{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T16:28:56Z","timestamp":1743006536941,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":34,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819787012"},{"type":"electronic","value":"9789819787029"}],"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\/978-981-97-8702-9_1","type":"book-chapter","created":{"date-parts":[[2025,2,8]],"date-time":"2025-02-08T04:25:57Z","timestamp":1738988757000},"page":"3-17","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SwInception - Local Attention Meets Convolutions"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5193-3789","authenticated-orcid":false,"given":"David","family":"Hagerman","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2625-125X","authenticated-orcid":false,"given":"Roman","family":"Naeem","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2790-8775","authenticated-orcid":false,"given":"Jakob","family":"Lindqvist","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3563-8946","authenticated-orcid":false,"given":"Carl","family":"Lindstr\u00f6m","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9835-3020","authenticated-orcid":false,"given":"Fredrik","family":"Kahl","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0206-9186","authenticated-orcid":false,"given":"Lennart","family":"Svensson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,2,8]]},"reference":[{"issue":"1","key":"1_CR1","doi-asserted-by":"publisher","first-page":"4128","DOI":"10.1038\/s41467-022-30695-9","volume":"13","author":"M Antonelli","year":"2022","unstructured":"Antonelli, M., et al.: The medical segmentation decathlon. Nat. Commun. 13(1), 4128 (2022)","journal-title":"Nat. Commun."},{"key":"1_CR2","unstructured":"Choromanski, K.M., et\u00a0al.: Rethinking attention with performers. In: ICLR (2021)"},{"key":"1_CR3","unstructured":"Chu, X., et\u00a0al.: Conditional positional encodings for vision transformers. In: ICLR (2023)"},{"key":"1_CR4","doi-asserted-by":"crossref","unstructured":"Dong, X., et\u00a0al.: Cswin transformer: a general vision transformer backbone with cross-shaped windows. In: CVPR, pp. 12124\u201312134 (2022)","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"1_CR5","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"issue":"8","key":"1_CR6","doi-asserted-by":"publisher","first-page":"1822","DOI":"10.1109\/TMI.2018.2806309","volume":"37","author":"E Gibson","year":"2018","unstructured":"Gibson, E., et al.: Automatic multi-organ segmentation on abdominal CT with dense v-networks. IEEE Trans. Med. Imaging 37(8), 1822\u20131834 (2018)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"1_CR7","doi-asserted-by":"crossref","unstructured":"Guo, J., et\u00a0al.: CMT: convolutional neural networks meet vision transformers. In: CVPR, pp. 12175\u201312185 (2022)","DOI":"10.1109\/CVPR52688.2022.01186"},{"key":"1_CR8","unstructured":"Guo, M.H., et\u00a0al.: SegNeXT: rethinking convolutional attention design for semantic segmentation. In: NeurIPS, vol.\u00a035 (2022)"},{"key":"1_CR9","doi-asserted-by":"crossref","unstructured":"Hatamizadeh, A., et\u00a0al.: UNETR: transformers for 3d medical image segmentation. In: WACV, pp. 574\u2013584 (2022)","DOI":"10.1109\/WACV51458.2022.00181"},{"key":"1_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"1_CR11","doi-asserted-by":"crossref","unstructured":"He, Y., Yang, D., Roth, H., Zhao, C., Xu, D.: Dints: differentiable neural network topology search for 3d medical image segmentation. In: CVPR, pp. 5841\u20135850 (2021)","DOI":"10.1109\/CVPR46437.2021.00578"},{"key":"1_CR12","unstructured":"Ho, J., Kalchbrenner, N., Weissenborn, D., Salimans, T.: Axial attention in multidimensional transformers. arXiv preprint arXiv:1912.12180 (2019)"},{"key":"1_CR13","unstructured":"Huang, X., Deng, Z., Li, D., Yuan, X.: Missformer: an effective medical image segmentation transformer. arXiv preprint arXiv:2109.07162 (May 2021)"},{"issue":"2","key":"1_CR14","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., Petersen, J., Maier-Hein, K.H.: nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat. Methods 18(2), 203\u2013211 (2021)","journal-title":"Nat. Methods"},{"key":"1_CR15","unstructured":"Kitaev, N., Kaiser, L., Levskaya, A.: Reformer: the efficient transformer. In: ICLR (2020)"},{"key":"1_CR16","doi-asserted-by":"crossref","unstructured":"Lin, A., Xu, J., Li, J., Lu, G.: Contrans: improving transformer with convolutional attention for medical image segmentation. In: MICCAI, pp. 297\u2013307. Springer (2022)","DOI":"10.1007\/978-3-031-16443-9_29"},{"key":"1_CR17","doi-asserted-by":"crossref","unstructured":"Liu, J., et\u00a0al.: Clip-driven universal model for organ segmentation and tumor detection. In: ICCV, pp. 21152\u201321164 (2023)","DOI":"10.1109\/ICCV51070.2023.01934"},{"key":"1_CR18","doi-asserted-by":"crossref","unstructured":"Liu, W., et\u00a0al.: Phtrans: Parallelly aggregating global and local representations for medical image segmentation. In: MICCAI, pp. 235\u2013244. Springer (2022)","DOI":"10.1007\/978-3-031-16443-9_23"},{"key":"1_CR19","doi-asserted-by":"crossref","unstructured":"Liu, Z., et\u00a0al.: Swin transformer: hierarchical vision transformer using shifted windows. In: ICCV, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"1_CR20","doi-asserted-by":"crossref","unstructured":"Rahman, M.M., Marculescu, R.: Medical image segmentation via cascaded attention decoding. In: WACV, pp. 6222\u20136231 (2023)","DOI":"10.1109\/WACV56688.2023.00616"},{"key":"1_CR21","first-page":"23495","volume":"35","author":"C Si","year":"2022","unstructured":"Si, C., Yu, W., Zhou, P., Zhou, Y., Wang, X., Yan, S.: Inception transformer. NeurIPS 35, 23495\u201323509 (2022)","journal-title":"NeurIPS"},{"key":"1_CR22","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"1_CR23","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et\u00a0al.: Going deeper with convolutions. In: CVPR. pp.\u00a01\u20139 (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"1_CR24","unstructured":"Tang, Y.: Private communication (2023)"},{"key":"1_CR25","doi-asserted-by":"crossref","unstructured":"Tang, Y., et\u00a0al.: Self-supervised pre-training of swin transformers for 3d medical image analysis. In: CVPR, pp. 20730\u201320740 (2022)","DOI":"10.1109\/CVPR52688.2022.02007"},{"key":"1_CR26","unstructured":"Vaswani, A., et\u00a0al.: Attention is all you need. In: NeurIPS, vol.\u00a030 (2017)"},{"key":"1_CR27","unstructured":"Wang, S., Li, B.Z., Khabsa, M., Fang, H., Ma, H.: Linformer: self-attention with linear complexity. arXiv preprint arXiv:2006.04768 (2020)"},{"key":"1_CR28","doi-asserted-by":"crossref","unstructured":"Wu, H., et\u00a0al.: CVT: introducing convolutions to vision transformers. In: ICCV, pp. 22\u201331 (2021)","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"1_CR29","first-page":"12077","volume":"34","author":"E Xie","year":"2021","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M., Luo, P.: Segformer: simple and efficient design for semantic segmentation with transformers. NeurIPS 34, 12077\u201312090 (2021)","journal-title":"NeurIPS"},{"key":"1_CR30","first-page":"30008","volume":"34","author":"J Yang","year":"2021","unstructured":"Yang, J., et al.: Focal attention for long-range interactions in vision transformers. NeurIPS 34, 30008\u201330022 (2021)","journal-title":"NeurIPS"},{"key":"1_CR31","doi-asserted-by":"crossref","unstructured":"Yuan, K., Guo, S., Liu, Z., Zhou, A., Yu, F., Wu, W.: Incorporating convolution designs into visual transformers. In: ICCV, pp. 579\u2013588 (2021)","DOI":"10.1109\/ICCV48922.2021.00062"},{"key":"1_CR32","doi-asserted-by":"crossref","unstructured":"Zhai, X., Kolesnikov, A., Houlsby, N., Beyer, L.: Scaling vision transformers. In: CVPR, pp. 12104\u201312113 (2022)","DOI":"10.1109\/CVPR52688.2022.01179"},{"key":"1_CR33","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Xu, Y., Zhang, J., Tao, D.: Vitaev2: vision transformer advanced by exploring inductive bias for image recognition and beyond. Int. J. Comput. Vis. 1141\u20131162 (2023)","DOI":"10.1007\/s11263-022-01739-w"},{"key":"1_CR34","doi-asserted-by":"crossref","unstructured":"Zhou, H.Y., et\u00a0al.: nnformer: volumetric medical image segmentation via a 3d transformer. IEEE Trans. Image Process. (2023)","DOI":"10.1109\/TIP.2023.3293771"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-8702-9_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,8]],"date-time":"2025-02-08T04:26:29Z","timestamp":1738988789000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8702-9_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819787012","9789819787029"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8702-9_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"8 February 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPRAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition and Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Jeju Island","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 June 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 June 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icprai2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/brain.korea.ac.kr\/icprai2024\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}