{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T15:22:07Z","timestamp":1772119327467,"version":"3.50.1"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2024,10,9]],"date-time":"2024-10-09T00:00:00Z","timestamp":1728432000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,9]],"date-time":"2024-10-09T00:00:00Z","timestamp":1728432000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"China government project","award":["No.YCKYXM-07-2021"],"award-info":[{"award-number":["No.YCKYXM-07-2021"]}]},{"name":"China government project","award":["No.2023SFGC0101"],"award-info":[{"award-number":["No.2023SFGC0101"]}]},{"name":"China government project","award":["No.ZR2023QE118"],"award-info":[{"award-number":["No.ZR2023QE118"]}]},{"name":"China government project","award":["No.2023SFGC0101"],"award-info":[{"award-number":["No.2023SFGC0101"]}]},{"name":"China government project","award":["No.2023SFGC0101"],"award-info":[{"award-number":["No.2023SFGC0101"]}]},{"name":"Key Technology R&D Program of Shandong","award":["No.2022CXGC020701"],"award-info":[{"award-number":["No.2022CXGC020701"]}]},{"name":"Key Technology R&D Program of Shandong","award":["No.2023JMRH0306"],"award-info":[{"award-number":["No.2023JMRH0306"]}]},{"name":"Key Technology R&D Program of Shandong","award":["No.2022CXGC020701"],"award-info":[{"award-number":["No.2022CXGC020701"]}]},{"name":"Key Technology R&D Program of Shandong","award":["No.2022CXGC020701"],"award-info":[{"award-number":["No.2022CXGC020701"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1007\/s00371-024-03654-2","type":"journal-article","created":{"date-parts":[[2024,10,9]],"date-time":"2024-10-09T15:01:58Z","timestamp":1728486118000},"page":"4183-4198","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Spatial-frequency attention-based optical and scene flow with cross-modal knowledge distillation"],"prefix":"10.1007","volume":"41","author":[{"given":"Youjie","family":"Zhou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Runyu","family":"Jiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhonghan","family":"Tao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xichang","family":"Liang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Wan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,9]]},"reference":[{"key":"3654_CR1","doi-asserted-by":"crossref","unstructured":"Dosovitskiy, A., Fischer, P., Ilg, E., Hausser, P., Hazirbas, C., Golkov, V., Van Der\u00a0Smagt, P., Cremers, D., Brox, T.: Flownet: learning optical flow with convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2758\u20132766 (2015)","DOI":"10.1109\/ICCV.2015.316"},{"key":"3654_CR2","doi-asserted-by":"crossref","unstructured":"Teed, Z., Deng, J.: Raft: recurrent all-pairs field transforms for optical flow. In: Computer Vision\u2014ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part II 16, pp. 402\u2013419. Springer (2020)","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"3654_CR3","doi-asserted-by":"crossref","unstructured":"Liu, X., Qi, C.R., Guibas, L.J.: Flownet3d: learning scene flow in 3d point clouds. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 529\u2013537 (2019)","DOI":"10.1109\/CVPR.2019.00062"},{"key":"3654_CR4","doi-asserted-by":"crossref","unstructured":"Teed, Z., Deng, J.: Raft-3d: scene flow using rigid-motion embeddings. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8375\u20138384 (2021)","DOI":"10.1109\/CVPR46437.2021.00827"},{"key":"3654_CR5","doi-asserted-by":"crossref","unstructured":"Zhang, T., Zhang, H., Li, Y., Nakamura, Y., Zhang, L.: Flowfusion: dynamic dense rgb-d slam based on optical flow. In: 2020 International Conference on Robotics and Automation (ICRA), pp. 7322\u20137328. IEEE (2020)","DOI":"10.1109\/ICRA40945.2020.9197349"},{"key":"3654_CR6","first-page":"16558","volume":"34","author":"Z Teed","year":"2021","unstructured":"Teed, Z., Deng, J.: Droid-slam: deep visual slam for monocular, stereo, and rgb-d cameras. Adv. Neural Inf. Process. Syst. 34, 16558\u201316569 (2021)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"3654_CR7","doi-asserted-by":"crossref","unstructured":"Zhu, H., Bai, S., Shi, J., Wang, C., Sun, Y., Lu, J., Shu, X., Huang, S.: