{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T22:13:02Z","timestamp":1778278382820,"version":"3.51.4"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"1","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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["No.62301315"],"award-info":[{"award-number":["No.62301315"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Startup Fund for Young Faculty at SJTU","award":["No.23X010501967"],"award-info":[{"award-number":["No.23X010501967"]}]},{"name":"Shanghai Municipal Health Commission Health Industry Clinical Research Special Project","award":["No.202340010"],"award-info":[{"award-number":["No.202340010"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1007\/s10994-024-06728-3","type":"journal-article","created":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T16:22:49Z","timestamp":1736958169000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["Learning multi-axis representation in frequency domain for medical image segmentation"],"prefix":"10.1007","volume":"114","author":[{"given":"Jiacheng","family":"Ruan","sequence":"first","affiliation":[]},{"given":"Jingsheng","family":"Gao","sequence":"additional","affiliation":[]},{"given":"Mingye","family":"Xie","sequence":"additional","affiliation":[]},{"given":"Suncheng","family":"Xiang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,1,15]]},"reference":[{"issue":"11","key":"6728_CR1","doi-asserted-by":"publisher","first-page":"2514","DOI":"10.1109\/TMI.2018.2837502","volume":"37","author":"O Bernard","year":"2018","unstructured":"Bernard, O., Lalande, A., Zotti, C., et al. (2018). Deep learning techniques for automatic mri cardiac multi-structures segmentation and diagnosis: Is the problem solved? IEEE Transactions on Medical Imaging, 37(11), 2514\u20132525.","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"6728_CR2","unstructured":"Berseth, M. (2017). Isic 2017-skin lesion analysis towards melanoma detection. arXiv preprint arXiv:1703.00523"},{"key":"6728_CR3","unstructured":"Cao, H., Wang, Y., Chen, J., et\u00a0al. (2021). Swin-unet: Unet-like pure transformer for medical image segmentation. arXiv preprint arXiv:2105.05537"},{"key":"6728_CR4","unstructured":"Chen, J., Lu, Y., Yu, Q., et\u00a0al. (2021). Transunet: Transformers make strong encoders for medical image segmentation. arXiv preprint arXiv:2102.04306"},{"key":"6728_CR5","doi-asserted-by":"crossref","unstructured":"Chen, J., He, T., Zhuo, W., et\u00a0al. (2022). Tvconv: Efficient translation variant convolution for layout-aware visual processing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 12 pp. 548\u201312,558","DOI":"10.1109\/CVPR52688.2022.01222"},{"key":"6728_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Q., Cai, S., Cai, C., et\u00a0al. (2023). Colo-scrl: Self-supervised contrastive representation learning for colonoscopic video retrieval. arXiv preprint arXiv:2303.15671","DOI":"10.1109\/ICME55011.2023.00185"},{"key":"6728_CR7","unstructured":"Codella, N., Rotemberg, V., Tschandl, P., et\u00a0al. (2019). Skin lesion analysis toward melanoma detection 2018: A challenge hosted by the international skin imaging collaboration (isic). arXiv preprint arXiv:1902.03368"},{"issue":"5","key":"6728_CR8","doi-asserted-by":"publisher","first-page":"1116","DOI":"10.1109\/TMI.2018.2878669","volume":"38","author":"J Dolz","year":"2018","unstructured":"Dolz, J., Gopinath, K., Yuan, J., et al. (2018). Hyperdense-net: A hyper-densely connected cnn for multi-modal image segmentation. IEEE Transactions on Medical Imaging, 38(5), 1116\u20131126.","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"6728_CR9","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., et\u00a0al. (2020a). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929"},{"key":"6728_CR10","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., et\u00a0al. (2020b). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929"},{"key":"6728_CR11","doi-asserted-by":"crossref","unstructured":"Duan, H., Long, Y., Wang, S., et\u00a0al. (2023). Dynamic unary convolution in transformers. IEEE Transactions on Pattern Analysis and Machine Intelligence","DOI":"10.1109\/TPAMI.2022.3233482"},{"key":"6728_CR12","doi-asserted-by":"crossref","unstructured":"Duan, H., Wan, F., Sun, R., et\u00a0al. (2024). Wearable-based behaviour interpolation for semi-supervised human activity recognition. Available at SSRN 4342069","DOI":"10.2139\/ssrn.4342069"},{"key":"6728_CR13","unstructured":"Gao, J., Ruan, J., Xiang, S., et\u00a0al. (2023). Lamm: Label alignment for multi-modal prompt learning. arXiv preprint arXiv:2312.08212"},{"key":"6728_CR14","doi-asserted-by":"crossref","unstructured":"Gao, J., Ruan, J., Xiang, S., et\u00a0al. (2024). Lamm: Label alignment for multi-modal prompt learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp 1815\u20131823","DOI":"10.1609\/aaai.v38i3.27950"},{"key":"6728_CR15","unstructured":"Gao, Y., Zhou, M., Liu, D., et\u00a0al. (2022). A multi-scale transformer for medical image segmentation: Architectures, model efficiency, and benchmarks. arXiv preprint arXiv:2203.00131"},{"key":"6728_CR16","doi-asserted-by":"crossref","unstructured":"Huang, Y., Zhou, C., Chen, L., et\u00a0al. (2021). Medical frequency domain learning: Consider inter-class and intra-class frequency for medical image segmentation and classification. In: 2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), IEEE, pp 897\u2013904","DOI":"10.1109\/BIBM52615.2021.9669443"},{"key":"6728_CR17","unstructured":"Ioffe, S., & Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: International conference on machine learning, pmlr, pp 448\u2013456"},{"issue":"2","key":"6728_CR18","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","volume":"18","author":"F Isensee","year":"2021","unstructured":"Isensee, F., Jaeger, P. F., Kohl, S. A., et al. (2021). nnu-net: A self-configuring method for deep learning-based biomedical image segmentation. Nature Methods, 18(2), 203\u2013211.","journal-title":"Nature Methods"},{"key":"6728_CR19","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1016\/j.media.2016.10.004","volume":"36","author":"K Kamnitsas","year":"2017","unstructured":"Kamnitsas, K., Ledig, C., Newcombe, V. F., et al. (2017). Efficient multi-scale 3d cnn with fully connected crf for accurate brain lesion segmentation. Medical Image Analysis, 36, 61\u201378.","journal-title":"Medical Image Analysis"},{"key":"6728_CR20","doi-asserted-by":"crossref","unstructured":"Karimi, D., Vasylechko, S. D., & Gholipour, A. (2021). Convolution-free medical image segmentation using transformers. In: medical image computing and computer assisted intervention\u2013MICCAI 2021: 24th International Conference, Strasbourg, France, September 27\u2013October 1, 2021, Proceedings, Part I 24, Springer, pp 78\u201388","DOI":"10.1007\/978-3-030-87193-2_8"},{"key":"6728_CR21","unstructured":"Landman, B., Xu, Z., Igelsias, J., et\u00a0al. (2015). Miccai multi-atlas labeling beyond the cranial vault\u2013workshop and challenge. In: Proc. MICCAI Multi-atlas labeling beyond cranial vault-workshop challenge, p\u00a012"},{"key":"6728_CR22","first-page":"1","volume-title":"ICASSP 2023\u20132023 IEEE international conference on acoustics","author":"Y Li","year":"2023","unstructured":"Li, Y., Yu, Z., Xiang, S., et al. (2023). Av-tad: Audio-visual temporal action detection with transformer. ICASSP 2023\u20132023 IEEE international conference on acoustics (pp. 1\u20135). Speech and Signal Processing (ICASSP): IEEE."},{"key":"6728_CR23","unstructured":"Loshchilov, I., & Hutter, F. (2016). Sgdr: Stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983"},{"key":"6728_CR24","unstructured":"Loshchilov, I., & Hutter, F. (2017). Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101"},{"key":"6728_CR25","doi-asserted-by":"crossref","unstructured":"Milletari, F., Navab, N., & Ahmadi, S. A. (2016). V-net: Fully convolutional neural networks for volumetric medical image segmentation. In: 2016 fourth international conference on 3D vision (3DV), IEEE, pp 565\u2013571","DOI":"10.1109\/3DV.2016.79"},{"key":"6728_CR26","unstructured":"Oktay, O., Schlemper, J., Folgoc, L. L., et\u00a0al. (2018). Attention u-net: Learning where to look for the pancreas. arXiv preprint arXiv:1804.03999"},{"key":"6728_CR27","first-page":"980","volume":"34","author":"Y Rao","year":"2021","unstructured":"Rao, Y., Zhao, W., Zhu, Z., et al. (2021). Global filter networks for image classification. Advances in Neural Information Processing Systems, 34, 980\u2013993.