{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T07:22:31Z","timestamp":1783581751325,"version":"3.55.0"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2025,2,20]],"date-time":"2025-02-20T00:00:00Z","timestamp":1740009600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,2,20]],"date-time":"2025-02-20T00:00:00Z","timestamp":1740009600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"National Natural Science Foundation of China Youth Fund","award":["62302462"],"award-info":[{"award-number":["62302462"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1007\/s00371-025-03837-5","type":"journal-article","created":{"date-parts":[[2025,2,19]],"date-time":"2025-02-19T23:36:53Z","timestamp":1740008213000},"page":"7767-7780","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Lightweight multi-scale feature fusion with attention guidance for passive non-line-of-sight imaging"],"prefix":"10.1007","volume":"41","author":[{"given":"Pengyun","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuang","family":"Cui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ning","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenhao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengfei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaohui","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingliang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,2,20]]},"reference":[{"issue":"23","key":"3837_CR1","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.132.233802","volume":"132","author":"X Huang","year":"2024","unstructured":"Huang, X., Ye, R., Li, W., Zeng, J.-W., Lu, Y.-C., Hu, H., Zhou, Y., Hou, L., Li, Z.-P., Jiang, H.-F.: Non-line-of-sight imaging and vibrometry using a comb-calibrated coherent sensor. Phys. Rev. Lett. 132(23), 233802 (2024)","journal-title":"Phys. Rev. Lett."},{"key":"3837_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103106","volume":"94","author":"Y Ma","year":"2024","unstructured":"Ma, Y., Zhou, W., Ma, R., Wang, E., Yang, S., Tang, Y., Zhang, X.-P., Guan, X.: Dove: doodled vessel enhancement for photoacoustic angiography super resolution. Med. Image Anal. 94, 103106 (2024)","journal-title":"Med. Image Anal."},{"key":"3837_CR3","unstructured":"Ramesh, R., Davis, J.: 5d time-light transport matrix: What can we reason about scene properties? Technical report (2008)"},{"key":"3837_CR4","doi-asserted-by":"crossref","unstructured":"Kirmani, A., Hutchison, T., Davis, J., Raskar, R.: Looking around the corner using transient imaging. In: 2009 IEEE 12th International Conference on Computer Vision, pp. 159\u2013166, IEEE (2009)","DOI":"10.1109\/ICCV.2009.5459160"},{"key":"3837_CR5","doi-asserted-by":"publisher","DOI":"10.1007\/s12204-023-2686-8","author":"M Liu","year":"2024","unstructured":"Liu, M., Liu, H., He, X., Jin, S., Chen, P., Xu, M.: Research advances on non-line-of-sight imaging technology. J. Shanghai Jiaotong Univ. (Sci.) (2024). https:\/\/doi.org\/10.1007\/s12204-023-2686-8","journal-title":"J. Shanghai Jiaotong Univ. (Sci.)"},{"key":"3837_CR6","doi-asserted-by":"crossref","unstructured":"Tanaka, K., Mukaigawa, Y., Kadambi, A.: Polarized non-line-of-sight imaging. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2136\u20132145 (2020)","DOI":"10.1109\/CVPR42600.2020.00221"},{"key":"3837_CR7","doi-asserted-by":"crossref","unstructured":"Chen, W., Daneau, S., Mannan, F., Heide, F.: Steady-state non-line-of-sight imaging. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6790\u20136799 (2019)","DOI":"10.1109\/CVPR.2019.00695"},{"key":"3837_CR8","doi-asserted-by":"crossref","unstructured":"Yedidia, A.B., Baradad, M., Thrampoulidis, C., Freeman, W.T., Wornell, G.W.: Using unknown occluders to recover hidden scenes. