{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T15:56:09Z","timestamp":1768233369329,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":46,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819557547","type":"print"},{"value":"9789819557554","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\/978-981-95-5755-4_2","type":"book-chapter","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T12:29:39Z","timestamp":1768220979000},"page":"25-38","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["EUMamba:Towards a\u00a0Efficient Utilization of\u00a0Mamba in\u00a0Vision Backbone"],"prefix":"10.1007","author":[{"given":"Jianning","family":"Liu","sequence":"first","affiliation":[]},{"given":"Juntao","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Kun","family":"Bian","sequence":"additional","affiliation":[]},{"given":"You","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Jun","family":"Zhou","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,13]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Chen, G., Huang, Y., Xu, J., Pei, B., Chen, Z., Li, Z., Wang, J., Li, K., Lu, T., Wang, L.: Video mamba suite: State space model as a versatile alternative for video understanding. arXiv preprint arXiv:2403.09626 (2024)","DOI":"10.1007\/s11263-025-02597-y"},{"key":"2_CR2","unstructured":"Chen, K., Wang, J., Pang, J., Cao, Y., Xiong, Y., Li, X., Sun, S., Feng, W., Liu, Z., Xu, J., et\u00a0al.: MMdetection: Open MMlab detection toolbox and benchmark. arXiv preprint arXiv:1906.07155 (2019)"},{"key":"2_CR3","unstructured":"Contributors, M.: MMsegmentation: Open MMlab semantic segmentation toolbox and benchmark (2020)"},{"key":"2_CR4","doi-asserted-by":"crossref","unstructured":"Dong, X., Bao, J., Chen, D., Zhang, W., Yu, N., Yuan, L., Chen, D., Guo, B.: Cswin transformer: a general vision transformer backbone with cross-shaped windows. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12124\u201312134 (2022)","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"2_CR5","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., Houlsby, N.: An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale (2021). https:\/\/arxiv.org\/abs\/2010.11929"},{"key":"2_CR6","unstructured":"Fu, D.Y., Dao, T., Saab, K.K., Thomas, A.W., Rudra, A., R\u00e9, C.: Hungry hungry hippos: Towards language modeling with state space models. arXiv preprint arXiv:2212.14052 (2022)"},{"key":"2_CR7","unstructured":"Gu, A., Dao, T.: Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752 (2023)"},{"key":"2_CR8","unstructured":"Gu, A., Goel, K., R\u00e9, C.: Efficiently modeling long sequences with structured state spaces. arXiv preprint arXiv:2111.00396 (2021)"},{"key":"2_CR9","first-page":"572","volume":"34","author":"A Gu","year":"2021","unstructured":"Gu, A., Johnson, I., Goel, K., Saab, K., Dao, T., Rudra, A., R\u00e9, C.: Combining recurrent, convolutional, and continuous-time models with linear state space layers. Adv. Neural. Inf. Process. Syst. 34, 572\u2013585 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2_CR10","unstructured":"Guo, T., Wang, Y., Meng, C.: Mambamorph: a mamba-based backbone with contrastive feature learning for deformable MR-CT registration. arXiv e-prints pp. arXiv\u20132401 (2024)"},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: 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":"2_CR13","unstructured":"Howard, A.G.: Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)"},{"issue":"12","key":"2_CR14","doi-asserted-by":"publisher","first-page":"8704","DOI":"10.1109\/TPAMI.2019.2918284","volume":"44","author":"G Huang","year":"2019","unstructured":"Huang, G., Liu, Z., Pleiss, G., Van Der Maaten, L., Weinberger, K.Q.: Convolutional networks with dense connectivity. IEEE Trans. Pattern Anal. Mach. Intell. 44(12), 8704\u20138716 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2_CR15","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, CoRR (2024)","DOI":"10.1007\/978-3-031-91979-4_2"},{"key":"2_CR16","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Syst. 25 (2012)"},{"key":"2_CR17","first-page":"12934","volume":"35","author":"Y Li","year":"2022","unstructured":"Li, Y., Yuan, G., Wen, Y., Hu, J., Evangelidis, G., Tulyakov, S., Wang, Y., Ren, J.: Efficientformer: Vision transformers at mobilenet speed. Adv. Neural. Inf. Process. Syst. 35, 12934\u201312949 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2_CR18","unstructured":"Liang, D., Zhou, X., Xu, W., Zhu, X., Zou, Z., Ye, X., Tan, X., Bai, X.: Pointmamba: a simple state space model for point cloud analysis. arXiv preprint arXiv:2402.10739 (2024)"},{"key":"2_CR19","doi-asserted-by":"publisher","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2_CR20","unstructured":"Liu, J., Yang, H., Zhou, H.Y., Xi, Y., Yu, L., Li, C., Liang, Y., Shi, G., Yu, Y., Zhang, S., et\u00a0al.: Swin-umamba: Mamba-based UNET with ImageNet-based pretraining. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 615\u2013625. Springer, Berlin (2024)"},{"key":"2_CR21","first-page":"103031","volume":"37","author":"Y Liu","year":"2024","unstructured":"Liu, Y., Tian, Y., Zhao, Y., Yu, H., Xie, L., Wang, Y., Ye, Q., Jiao, J., Liu, Y.: Vmamba: Visual state space model. Adv. Neural. Inf. Process. Syst. 37, 103031\u2013103063 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2_CR22","doi-asserted-by":"crossref","unstructured":"Liu, Z., Hu, H., Lin, Y., Yao, Z., Xie, Z., Wei, Y., Ning, J., Cao, Y., Zhang, Z., Dong, L., et\u00a0al.: Swin transformer v2: Scaling up capacity and resolution. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12009\u201312019 (2022)","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"2_CR23","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., Guo, B.: 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":"2_CR24","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.Y., Feichtenhofer, C., Darrell, T., Xie, S.: A convnet for the 2020s. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11976\u201311986 (2022)","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"2_CR25","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"},{"key":"2_CR26","unstructured":"Mehta, H., Gupta, A., Cutkosky, A., Neyshabur, B.: Long range language modeling via gated state spaces. arXiv preprint arXiv:2206.13947 (2022)"},{"key":"2_CR27","unstructured":"Mehta, S., Rastegari, M.: Mobilevit: light-weight, general-purpose, and mobile-friendly vision transformer. arXiv preprint arXiv:2110.02178 (2021)"},{"key":"2_CR28","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":"2_CR29","doi-asserted-by":"crossref","unstructured":"Radosavovic, I., Kosaraju, R.P., Girshick, R., He, K., Doll\u00e1r, P.: Designing network design spaces. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10428\u201310436 (2020)","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"2_CR30","doi-asserted-by":"crossref","unstructured":"Ruan, J., Li, J., Xiang, S.: Vm-unet: Vision mamba UNET for medical image segmentation. arXiv preprint arXiv:2402.02491 (2024)","DOI":"10.1145\/3767748"},{"key":"2_CR31","doi-asserted-by":"crossref","unstructured":"Shi, Y., Dong, M., Xu, C.: Multi-scale VMamba: Hierarchy in hierarchy visual state space model. arXiv preprint arXiv:2405.14174 (2024)","DOI":"10.52202\/079017-0808"},{"key":"2_CR32","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"2_CR33","unstructured":"Smith, J.T., Warrington, A., Linderman, S.W.: Simplified state space layers for sequence modeling. arXiv preprint arXiv:2208.04933 (2022)"},{"key":"2_CR34","unstructured":"Tan, M., Le\u00a0Q\u00a0V, E.: Rethinking model scaling for convolutional neural networks 2019. arXiv preprint arXiv:1905.11946 (1905)"},{"key":"2_CR35","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":"2_CR36","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"2_CR37","unstructured":"Wang, C., Tsepa, O., Ma, J., Wang, B.: Graph-mamba: Towards long-range graph sequence modeling with selective state spaces. arXiv preprint arXiv:2402.00789 (2024)"},{"key":"2_CR38","doi-asserted-by":"crossref","unstructured":"Wang, W., Xie, E., Li, X., Fan, D.P., Song, K., Liang, D., Lu, T., Luo, P., Shao, L.: 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":"2_CR39","doi-asserted-by":"crossref","unstructured":"Wang, W., Xie, E., Li, X., Fan, D.P., Song, K., Liang, D., Lu, T., Luo, P., Shao, L.: Pvt v2: Improved baselines with pyramid vision transformer. Computat. Vis. Media 8(3), 415\u2013424 (2022)","DOI":"10.1007\/s41095-022-0274-8"},{"key":"2_CR40","first-page":"117682","volume":"37","author":"F Xie","year":"2024","unstructured":"Xie, F., Zhang, W., Wang, Z., Ma, C.: Quadmamba: Learning quadtree-based selective scan for visual state space model. Adv. Neural. Inf. Process. Syst. 37, 117682\u2013117707 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2_CR41","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":"2_CR42","unstructured":"Yang, C., Chen, Z., Espinosa, M., Ericsson, L., Wang, Z., Liu, J., Crowley, E.: Plainmamba: improving non-hierarchical mamba in visual recognition. arXiv preprint arXiv:2403.17695 (2024)"},{"key":"2_CR43","doi-asserted-by":"crossref","unstructured":"Yang, Y., Xing, Z., Yu, L., Huang, C., Fu, H., Zhu, L.: Vivim: A video vision mamba for medical video segmentation. arXiv preprint arXiv:2401.14168 (2024)","DOI":"10.1109\/TCSVT.2025.3563411"},{"key":"2_CR44","doi-asserted-by":"crossref","unstructured":"Yu, W., Luo, M., Zhou, P., Si, C., Zhou, Y., Wang, X., Feng, J., Yan, S.: Metaformer is actually what you need for vision. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10819\u201310829 (2022)","DOI":"10.1109\/CVPR52688.2022.01055"},{"key":"2_CR45","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ade20k dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 633\u2013641 (2017)","DOI":"10.1109\/CVPR.2017.544"},{"key":"2_CR46","unstructured":"Zhu, L., Liao, B., Zhang, Q., Wang, X., Liu, W., Wang, X.: Vision mamba: efficient visual representation learning with bidirectional state space model (2024). https:\/\/arxiv.org\/abs\/2401.09417"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-5755-4_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T12:30:17Z","timestamp":1768221017000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-5755-4_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819557547","9789819557554"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-5755-4_2","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":"13 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shanghai","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":"15 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2025.prcv.cn\/index.asp","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}