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"6728_CR28","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., & Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. In: International Conference on Medical image computing and computer-assisted intervention, Springer, pp 234\u2013241","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"6728_CR29","doi-asserted-by":"crossref","unstructured":"Ruan, J., & Xiang, S. (2024). Vm-unet: Vision mamba unet for medical image segmentation. arXiv preprint arXiv:2402.02491","DOI":"10.1145\/3767748"},{"key":"6728_CR30","doi-asserted-by":"crossref","unstructured":"Ruan, J., Xiang, S., Xie, M., et\u00a0al. (2022). Malunet: A multi-attention and light-weight unet for skin lesion segmentation. In: 2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), IEEE, pp 1150\u20131156","DOI":"10.1109\/BIBM55620.2022.9995040"},{"key":"6728_CR31","doi-asserted-by":"crossref","unstructured":"Ruan, J., Xie, M., Gao, J., et\u00a0al. (2023). Ege-unet: an efficient group enhanced unet for skin lesion segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer, pp 481\u2013490","DOI":"10.1007\/978-3-031-43901-8_46"},{"key":"6728_CR32","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., et\u00a0al. (2018). Mobilenetv2: Inverted residuals and linear bottlenecks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4510\u20134520","DOI":"10.1109\/CVPR.2018.00474"},{"key":"6728_CR33","doi-asserted-by":"crossref","unstructured":"Wang, H., Cao, P., Wang, J., et\u00a0al. (2022a). Uctransnet: rethinking the skip connections in u-net from a channel-wise perspective with transformer. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp 2441\u20132449","DOI":"10.1609\/aaai.v36i3.20144"},{"key":"6728_CR34","doi-asserted-by":"crossref","unstructured":"Wang, H., Cao, P., Wang, J., et\u00a0al. (2022b). Uctransnet: rethinking the skip connections in u-net from a channel-wise perspective with transformer. In: Proceedings of the AAAI conference on artificial intelligence, pp 2441\u20132449","DOI":"10.1609\/aaai.v36i3.20144"},{"key":"6728_CR35","doi-asserted-by":"crossref","unstructured":"Wang, H., Xie, S., Lin, L., et al. (2022). Mixed transformer u-net for medical image segmentation. ICASSP 2022\u20132022 IEEE International Conference on Acoustics (pp. 2390\u20132394). Speech and Signal Processing (ICASSP): IEEE.","DOI":"10.1109\/ICASSP43922.2022.9746172"},{"key":"6728_CR36","doi-asserted-by":"crossref","unstructured":"Wei, J., Hu, Y., Zhang, R., et\u00a0al. (2021). Shallow attention network for polyp segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer, pp 699\u2013708","DOI":"10.1007\/978-3-030-87193-2_66"},{"key":"6728_CR37","doi-asserted-by":"crossref","unstructured":"Wu, Y., & He, K. (2018). Group normalization. In: Proceedings of the European conference on computer vision (ECCV), pp 3\u201319","DOI":"10.1007\/978-3-030-01261-8_1"},{"issue":"14","key":"6728_CR38","doi-asserted-by":"publisher","first-page":"3527","DOI":"10.1049\/iet-ipr.2020.0166","volume":"14","author":"S Xiang","year":"2020","unstructured":"Xiang, S., Fu, Y., & Liu, T. (2020). Progressive learning with style transfer for distant domain adaptation. IET Image Processing, 14(14), 3527\u20133535.","journal-title":"IET Image Processing"},{"key":"6728_CR39","doi-asserted-by":"crossref","unstructured":"Xiang, S., You, G., Li, L., et\u00a0al. (2022). Rethinking illumination for person re-identification: A unified view. