{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T18:50:14Z","timestamp":1782499814182,"version":"3.54.5"},"publisher-location":"Singapore","reference-count":23,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819570836","type":"print"},{"value":"9789819570843","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-7084-3_23","type":"book-chapter","created":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T10:23:54Z","timestamp":1778235834000},"page":"364-380","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Vim-F: Visual State Space Model Benefiting from\u00a0Learning in\u00a0the\u00a0Frequency Domain"],"prefix":"10.1007","author":[{"given":"Juntao","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaogeng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kun","family":"Bian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"You","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianning","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bingyan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,1]]},"reference":[{"key":"23_CR1","unstructured":"Goyal, P., et al.: Accurate, large minibatch SGD: training imagenet in 1 hour. Preprint arXiv:2111.11429 (2017)"},{"key":"23_CR2","unstructured":"Gu, A., Dao, T.: Mamba: linear-time sequence modeling with selective state spaces. Preprint arxiv:2312.00752 (2023)"},{"key":"23_CR3","doi-asserted-by":"crossref","unstructured":"Gupta, A., Gu, A., Berant, J.: Diagonal state spaces are as effective as structured state spaces. In: NeurIPS (2022)","DOI":"10.52202\/068431-1670"},{"key":"23_CR4","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":"23_CR5","doi-asserted-by":"crossref","unstructured":"Huang, T., Pei, X., You, S., Wang, F., Qian, C., Xu, C.: Localmamba: visual state space model with windowed selective scan. Preprint arXiv:2403.09338 (2024)","DOI":"10.1007\/978-3-031-91979-4_2"},{"key":"23_CR6","unstructured":"Katharopoulos, A., Vyas, A., Pappas, N., Fleuret, F.: Transformers are RNNs: fast autoregressive transformers with linear attention. In: ICML Proceedings of Machine Learning Research, vol.\u00a0119, pp. 5156\u20135165 (2020)"},{"key":"23_CR7","unstructured":"Li, Y., Xie, S., Chen, X., Doll\u00e1r, P., He, K., Girshick, R.B.: Benchmarking detection transfer learning with vision transformers. Preprint arXiv:2111.11429 (2021)"},{"key":"23_CR8","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Efficientformer: vision transformers at mobilenet speed. In: NeurIPS (2022)","DOI":"10.52202\/068431-0940"},{"key":"23_CR9","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: VMAMBA: visual state space model. In: NeurIPS. vol.\u00a037, pp. 103031\u2013103063 (2024)","DOI":"10.52202\/079017-3273"},{"key":"23_CR10","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 9992\u201310002 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"23_CR11","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C., Feichtenhofer, C., Darrell, T., Xie, S.: A convnet for the 2020s. In: CVPR, pp. 11966\u201311976 (2022)","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"23_CR12","unstructured":"Mehta, H., Gupta, A., Cutkosky, A., Neyshabur, B.: Long range language modeling via gated state spaces. In: The Eleventh International Conference on Learning Representations (ICLR) (2023)"},{"key":"23_CR13","unstructured":"Mehta, S., Rastegari, M.: Mobilevit: light-weight, general-purpose, and mobile-friendly vision transformer. In: The Tenth International Conference on Learning Representations (ICLR) (2022)"},{"key":"23_CR14","doi-asserted-by":"crossref","unstructured":"Pei, X., Huang, T., Xu, C.: Efficientvmamba: atrous selective scan for light weight visual mamba. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a039, pp. 6443\u20136451 (2025)","DOI":"10.1609\/aaai.v39i6.32690"},{"key":"23_CR15","doi-asserted-by":"crossref","unstructured":"Radosavovic, I., Kosaraju, R.P., Girshick, R., He, K., Doll\u00e1r, P.: Designing betwork design spaces. In: CVPR, pp. 10428\u201310436 (2020)","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"23_CR16","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. In: ICML, pp. 10347\u201310357 (2021)"},{"issue":"3","key":"23_CR17","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. Visual Media 8(3), 415\u2013424 (2022)","journal-title":"Comput. Visual Media"},{"key":"23_CR18","doi-asserted-by":"crossref","unstructured":"Xiao, T., Liu, Y., Zhou, B., Jiang, Y., Sun, J.: Unified perceptual parsing for scene understanding. In: Computer Vision - ECCV 2018 - 15th European Conference. vol. 11209, pp. 432\u2013448, Munich, September 8-14, 2018, Proceedings, Part V (2018)","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"23_CR19","doi-asserted-by":"crossref","unstructured":"Yang, C., et al.: Lite vision transformer with enhanced self-attention. In: CVPR, pp. 11998\u201312008 (2022)","DOI":"10.1109\/CVPR52688.2022.01169"},{"key":"23_CR20","unstructured":"Yang, C., et al.: Plainmamba: improving non-hierarchical mamba in visual recognition. In: British Machine Vision Conference (BMVC) (2024)"},{"issue":"2","key":"23_CR21","doi-asserted-by":"publisher","first-page":"896","DOI":"10.1109\/TPAMI.2023.3329173","volume":"46","author":"W Yu","year":"2024","unstructured":"Yu, W., et al.: Metaformer baselines for vision. IEEE Trans. Pattern Anal. Mach. Intell. 46(2), 896\u2013912 (2024)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"23_CR22","unstructured":"Zhu, L., Liao, B., Zhang, Q., Wang, X., Liu, W., Wang, X.: Vision mamba: efficient visual representation learning with bidirectional state space model. In: ICML (2024)"},{"key":"23_CR23","doi-asserted-by":"crossref","unstructured":"Zhu, Q., Fang, Y., Cai, Y., Chen, C., Fan, L.: Rethinking scanning strategies with vision mamba in semantic segmentation of remote sensing imagery: an experimental study. IEEE J. Selected Top. Appl. Earth Observ. Remote Sens. (2024)","DOI":"10.1109\/JSTARS.2024.3472296"}],"container-title":["Lecture Notes in Computer Science","PRICAI 2025: Trends in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-7084-3_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T18:16:35Z","timestamp":1782497795000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-7084-3_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819570836","9789819570843"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-7084-3_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"1 May 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific Rim International Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Wellington","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Zealand","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":"17 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pricai2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.pricai.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}