{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T16:49:50Z","timestamp":1758041390464,"version":"3.44.0"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783032045577"},{"type":"electronic","value":"9783032045584"}],"license":[{"start":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T00:00:00Z","timestamp":1757635200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T00:00:00Z","timestamp":1757635200000},"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\/978-3-032-04558-4_4","type":"book-chapter","created":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T11:17:08Z","timestamp":1757589428000},"page":"42-54","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MFMamba: A Hierarchical Weakly Causal Mamba with\u00a0Multi-scale Feature Fusion for\u00a0Vision Tasks"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9053-0237","authenticated-orcid":false,"given":"Zechen","family":"Sun","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8457-2900","authenticated-orcid":false,"given":"Zuogong","family":"Yue","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,9,12]]},"reference":[{"unstructured":"Dai, Z., Liu, H., Le, Q.V., Tan, M.: Coatnet: marrying convolution and attention for all data sizes. In: Neural Information Processing Systems, vol.\u00a034, pp. 3965\u20133977. Curran Associates, Inc. (2021)","key":"4_CR1"},{"unstructured":"Dosovitskiy, A.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (Oct 2020)","key":"4_CR2"},{"doi-asserted-by":"publisher","unstructured":"Gu, A., Dao, T.: Mamba: linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752 (2024). https:\/\/doi.org\/10.48550\/arXiv.2312.00752","key":"4_CR3","DOI":"10.48550\/arXiv.2312.00752"},{"unstructured":"Gu, A., Goel, K., R\u00e9, C.: Efficiently modeling long sequences with structured state spaces. In: International Conference on Learning Representations (2022)","key":"4_CR4"},{"doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Dollar, P., Girshick, R.: Mask r-cnn. In: IEEE International Conference on Computer Vision, pp. 2961\u20132969 (2017)","key":"4_CR5","DOI":"10.1109\/ICCV.2017.322"},{"doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","key":"4_CR6","DOI":"10.1109\/CVPR.2016.90"},{"unstructured":"Howard, A.G.: Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)","key":"4_CR7"},{"doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., van der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700\u20134708 (2017)","key":"4_CR8","DOI":"10.1109\/CVPR.2017.243"},{"unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Neural Information Processing Systems, vol.\u00a025. Curran Associates, Inc. (2012)","key":"4_CR9"},{"doi-asserted-by":"publisher","unstructured":"Liu, Y., et al.: Vmamba: visual state space model. In: Neural Information Processing Systems (2024). https:\/\/doi.org\/10.48550\/arXiv.2401.10166","key":"4_CR10","DOI":"10.48550\/arXiv.2401.10166"},{"doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","key":"4_CR11","DOI":"10.1109\/ICCV48922.2021.00986"},{"doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.Y., Feichtenhofer, C., Darrell, T., Xie, S.: A convnet for the 2020s. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11976\u201311986 (2022)","key":"4_CR12","DOI":"10.1109\/CVPR52688.2022.01167"},{"doi-asserted-by":"publisher","unstructured":"Pei, X., Huang, T., Xu, C.: Efficientvmamba: atrous selective scan for light weight visual mamba. arXiv preprint arXiv:2403.09977 (2024). https:\/\/doi.org\/10.48550\/arXiv.2403.09977","key":"4_CR13","DOI":"10.48550\/arXiv.2403.09977"},{"doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: Mobilenetv2: inverted residuals and linear bottlenecks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510\u20134520 (2018)","key":"4_CR14","DOI":"10.1109\/CVPR.2018.00474"},{"unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (2015)","key":"4_CR15"},{"unstructured":"Tan, M., Le, Q.: Efficientnet: rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, pp. 6105\u20136114. PMLR (2019)","key":"4_CR16"},{"unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., Jegou, H.: Training data-efficient image transformers & distillation through attention. In: International Conference on Machine Learning, pp. 10347\u201310357. PMLR (2021)","key":"4_CR17"},{"unstructured":"Vaswani, A., et al.: Attention is all you need. In: Neural Information Processing Systems (2017)","key":"4_CR18"},{"doi-asserted-by":"crossref","unstructured":"Wang, F., et al.: Mamba-r: vision mamba also needs registers. arXiv preprint arXiv:2405.14858 (May 2024)","key":"4_CR19","DOI":"10.1109\/CVPR52734.2025.01392"},{"doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Pyramid vision transformer: a versatile backbone for dense prediction without convolutions. In: IEEE\/CVF International Conference on Computer Vision, pp. 568\u2013578 (2021)","key":"4_CR20","DOI":"10.1109\/ICCV48922.2021.00061"},{"doi-asserted-by":"crossref","unstructured":"Wu, H., et al.: CVT: introducing convolutions to vision transformers. In: IEEE\/CVF International Conference on Computer Vision, pp. 22\u201331 (2021)","key":"4_CR21","DOI":"10.1109\/ICCV48922.2021.00009"},{"doi-asserted-by":"crossref","unstructured":"Xiao, T., Liu, Y., Zhou, B., Jiang, Y., Sun, J.: Unified perceptual parsing for scene understanding. In: European Conference on Computer Vision (ECCV), pp. 418\u2013434 (2018)","key":"4_CR22","DOI":"10.1007\/978-3-030-01228-1_26"},{"unstructured":"Xie, F., Zhang, W., Wang, Z., Ma, C.: Quadmamba: learning quadtree-based selective scan for visual state space model. In: Neural Information Processing Systems (2024)","key":"4_CR23"},{"unstructured":"Yang, C., et al.: Plainmamba: improving non-hierarchical mamba in visual recognition. In: British Machine Vision Conference (2024)","key":"4_CR24"},{"doi-asserted-by":"publisher","unstructured":"Yu, W., Wang, X.: Mambaout: do we really need mamba for vision? arXiv preprint arXiv:2405.07992 (2024). https:\/\/doi.org\/10.48550\/arXiv.2405.07992","key":"4_CR25","DOI":"10.48550\/arXiv.2405.07992"},{"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: International Conferenceon Machine Learning (2024)","key":"4_CR26"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-04558-4_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T11:17:21Z","timestamp":1757589441000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04558-4_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,12]]},"ISBN":["9783032045577","9783032045584"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04558-4_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025,9,12]]},"assertion":[{"value":"12 September 2025","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":"Kaunas","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lithuania","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":"9 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"34","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}