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 4731\u20134739","DOI":"10.1109\/CVPRW56347.2022.00519"},{"key":"6728_CR40","unstructured":"Xiang, S., Chen, H., Ran, W., et\u00a0al. (2023a). Deep multimodal representation learning for generalizable person re-identification. Machine Learning pp 1\u201319"},{"issue":"6","key":"6728_CR41","doi-asserted-by":"publisher","first-page":"1923","DOI":"10.1007\/s10994-022-06184-x","volume":"112","author":"S Xiang","year":"2023","unstructured":"Xiang, S., Fu, Y., Guan, M., et al. (2023). Learning from self-discrepancy via multiple co-teaching for cross-domain person re-identification. Machine Learning, 112(6), 1923\u20131940.","journal-title":"Machine Learning"},{"issue":"3","key":"6728_CR42","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3628452","volume":"20","author":"S Xiang","year":"2023","unstructured":"Xiang, S., Qian, D., Gao, J., et al. (2023). Rethinking person re-identification via semantic-based pretraining. ACM Transactions on Multimedia Computing, Communications and Applications, 20(3), 1\u201317.","journal-title":"ACM Transactions on Multimedia Computing, Communications and Applications"},{"issue":"5s","key":"6728_CR43","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3588441","volume":"19","author":"S Xiang","year":"2023","unstructured":"Xiang, S., Qian, D., Guan, M., et al. (2023). Less is more: Learning from synthetic data with fine-grained attributes for person re-identification. ACM Transactions on Multimedia Computing, Communications and Applications, 19(5s), 1\u201320.","journal-title":"ACM Transactions on Multimedia Computing, Communications and Applications"},{"key":"6728_CR44","doi-asserted-by":"crossref","unstructured":"You, D., Xia, P., Chen, Q., et\u00a0al. (2023). Autokary2022: A large-scale densely annotated dateset for chromosome instance segmentation. arXiv preprint arXiv:2303.15839","DOI":"10.1109\/ICME55011.2023.00272"},{"issue":"3","key":"6728_CR45","doi-asserted-by":"publisher","first-page":"1116","DOI":"10.1016\/j.neuroimage.2006.01.015","volume":"31","author":"PA Yushkevich","year":"2006","unstructured":"Yushkevich, P. A., Piven, J., Cody Hazlett, H., et al. (2006). User-guided 3D active contour segmentation of anatomical structures: Significantly improved efficiency and reliability. Neuroimage, 31(3), 1116\u20131128.","journal-title":"Neuroimage"},{"key":"6728_CR46","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Liu, H., & Hu, Q. (2021). Transfuse: Fusing transformers and cnns for medical image segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer, pp 14\u201324","DOI":"10.1007\/978-3-030-87193-2_2"},{"key":"6728_CR47","doi-asserted-by":"crossref","unstructured":"Zhong, Y., Li, B., Tang, L., et\u00a0al. (2022). Detecting camouflaged object in frequency domain. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 4504\u20134513","DOI":"10.1109\/CVPR52688.2022.00446"},{"key":"6728_CR48","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Rahman\u00a0Siddiquee, M. M., Tajbakhsh, N., et\u00a0al. (2018). Unet++: A nested u-net architecture for medical image segmentation. In: Deep learning in medical image analysis and multimodal learning for clinical decision support. Springer, p 3\u201311","DOI":"10.1007\/978-3-030-00889-5_1"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-024-06728-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10994-024-06728-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-024-06728-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T01:02:16Z","timestamp":1768438936000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10994-024-06728-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":48,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["6728"],"URL":"https:\/\/doi.org\/10.1007\/s10994-024-06728-3","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]},"assertion":[{"value":"5 January 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 June 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 September 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 January 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not Applicable. The datasets and the work do not contain personal or sensitive information, no ethical issue is concerned.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}},{"value":"The authors are fine that the work is submitted and published by Machine Learning Journal. There is no human study in this work, so this aspect is not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participate"}},{"value":"The authors are fine that the work (including all content, data and images) is published by Machine Learning Journal.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}],"article-number":"10"}}