{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T00:53:26Z","timestamp":1780880006327,"version":"3.54.1"},"reference-count":59,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2025,3,11]],"date-time":"2025-03-11T00:00:00Z","timestamp":1741651200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,3,11]],"date-time":"2025-03-11T00:00:00Z","timestamp":1741651200000},"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":["Vis Comput"],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1007\/s00371-025-03848-2","type":"journal-article","created":{"date-parts":[[2025,3,11]],"date-time":"2025-03-11T11:45:21Z","timestamp":1741693521000},"page":"7951-7963","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Msu-mamba: multi-scale defocus blur detection using cross-scale fusion and state-space models"],"prefix":"10.1007","volume":"41","author":[{"given":"Xijun","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Songto","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haobo","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Song","family":"Fei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,3,11]]},"reference":[{"key":"3848_CR1","doi-asserted-by":"crossref","unstructured":"Alireza\u00a0Golestaneh, S., Karam, L.J.: Spatially-varying blur detection based on multiscale fused and sorted transform coefficients of gradient magnitudes. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 5800\u20135809 (2017)","DOI":"10.1109\/CVPR.2017.71"},{"key":"3848_CR2","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1007\/s41095-019-0149-9","volume":"5","author":"A Borji","year":"2019","unstructured":"Borji, A., Cheng, M.M., Hou, Q., Jiang, H., Li, J.: Salient object detection: a survey. Comput. Vis. Media 5, 117\u2013150 (2019)","journal-title":"Comput. Vis. Media"},{"key":"3848_CR3","unstructured":"Chen, H., Liu, M., Zhang, L.: Br-net: Bidirectional channel attention for defocus blur detection. In: Proceedings of the European Conference on Computer Vision, pp. 1234\u20131245 (2022)"},{"key":"3848_CR4","unstructured":"Dao, T., Gu, A.: Transformers are ssms: Generalized models and efficient algorithms through structured state space duality (2024). arXiv preprint arXiv:2405.21060"},{"key":"3848_CR5","unstructured":"Dosovitskiy, A.: An image is worth 16x16 words: Transformers for image recognition at scale (2020). arXiv preprint arXiv:2010.11929"},{"key":"3848_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 (2022). arXiv preprint arXiv:2212.14052"},{"key":"3848_CR7","unstructured":"Gu, A., Dao, T.: Mamba: Linear-time sequence modeling with selective state spaces (2023). arXiv preprint arXiv:2312.00752"},{"key":"3848_CR8","first-page":"35971","volume":"35","author":"A Gu","year":"2022","unstructured":"Gu, A., Goel, K., Gupta, A., R\u00e9, C.: On the parameterization and initialization of diagonal state space models. Adv. Neural Inf. Process. Syst. 35, 35971\u201335983 (2022)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"3848_CR9","unstructured":"Gu, A., Goel, K., R\u00e9, C.: Efficiently modeling long sequences with structured state spaces (2021). arXiv preprint arXiv:2111.00396"},{"key":"3848_CR10","unstructured":"Gu, A., Johnson, I., Timalsina, A., Rudra, A., R\u00e9, C.: How to train your hippo: State space models with generalized orthogonal basis projections (2022). arXiv preprint arXiv:2206.12037"},{"key":"3848_CR11","first-page":"2345","volume":"32","author":"X Guo","year":"2023","unstructured":"Guo, X., Wang, J., Li, Y.: Depth and dof cues make a better defocus blur detector. IEEE Trans. Image Process. 32, 2345\u20132356 (2023)","journal-title":"IEEE Trans. Image Process."},{"key":"3848_CR12","unstructured":"Hasani, R., Lechner, M., Wang, T.H., Chahine, M., Amini, A., Rus, D.: Liquid structural state-space models (2022). arXiv preprint arXiv:2209.12951"},{"key":"3848_CR13","unstructured":"Heidari, M., Kolahi, S.G., Karimijafarbigloo, S., Azad, B., Bozorgpour, A., Hatami, S., Azad, R., Diba, A., Bagci, U., Merhof, D., et\u00a0al.: Computation-efficient era: A comprehensive survey of state space models in medical image analysis (2024). arXiv preprint arXiv:2406.03430"},{"key":"3848_CR14","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 (2024). arXiv preprint arXiv:2403.09338","DOI":"10.1007\/978-3-031-91979-4_2"},{"key":"3848_CR15","unstructured":"Kingma, D.P.: Adam: A method for stochastic optimization (2014). arXiv preprint arXiv:1412.6980"},{"key":"3848_CR16","doi-asserted-by":"publisher","unstructured":"Lee, J., Lee, S., Cho, S., Lee, S.: Deep defocus map estimation using domain adaptation. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12214\u201312222 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.01250","DOI":"10.1109\/CVPR.2019.01250"},{"key":"3848_CR17","unstructured":"Lei\u00a0Ba, J., Kiros, J.R., Hinton, G.E.: Layer normalization. ArXiv e-prints pp. arXiv\u20131607 (2016)"},{"key":"3848_CR18","doi-asserted-by":"crossref","unstructured":"Li, S., Singh, H., Grover, A.: Mamba-nd: Selective state space modeling for multi-dimensional data. In: European Conference on Computer Vision, pp. 75\u201392. Springer (2025)","DOI":"10.1007\/978-3-031-73414-4_5"},{"key":"3848_CR19","unstructured":"Lieber, O., Lenz, B., Bata, H., Cohen, G., Osin, J., Dalmedigos, I., Safahi, E., Meirom, S., Belinkov, Y., Shalev-Shwartz, S., et\u00a0al.: Jamba: A hybrid transformer-mamba language model (2024). arXiv preprint arXiv:2403.19887"},{"key":"3848_CR20","volume":"125","author":"M Liu","year":"2022","unstructured":"Liu, M., Chen, H., Zhang, L.: Improving defocus blur detection via adaptive supervision prior-tokens. Pattern Recognit. 125, 108504 (2022)","journal-title":"Pattern Recognit."},{"key":"3848_CR21","unstructured":"Liu, X., Zhang, C., Zhang, L.: Vision mamba: A comprehensive survey and taxonomy (2024). arXiv preprint arXiv:2405.04404"},{"key":"3848_CR22","unstructured":"Liu, Y., Tian, Y., Zhao, Y., Yu, H., Xie, L., Wang, Y., Ye, Q., Jiao, J., Liu, Y.: Vmamba: Visual state space model. In: The Thirty-eighth Annual Conference on Neural Information Processing Systems (2024)"},{"key":"3848_CR23","unstructured":"Ma, J., Li, F., Wang, B.: U-mamba: Enhancing long-range dependency for biomedical image segmentation (2024). arXiv preprint arXiv:2401.04722"},{"issue":"10","key":"3848_CR24","doi-asserted-by":"publisher","first-page":"5155","DOI":"10.1109\/TIP.2018.2847421","volume":"27","author":"K Ma","year":"2018","unstructured":"Ma, K., Fu, H., Liu, T., Wang, Z., Tao, D.: Deep blur mapping: exploiting high-level semantics by deep neural networks. IEEE Trans. Image Process. 27(10), 5155\u20135166 (2018)","journal-title":"IEEE Trans. Image Process."},{"key":"3848_CR25","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1016\/j.neucom.2020.12.089","volume":"438","author":"Y Ming","year":"2021","unstructured":"Ming, Y., Meng, X., Fan, C., Yu, H.: Deep learning for monocular depth estimation: a review. Neurocomputing 438, 14\u201333 (2021)","journal-title":"Neurocomputing"},{"key":"3848_CR26","unstructured":"Orvieto, A., Smith, S.L., Gu, A., Fernando, A., Gulcehre, C., Pascanu, R., De, S.: Resurrecting recurrent neural networks for long sequences. In: International Conference on Machine Learning, pp. 26670\u201326698. PMLR (2023)"},{"issue":"10","key":"3848_CR27","doi-asserted-by":"publisher","first-page":"2220","DOI":"10.1109\/TCYB.2015.2472478","volume":"46","author":"Y Pang","year":"2015","unstructured":"Pang, Y., Zhu, H., Li, X., Li, X.: Classifying discriminative features for blur detection. IEEE Trans. Cybern. 46(10), 2220\u20132227 (2015)","journal-title":"IEEE Trans. Cybern."},{"key":"3848_CR28","unstructured":"Park, J., Park, J., Xiong, Z., Lee, N., Cho, J., Oymak, S., Lee, K., Papailiopoulos, D.: Can mamba learn how to learn? a comparative study on in-context learning tasks. arXiv preprint arXiv:2402.04248 (2024)"},{"key":"3848_CR29","doi-asserted-by":"crossref","unstructured":"Park, J., Tai, Y.W., Cho, D., So\u00a0Kweon, I.: A unified approach of multi-scale deep and hand-crafted features for defocus estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.295"},{"key":"3848_CR30","unstructured":"Patro, B.N., Agneeswaran, V.S.: Simba: Simplified mamba-based architecture for vision and multivariate time series. arXiv preprint arXiv:2403.15360 (2024)"},{"key":"3848_CR31","doi-asserted-by":"crossref","unstructured":"Pei, X., Huang, T., Xu, C.: Efficientvmamba: Atrous selective scan for light weight visual mamba (2024). arXiv preprint arXiv:2403.09977","DOI":"10.1609\/aaai.v39i6.32690"},{"key":"3848_CR32","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: Convolutional networks for biomedical image segmentation. In: Medical image computing and computer-assisted intervention\u2013MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, proceedings, part III 18, pp. 234\u2013241. Springer (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"issue":"7","key":"3848_CR33","doi-asserted-by":"publisher","first-page":"3141","DOI":"10.1109\/TIP.2016.2555702","volume":"25","author":"E Saad","year":"2016","unstructured":"Saad, E., Hirakawa, K.: Defocus blur-invariant scale-space feature extractions. IEEE Trans. Image Process. 