Iofusion: instance segmentation and optical-flow guided 3d reconstruction in dynamic scenes. In: The Visual Computer, pp. 1\u201315 (2024)","DOI":"10.1007\/s00371-024-03365-8"},{"key":"3654_CR8","doi-asserted-by":"crossref","unstructured":"Sevilla-Lara, L., Liao, Y., G\u00fcney, F., Jampani, V., Geiger, A., Black, M.J.: On the integration of optical flow and action recognition. In: Pattern Recognition: 40th German Conference, GCPR 2018, Stuttgart, Germany, October 9\u201312, 2018, Proceedings 40, pp. 281\u2013297. Springer (2019)","DOI":"10.1007\/978-3-030-12939-2_20"},{"key":"3654_CR9","doi-asserted-by":"crossref","unstructured":"Sun, S., Kuang, Z., Sheng, L., Ouyang, W., Zhang, W.: Optical flow guided feature: a fast and robust motion representation for video action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1390\u20131399 (2018)","DOI":"10.1109\/CVPR.2018.00151"},{"key":"3654_CR10","doi-asserted-by":"crossref","unstructured":"Jiang, S., Campbell, D., Lu, Y., Li, H., Hartley, R.: Learning to estimate hidden motions with global motion aggregation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9772\u20139781 (2021)","DOI":"10.1109\/ICCV48922.2021.00963"},{"key":"3654_CR11","doi-asserted-by":"crossref","unstructured":"Sui, X., Li, S., Geng, X., Wu, Y., Xu, X., Liu, Y., Goh, R., Zhu, H.: Craft: cross-attentional flow transformer for robust optical flow. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17602\u201317611 (2022)","DOI":"10.1109\/CVPR52688.2022.01708"},{"key":"3654_CR12","doi-asserted-by":"crossref","unstructured":"Liu, H., Lu, T., Xu, Y., Liu, J., Li, W., Chen, L.: Camliflow: bidirectional camera-lidar fusion for joint optical flow and scene flow estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5791\u20135801 (2022)","DOI":"10.1109\/CVPR52688.2022.00570"},{"key":"3654_CR13","doi-asserted-by":"crossref","unstructured":"Liu, H., Tao, L., Yihui, X., Liu, J., Wang, L.: Learning optical flow and scene flow with bidirectional camera-lidar fusion. IEEE Trans. Pattern Anal. Mach. Intell. 46(4), 2378\u20132395 (2023)","DOI":"10.1109\/TPAMI.2023.3330866"},{"key":"3654_CR14","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol.\u00a030 (2017)"},{"key":"3654_CR15","doi-asserted-by":"crossref","unstructured":"Sun, D., Yang, X., Liu, M.-Y., Kautz, J.: Pwc-net: Cnns for optical flow using pyramid, warping, and cost volume. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8934\u20138943 (2018)","DOI":"10.1109\/CVPR.2018.00931"},{"key":"3654_CR16","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Mei, G., Wang, Y., Poiesi, F., Wan, Y.: Attentive multimodal fusion for optical and scene flow. IEEE Robot. Autom. Lett. 8(10), 6091\u20136098 (2023)","DOI":"10.1109\/LRA.2023.3300252"},{"issue":"8","key":"3654_CR17","doi-asserted-by":"publisher","first-page":"4499","DOI":"10.1109\/TNNLS.2021.3116209","volume":"34","author":"Z Xie","year":"2021","unstructured":"Xie, Z., Zhang, W., Sheng, B., Li, P., Chen, C.P.: Bagfn: broad attentive graph fusion network for high-order feature interactions. IEEE Trans. Neural Netw. Learn. Syst. 34(8), 4499\u20134513 (2021)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"3654_CR18","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1109\/TMM.2021.3120873","volume":"25","author":"X Lin","year":"2021","unstructured":"Lin, X., Sun, S., Huang, W., Sheng, B., Li, P., Feng, D.D.: Eapt: efficient attention pyramid transformer for image processing. IEEE Trans. Multimed. 25, 50\u201361 (2021)","journal-title":"IEEE Trans. Multimed."},{"key":"3654_CR19","doi-asserted-by":"crossref","unstructured":"Li, L., Chen, Z., Dai, L., Li, R., Sheng, B.: Ma-mfcnet: mixed attention-based multi-scale feature calibration network for image dehazing. IEEE Trans. Emerg. Top. Comput. Intell. 8(5), 3408\u20133421 (2024)","DOI":"10.1109\/TETCI.2024.3382233"},{"key":"3654_CR20","doi-asserted-by":"crossref","unstructured":"Kong, L., Dong, J., Ge, J., Li, M., Pan, J.: Efficient frequency domain-based transformers for high-quality image deblurring. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5886\u20135895 (2023)","DOI":"10.1109\/CVPR52729.2023.00570"},{"issue":"01","key":"3654_CR21","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1109\/MCISE.2000.814652","volume":"2","author":"J Dongarra","year":"2000","unstructured":"Dongarra, J., Sullivan, F.: Guest editors introduction to the top 10 algorithms. Comput. Sci. Eng. 2(01), 22\u201323 (2000)","journal-title":"Comput. Sci. Eng."},{"key":"3654_CR22","doi-asserted-by":"crossref","unstructured":"Mayer, N., Ilg, E., Hausser, P., Fischer, P., Cremers, D., Dosovitskiy, A., Brox, T.: A large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4040\u20134048 (2016)","DOI":"10.1109\/CVPR.2016.438"},{"issue":"11","key":"3654_CR23","doi-asserted-by":"publisher","first-page":"1231","DOI":"10.1177\/0278364913491297","volume":"32","author":"A Geiger","year":"2013","unstructured":"Geiger, A., Lenz, P., Stiller, C., Urtasun, R.: Vision meets robotics: the kitti dataset. Int. J. Robot. Res. 32(11), 1231\u20131237 (2013)","journal-title":"Int. J. Robot. Res."},{"key":"3654_CR24","doi-asserted-by":"crossref","unstructured":"Brox, T., Bregler, C., Malik, J.: Large displacement optical flow. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 41\u201348. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206697"},{"key":"3654_CR25","doi-asserted-by":"crossref","unstructured":"Weinzaepfel, P., Revaud, J., Harchaoui, Z., Schmid, C.: Deepflow: large displacement optical flow with deep matching. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1385\u20131392 (2013)","DOI":"10.1109\/ICCV.2013.175"},{"key":"3654_CR26","doi-asserted-by":"crossref","unstructured":"Ilg, E., Mayer, N., Saikia, T., Keuper, M., Dosovitskiy, A., Brox, T.: Flownet 2.0: evolution of optical flow estimation with deep networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2462\u20132470 (2017)","DOI":"10.1109\/CVPR.2017.179"},{"key":"3654_CR27","doi-asserted-by":"crossref","unstructured":"Zhang, F., Woodford, O.J., Prisacariu, V.A., Torr, P.H.S.: Separable flow: learning motion cost volumes for optical flow estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10807\u201310817 (2021)","DOI":"10.1109\/ICCV48922.2021.01063"},{"key":"3654_CR28","doi-asserted-by":"crossref","unstructured":"Jaimez, M., Souiai, M., Gonzalez-Jimenez, J., Cremers, D.: A primal\u2013dual framework for real-time dense rgb-d scene flow. In: 2015 International Conference on Robotics and Automation (ICRA), pp. 98\u2013104. IEEE (2015)","DOI":"10.1109\/ICRA.2015.7138986"},{"key":"3654_CR29","doi-asserted-by":"crossref","unstructured":"Quiroga, J., Brox, T., Devernay, F., Crowley, J.: Dense semi-rigid scene flow estimation from rgbd images. In: Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6\u201312, 2014, Proceedings, Part VII 13, pp. 567\u2013582. Springer (2014)","DOI":"10.1007\/978-3-319-10584-0_37"},{"key":"3654_CR30","unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: Pointnet++: deep hierarchical feature learning on point sets in a metric space. Adv. Neural Inf. Process. Syst. 30, 5105\u20135114 (2017)"},{"key":"3654_CR31","doi-asserted-by":"crossref","unstructured":"Wang, Z., Li, S., Howard-Jenkins, H., Prisacariu, V., Chen, M.: Flownet3d++: geometric losses for deep scene flow estimation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 91\u201398 (2020)","DOI":"10.1109\/WACV45572.2020.9093302"},{"key":"3654_CR32","unstructured":"Wu, W., Wang, Z., Li, Z., Liu, W., Fuxin, L.: Pointpwc-net: a coarse-to-fine network for supervised and self-supervised scene flow estimation on 3d point clouds. arXiv preprint arXiv:1911.12408 (2019)"},{"key":"3654_CR33","first-page":"509","volume":"587","author":"J Wagner","year":"2016","unstructured":"Wagner, J., Fischer, V., Herman, M., Behnke, S., et al.: Multispectral pedestrian detection using deep fusion convolutional neural networks. ESANN 587, 509\u2013514 (2016)","journal-title":"ESANN"},{"key":"3654_CR34","doi-asserted-by":"crossref","unstructured":"Konig, D., Adam, M., Jarvers, C., Layher, G., Neumann, H., Teutsch, M.: Fully convolutional region proposal networks for multispectral person detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 49\u201356 (2017)","DOI":"10.1109\/CVPRW.2017.36"},{"key":"3654_CR35","doi-asserted-by":"publisher","unstructured":"Wang, S., Liu, J., Zhang, S., Metaxas, D.: Multispectral deep neural networks for pedestrian detection. In: Proceedings of the British Machine Vision Conference (BMVC), pp. 73.1\u201373.13. BMVA Press, September (2016). https:\/\/doi.org\/10.5244\/C.30.73","DOI":"10.5244\/C.30.73"},{"key":"3654_CR36","doi-asserted-by":"crossref","unstructured":"Chen, Y.