, B., et al.: Visual transformers: token-based image representation and processing for computer vision. arXiv:2006.03677 (2020)"},{"key":"36_CR5","unstructured":"Cheng, B., Schwing, A.G., Kirillov, A.: Per-pixel classification is not all you need for semantic segmentation. In: NIPS (2021)"},{"key":"36_CR6","doi-asserted-by":"crossref","unstructured":"Chen, S., (The University of Hong Kong, Hong Kong), Xie, E., Ge, C., Chen, R., Liang, D., Luo: CYCLEMLP: a MLP-like architecture for dense prediction. In: ICLR (2022)","DOI":"10.1109\/TPAMI.2023.3303397"},{"key":"36_CR7","unstructured":"Hendrycks, D., Gimpel, K.: Gaussian Error Linear Units (GELUs). arXiv:1606.08415 (2016)"},{"key":"36_CR8","doi-asserted-by":"crossref","unstructured":"Reisis, D., Vlassopoulos, N.: Conflict-free parallel memory accessing techniques for FFT architectures. In: IEEE Transactions on Circuits and Systems I: Regular Papers, pp. 3438\u20133447 (2008)","DOI":"10.1109\/TCSI.2008.924889"},{"key":"36_CR9","doi-asserted-by":"crossref","unstructured":"d\u2019Ascoli, S.,\u00a0 Touvron, H., Leavitt, M.L., Morcos, A.S., Biroli, G., Sagun: ConViT: improving vision transformers with soft convolutional inductive biases. Department of Physics, Ecole Normale Sup\u00e9rieure, Paris, France;\u00a0arXiv:2103.10697 (2021)","DOI":"10.1088\/1742-5468\/ac9830"},{"key":"36_CR10","unstructured":"Dosovitskiy, L., et al.: An image is worth 16 \u00d7 16 words: transformers for Image recognition at scale. In: ICLR (2021)"},{"key":"36_CR11","unstructured":"Baxes, G.A.: Digital Image Processing: Principles and Applications. John Wiley & Sons, Inc. (1994)"},{"key":"36_CR12","doi-asserted-by":"crossref","unstructured":"Guo, J., (Huawei Noah's Ark Lab.) et al.: Hire-MLP: vision MLP via hierarchical rearrangement. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00090"},{"key":"36_CR13","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers and distillation through attention. In: PMLR pp. 10347\u201310357 (2021)"},{"key":"36_CR14","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers and distillation through attention. arXiv:2012.12877 (2020)"},{"key":"36_CR15","doi-asserted-by":"crossref","unstructured":"Radosavovic, I., Kosaraju, R.P., Girshick, R., He, K., Dollar, P.: Designing network design spaces. In: CVPR, pp. 10428\u201310436 (2020)","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"36_CR16","unstructured":"Pitas, I.: Digital Image Processing Algorithms and Applications. John Wiley & Sons (2000)"},{"key":"36_CR17","doi-asserted-by":"crossref","unstructured":"Lee, J.-H., Heo, M., Kim, K.-R., Kim, C.-S.: Single-image depth estimation based on fourier domain analysis. In: CVPR, pp. 330\u2013339 (2018)","DOI":"10.1109\/CVPR.2018.00042"},{"key":"36_CR18","unstructured":"Yang, J., et al.: Focal self-attention for local-global interactions in vision transformers. arXiv:2107.00641 (2021)"},{"key":"36_CR19","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"36_CR20","doi-asserted-by":"crossref","unstructured":"Lee-Thorp, J., Ainslie, J., Eckstein, I., Onta\u00f1\u00f3n, S.: FNet: mixing tokens with fourier transforms. In: NAACL 2021\u20132022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 4296\u20134313 (2022)","DOI":"10.18653\/v1\/2022.naacl-main.319"},{"key":"36_CR21","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: MViTv2: improved multiscale vision transformers for classification and detection. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"36_CR22","unstructured":"Li, Y., (Computer Vision Lab, ETH Zurich, Switzerland), Zhang, K., Cao, J., Timofte, R., van Gool, L.: LocalViT: bringing locality to vision transformers. arXiv:2104.05707 (2021)"},{"key":"36_CR23","unstructured":"Lian, D., (ShanghaiTech University, China), Yu, Z., Sun, X., Gao, S.: AS-MLP: an axial shifted MLP architecture for vision. In: ICLR (2022)"},{"key":"36_CR24","unstructured":"Liu, H., Dai, Z., So, D., Le, Q.: Pay attention to MLPs. In: NIPS (2021)"},{"key":"36_CR25","doi-asserted-by":"crossref","unstructured":"Liu, P., Zhang, H., Lian, W., Zuo, W.: Multi-level wavelet convolutional neural networks. In: IEEE Access, pp. 74973\u201374985 (2019)","DOI":"10.1109\/ACCESS.2019.2921451"},{"key":"36_CR26","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv:1711.05101 (2017)"},{"key":"36_CR27","unstructured":"Chi, L., Jiang, B., Mu, Y.: Fast fourier convolution. In: NIPS (2020)"},{"key":"36_CR28","unstructured":"Lv, T., Bai, C., Wang, C.: MDMLP: image classification from scratch on small datasets with MLP. arXiv:2205.14477 (2022)"},{"key":"36_CR29","unstructured":"Mehta, S., Ghazvininejad, M., Iyer, S., et al.: Delight: deep and light-weight transformer. arXiv:2008.00623 (2020)"},{"key":"36_CR30","doi-asserted-by":"crossref","unstructured":"Peng, Z., (University of Chinese, Academy of Sciences, Beijing, China), et al.: Conformer: local features coupling global representations for visual recognition. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00042"},{"key":"36_CR31","unstructured":"Hou, Q., Jiang, Z., Yuan, L., Cheng, M.-M., Yan, S., Feng, J.: Vision permutator: a permutable MLP-like architecture for visual recognition. arXiv:2106.12368 (2021)"},{"key":"36_CR32","doi-asserted-by":"crossref","unstructured":"Qin, Z., Zhang, P., Wu, F., Li, X.: FcaNet: frequency channel attention networks. Source: In: The IEEE International Conference on Computer Vision, pp. 763\u2013772 (2021)","DOI":"10.1109\/ICCV48922.2021.00082"},{"key":"36_CR33","unstructured":"Sabour, S., Frosst, N., Hinton, G.E.: Dynamic routing between capsules. In: NIPS, pp. 3857\u20133867 (2017)"},{"key":"36_CR34","doi-asserted-by":"crossref","unstructured":"Li, S., et al.: FALCON: a fourier transform based approach for fast and secure convolutional neural network predictions. In: CVPR, pp. 8705\u20138714 (2020)","DOI":"10.1109\/CVPR42600.2020.00873"},{"key":"36_CR35","doi-asserted-by":"crossref","unstructured":"Zheng, S., et al.: Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. arXiv:2012.15840 (2020)","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"36_CR36","doi-asserted-by":"crossref","unstructured":"Srinivas, A., (UC Berkeley), Lin, T.-Y., Parmar, N., Shlens, J., Abbeel, P., Vaswani, A.: Bottleneck transformers for visual recognition. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01625"},{"key":"36_CR37","doi-asserted-by":"crossref","unstructured":"Tang, Y., et al.: An image patch is a wave: phase-aware vision MLP. In: CVPR, pp. 10925\u201310934 (2022)","DOI":"10.1109\/CVPR52688.2022.01066"},{"key":"36_CR38","unstructured":"Tolstikhin, I.O., et al.: MLP-mixer: an all-MLP architecture for vision. In: NIPS (2021)"},{"key":"36_CR39","doi-asserted-by":"crossref","unstructured":"Touvron, H., et al.: ResMLP: feedforward networks for image classification with data-efficient training. arXiv:2105.03404 (2021)","DOI":"10.1109\/TPAMI.2022.3206148"},{"key":"36_CR40","unstructured":"Vaswani, A., (Google Brain), et al.: Attention is all you need. arXiv:1706.03762 (2017)"},{"key":"36_CR41","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Pyramid vision transformer: a versatile backbone for dense prediction without convolutions. In: ICCV, pp. 568\u2013578 (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"36_CR42","doi-asserted-by":"crossref","unstructured":"Wolf, T., Debut, L., Sanh, V., et al.: HuggingFace's transformers: state-of-the-art natural language processing. arXiv:1910.03771 (2019)","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"36_CR43","doi-asserted-by":"crossref","unstructured":"Dong, X., et al.: CSWin transformer: a general vision transformer backbone with cross-shaped windows. arXiv:2107.00652 (2021)","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"36_CR44","doi-asserted-by":"crossref","unstructured":"Chen, X., Yan, B., Zhu, J., Wang, D., Yang, X., Lu, H.: Transformer tracking. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"36_CR45","doi-asserted-by":"crossref","unstructured":"Xu, K., Qin, M., Sun, F., Wang, Y., Chen, Y.-K., Ren, F.: Learning in the frequency domain. In: CVPR, pp. 1737\u20131746 (2020)","DOI":"10.1109\/CVPR42600.2020.00181"},{"key":"36_CR46","doi-asserted-by":"crossref","unstructured":"Yu, X., Rao, Y., Wang, Z., Liu, Z., Lu, J., Zhou, J.: PoinTr: diverse point cloud completion with geometry-aware transformers. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01227"},{"key":"36_CR47","doi-asserted-by":"crossref","unstructured":"Yang, Y., Soatto, S.: FDA: fourier domain adaptation for semantic segmentation. In: CVPR, pp. 4085\u20134095 (2020)","DOI":"10.1109\/CVPR42600.2020.00414"},{"key":"36_CR48","unstructured":"Rao, Y., Zhao, W., Liu, B., Lu, J., Zhou, J., Hsieh, C.-J.: DynamicViT: efficient vision transformers with dynamic token sparsification. In: NIPS (2021)"},{"key":"36_CR49","unstructured":"Rao, Y., Zhao, W., Zhu, Z., Lu, J., Zhou, J.: Global filter networks for image classification. arXiv:2107.00645 (2021)"},{"key":"36_CR50","doi-asserted-by":"crossref","unstructured":"Yu, W., Luo, M., Zhou, P., et al.: MetaFormer is actually what you need for vision. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01055"},{"key":"36_CR51","unstructured":"Rao, K.R., Yip, P.: Discrete Cosine Transform: Algorithms, Advantages, Applications. Academic press (2014)"},{"key":"36_CR52","doi-asserted-by":"crossref","unstructured":"Liu, Y.L., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: ICCV, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"36_CR53","doi-asserted-by":"crossref","unstructured":"Zhang, W., Yin, Z., Sheng, Z., et al.: Graph attention multi-layer perceptron. arXiv:2206.04355 (2022)","DOI":"10.1145\/3534678.3539121"},{"key":"36_CR54","doi-asserted-by":"crossref","unstructured":"Zhang, D.J., et al.: MorphMLP: an efficient MLP-like backbone for spatial-temporal representation learning. In: ECCV. National University of Singapore, Singapore, Singapore (2022)","DOI":"10.1007\/978-3-031-19833-5_14"},{"key":"36_CR55","doi-asserted-by":"crossref","unstructured":"Zhang, J., (Youtu Lab, Tencent, China) et al.: Rethinking mobile block for efficient neural models. arXiv:2301.01146 (2023)","DOI":"10.1109\/ICCV51070.2023.00134"},{"key":"36_CR56","unstructured":"Zhao, Y., Wang, G., Luo, C., Xie, W., Zeng, W., Tang, C., (Microsoft Research Asia, Beijing, China) et al.: Sparse MLP for image recognition: is self-attention really necessary? In: AAAI (2022)"},{"key":"36_CR57","unstructured":"Gonzalez, R.C., Woods, R.E.: Digital image Processing. N.J Prentice Hall, Upper Saddle River (2008)"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-44210-0_36","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T15:32:30Z","timestamp":1730129550000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-44210-0_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031442094","9783031442100"],"references-count":57,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-44210-0_36","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"22 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Heraklion","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2023\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"easyacademia.org","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"947","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"426","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"22","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"45% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.4","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"type of other papers accepted : 9 Abstract","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}