25(7), 3141\u20133156 (2016)","journal-title":"IEEE Trans. Image Process."},{"key":"3848_CR34","doi-asserted-by":"crossref","unstructured":"Shi, J., Xu, L., Jia, J.: Discriminative blur detection features. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2965\u20132972 (2014)","DOI":"10.1109\/CVPR.2014.379"},{"key":"3848_CR35","unstructured":"Smith, J.T., Warrington, A., Linderman, S.W.: Simplified state space layers for sequence modeling (2022). arXiv preprint arXiv:2208.04933"},{"key":"3848_CR36","doi-asserted-by":"crossref","unstructured":"Su, B., Lu, S., Tan, C.L.: Blurred image region detection and classification. In: Proceedings of the 19th ACM international conference on Multimedia, pp. 1397\u20131400 (2011)","DOI":"10.1145\/2072298.2072024"},{"issue":"2","key":"3848_CR37","doi-asserted-by":"publisher","first-page":"955","DOI":"10.1109\/TPAMI.2020.3014629","volume":"44","author":"C Tang","year":"2020","unstructured":"Tang, C., Liu, X., Zheng, X., Li, W., Xiong, J., Wang, L., Zomaya, A.Y., Longo, A.: Defusionnet: defocus blur detection via recurrently fusing and refining discriminative multi-scale deep features. IEEE Trans. Pattern Anal. Mach. Intell. 44(2), 955\u2013968 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"11","key":"3848_CR38","doi-asserted-by":"publisher","first-page":"1652","DOI":"10.1109\/LSP.2016.2611608","volume":"23","author":"C Tang","year":"2016","unstructured":"Tang, C., Wu, J., Hou, Y., Wang, P., Li, W.: A spectral and spatial approach of coarse-to-fine blurred image region detection. IEEE Signal Process. Lett. 23(11), 1652\u20131656 (2016)","journal-title":"IEEE Signal Process. Lett."},{"key":"3848_CR39","unstructured":"Ulyanov, D.: Instance normalization: The missing ingredient for fast stylization (2016). arXiv preprint arXiv:1607.08022"},{"key":"3848_CR40","unstructured":"Wang, J., Liu, Z., Chen, Y.: Defocus blur detection via multi-stream bottom-top-bottom fully convolutional network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9876\u20139885 (2020)"},{"key":"3848_CR41","doi-asserted-by":"publisher","unstructured":"Wang, Y., Huang, P., Han, L., Xu, C.: A relation-aware network for defocus blur detection. In: 2023 7th Asian Conference on Artificial Intelligence Technology (ACAIT), pp. 66\u201374 (2023). https:\/\/doi.org\/10.1109\/ACAIT60137.2023.10528486","DOI":"10.1109\/ACAIT60137.2023.10528486"},{"key":"3848_CR42","unstructured":"Xing, Z., Wan, L., Fu, H., Yang, G., Zhu, L.: Diff-unet: A diffusion embedded network for volumetric segmentation (2023). arXiv preprint arXiv:2303.10326"},{"key":"3848_CR43","doi-asserted-by":"crossref","unstructured":"Xing, Z., Yang, S., Chen, S., Ye, T., Yang, Y., Qin, J., Zhu, L.: Cross-conditioned diffusion model for medical image to image translation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 201\u2013211. Springer (2024)","DOI":"10.1007\/978-3-031-72104-5_20"},{"key":"3848_CR44","doi-asserted-by":"crossref","unstructured":"Xing, Z., Ye, T., Yang, Y., Liu, G., Zhu, L.: Segmamba: Long-range sequential modeling mamba for 3d medical image segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 578\u2013588. Springer (2024)","DOI":"10.1007\/978-3-031-72111-3_54"},{"key":"3848_CR45","doi-asserted-by":"crossref","unstructured":"Xing, Z., Yu, L., Wan, L., Han, T., Zhu, L.: Nestedformer: Nested modality-aware transformer for brain tumor segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 140\u2013150. Springer (2022)","DOI":"10.1007\/978-3-031-16443-9_14"},{"key":"3848_CR46","doi-asserted-by":"publisher","first-page":"2115","DOI":"10.1109\/JBHI.2024.3360239","volume":"28","author":"Z Xing","year":"2024","unstructured":"Xing, Z., Zhu, L., Yu, L., Xing, Z., Wan, L.: Hybrid masked image modeling for 3d medical image segmentation. IEEE J. Biomed. Health Inf. 28, 2115\u20132125 (2024)","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"3848_CR47","unstructured":"Xu, B.: Empirical evaluation of rectified activations in convolutional network (2015). arXiv preprint arXiv:1505.00853"},{"key":"3848_CR48","unstructured":"Yang, C., Chen, Z., Espinosa, M., Ericsson, L., Wang, Z., Liu, J., Crowley, E.J.: Plainmamba: Improving non-hierarchical mamba in visual recognition (2024). arXiv preprint arXiv:2403.17695"},{"issue":"13","key":"3848_CR49","doi-asserted-by":"publisher","first-page":"5683","DOI":"10.3390\/app14135683","volume":"14","author":"H Zhang","year":"2024","unstructured":"Zhang, H., Zhu, Y., Wang, D., Zhang, L., Chen, T., Wang, Z., Ye, Z.: A survey on visual mamba. Appl. Sci. 14(13), 5683 (2024)","journal-title":"Appl. Sci."},{"key":"3848_CR50","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Hirakawa, K.: Blur processing using double discrete wavelet transform. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1091\u20131098 (2013)","DOI":"10.1109\/CVPR.2013.145"},{"key":"3848_CR51","first-page":"1234","volume":"30","author":"Y Zhang","year":"2021","unstructured":"Zhang, Y., Li, J., Wang, X.: Defocus blur detection via depth distillation. IEEE Trans. Image Process. 30, 1234\u20131245 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"3848_CR52","doi-asserted-by":"crossref","unstructured":"Zhao, H., Zhang, M., Zhao, W., Ding, P., Huang, S., Wang, D.: Cobra: Extending mamba to multi-modal large language model for efficient inference (2024). arXiv preprint arXiv:2403.14520","DOI":"10.1609\/aaai.v39i10.33131"},{"key":"3848_CR53","doi-asserted-by":"publisher","first-page":"5426","DOI":"10.1109\/TIP.2021.3084101","volume":"30","author":"W Zhao","year":"2021","unstructured":"Zhao, W., Hou, X., He, Y., Lu, H.: Defocus blur detection via boosting diversity of deep ensemble networks. IEEE Trans. Image Process. 30, 5426\u20135438 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"3848_CR54","doi-asserted-by":"crossref","unstructured":"Zhao, W., Zhao, F., Wang, D., Lu, H.: Defocus blur detection via multi-stream bottom-top-bottom fully convolutional network. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 3080\u20133088 (2018)","DOI":"10.1109\/CVPR.2018.00325"},{"key":"3848_CR55","doi-asserted-by":"crossref","unstructured":"Zhao, W., Zheng, B., Lin, Q., Lu, H.: Enhancing diversity of defocus blur detectors via cross-ensemble network. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 8905\u20138913 (2019)","DOI":"10.1109\/CVPR.2019.00911"},{"key":"3848_CR56","first-page":"10234","volume":"45","author":"X Zhou","year":"2023","unstructured":"Zhou, X., Wang, Y., Li, J.: Defusionnet: recurrently fusing and refining multi-scale features for defocus blur detection. IEEE Trans. Pattern Anal. Mach. Intell. 45, 10234\u201310245 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3848_CR57","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). arXiv preprint arXiv:2401.09417"},{"issue":"9","key":"3848_CR58","doi-asserted-by":"publisher","first-page":"1852","DOI":"10.1016\/j.patcog.2011.03.009","volume":"44","author":"S Zhuo","year":"2011","unstructured":"Zhuo, S., Sim, T.: Defocus map estimation from a single image. Pattern Recognit. 44(9), 1852\u20131858 (2011)","journal-title":"Pattern Recognit."},{"key":"3848_CR59","unstructured":"Zou, Y., Chen, Y., Li, Z., Zhang, L., Zhao, H.: Venturing into uncharted waters: The navigation compass from transformer to mamba (2024). arXiv preprint arXiv:2406.16722"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-03848-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-025-03848-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-03848-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T07:37:47Z","timestamp":1757144267000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-025-03848-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,11]]},"references-count":59,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2025,8]]}},"alternative-id":["3848"],"URL":"https:\/\/doi.org\/10.1007\/s00371-025-03848-2","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-5719588\/v1","asserted-by":"object"}]},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,11]]},"assertion":[{"value":"11 February 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 March 2025","order":2,"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 no competing interests","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}