-T., Shi, J., Ye, Z., Mertz, C., Ramanan, D., Kong, S.: Multimodal object detection via probabilistic ensembling. In: Proceedings of European Conference on Computer Vision, pp. 139\u2013158. Springer (2022)","DOI":"10.1007\/978-3-031-20077-9_9"},{"key":"3654_CR37","doi-asserted-by":"crossref","unstructured":"Rishav, R., Battrawy, R., Schuster, R., Wasenm\u00fcller, O., Stricker, D.: Deeplidarflow: a deep learning architecture for scene flow estimation using monocular camera and sparse lidar. In: 2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 10460\u201310467. IEEE (2020)","DOI":"10.1109\/IROS45743.2020.9341077"},{"key":"3654_CR38","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. In: NIPS Deep Learning and Representation Learning Workshop (2015)"},{"key":"3654_CR39","doi-asserted-by":"crossref","unstructured":"Peng, Z., Li, Z., Zhang, J., Li, Y., Qi, G.-J., Tang, J.: Few-shot image recognition with knowledge transfer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 441\u2013449 (2019)","DOI":"10.1109\/ICCV.2019.00053"},{"issue":"7","key":"3654_CR40","doi-asserted-by":"publisher","first-page":"2415","DOI":"10.1109\/TMI.2019.2963882","volume":"39","author":"Q Dou","year":"2020","unstructured":"Dou, Q., Liu, Q., Heng, P.A., Glocker, B.: Unpaired multi-modal segmentation via knowledge distillation. IEEE Trans. Med. Imaging 39(7), 2415\u20132425 (2020)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"3654_CR41","doi-asserted-by":"crossref","unstructured":"Kang, M., Zhang, J., Zhang, J., Wang, X., Chen, Y., Ma, Z., Huang, X.: Alleviating catastrophic forgetting of incremental object detection via within-class and between-class knowledge distillation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 18894\u201318904 (2023)","DOI":"10.1109\/ICCV51070.2023.01732"},{"key":"3654_CR42","doi-asserted-by":"crossref","unstructured":"Wang, Z., Li, D., Luo, C., Xie, C., Yang, X.: Distillbev: boosting multi-camera 3d object detection with cross-modal knowledge distillation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8637\u20138646 (2023)","DOI":"10.1109\/ICCV51070.2023.00793"},{"key":"3654_CR43","unstructured":"Wang, W., Zhu, D., Wang, X., et\u00a0al.: TartanAir: a dataset to push the limits of visual slam. In: IROS, October (2012)"},{"key":"3654_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, F., Prisacariu, V., Yang, R., Torr, P.H.S.: Ga-net: guided aggregation net for end-to-end stereo matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 185\u2013194 (2019)","DOI":"10.1109\/CVPR.2019.00027"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03654-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-024-03654-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03654-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,16]],"date-time":"2025-04-16T06:21:27Z","timestamp":1744784487000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-024-03654-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,9]]},"references-count":44,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,4]]}},"alternative-id":["3654"],"URL":"https:\/\/doi.org\/10.1007\/s00371-024-03654-2","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-4712095\/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":[[2024,10,9]]},"assertion":[{"value":"10 September 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 October 2024","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 that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Written informed consent was obtained from all the participants prior to the enrollment (or for the publication) of this study.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}}]}}