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12231\u201312239 (2019)","DOI":"10.1109\/CVPR.2019.01251"},{"issue":"1","key":"3837_CR9","doi-asserted-by":"publisher","first-page":"6647","DOI":"10.1038\/s41467-021-26776-w","volume":"12","author":"F Willomitzer","year":"2021","unstructured":"Willomitzer, F., Rangarajan, P.V., Li, F., Balaji, M.M., Christensen, M.P., Cossairt, O.: Fast non-line-of-sight imaging with high-resolution and wide field of view using synthetic wavelength holography. Nat. Commun. 12(1), 6647 (2021)","journal-title":"Nat. Commun."},{"issue":"26","key":"3837_CR10","doi-asserted-by":"publisher","first-page":"44113","DOI":"10.1364\/OE.507875","volume":"31","author":"H Liu","year":"2023","unstructured":"Liu, H., Wang, P., He, X., Chen, M., Liu, M., Xu, Z., Jiang, X., Peng, X., Xu, M.: PI-NLOS: polarized infrared non-line-of-sight imaging. Opt. Express 31(26), 44113\u201344126 (2023)","journal-title":"Opt. Express"},{"key":"3837_CR11","first-page":"17117","volume":"36","author":"Y Wang","year":"2023","unstructured":"Wang, Y., Li, Y., Cui, Z.: Incomplete multimodality-diffused emotion recognition. Adv. Neural Inf. Process. Syst. 36, 17117\u201317128 (2023)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"3837_CR12","unstructured":"Zhou, C., Wang, C.-Y., Liu, Z.: Non-line-of-sight imaging off a Phong surface through deep learning. arXiv preprint arXiv:2005.00007 (2020)"},{"issue":"20","key":"3837_CR13","doi-asserted-by":"publisher","first-page":"34807","DOI":"10.1364\/OE.532699","volume":"32","author":"M Chen","year":"2024","unstructured":"Chen, M., Liu, H., Jin, S., Liu, M., Xu, Z., Jiang, X., xu, M.L.: Hyper-NLOS: hyperspectral passive non-line-of-sight imaging. Opt. Express 32(20), 34807\u201334824 (2024)","journal-title":"Opt. Express"},{"key":"3837_CR14","unstructured":"Wang, Y., Li, Y., Liu, M., Zhang, X., Liu, X., Cui, Z., Chan, A.B.: Re-attentional controllable video diffusion editing. arXiv preprint arXiv:2412.11710 (2024)"},{"key":"3837_CR15","doi-asserted-by":"crossref","unstructured":"Wang, Y., Lu, T., Yao, Y., Zhang, Y., Xiong, Z.: Learning to hallucinate face in the dark. IEEE Transactions on Multimedia (2023)","DOI":"10.1109\/TMM.2023.3294808"},{"key":"3837_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2024.102919","volume":"154","author":"J Li","year":"2024","unstructured":"Li, J., Zhang, P., Yang, X., Zhu, L., Wang, T., Zhang, P., Liu, R., Sheng, B., Wang, K.: SSM-NET: semi-supervised multi-task network for joint lesion segmentation and classification from pancreatic EUS images. Artif. Intell. Med. 154, 102919 (2024)","journal-title":"Artif. Intell. Med."},{"issue":"3","key":"3837_CR17","doi-asserted-by":"publisher","first-page":"329","DOI":"10.37936\/ecti-cit.2024183.255679","volume":"18","author":"A Dey","year":"2024","unstructured":"Dey, A., Biswas, S., Abualigah, L.: Efficient violence recognition in video streams using resDLCNN-GRU attention network. ECTI Trans. Comput. Inf. Technol. (ECTI-CIT) 18(3), 329\u2013341 (2024)","journal-title":"ECTI Trans. Comput. Inf. Technol. (ECTI-CIT)"},{"issue":"3","key":"3837_CR18","doi-asserted-by":"publisher","first-page":"1697","DOI":"10.1007\/s00371-023-02880-4","volume":"40","author":"H Zhao","year":"2024","unstructured":"Zhao, H., Zheng, J., Shang, X., Zhong, W., Liu, J.: Coarse-to-fine multi-scale attention-guided network for multi-exposure image fusion. Visual Comput. 40(3), 1697\u20131710 (2024)","journal-title":"Visual Comput."},{"issue":"6","key":"3837_CR19","doi-asserted-by":"publisher","first-page":"2533","DOI":"10.1109\/TCSVT.2022.3224940","volume":"33","author":"Y Wang","year":"2022","unstructured":"Wang, Y., Lu, T., Zhang, Y., Wang, Z., Jiang, J., Xiong, Z.: FaceFormer: aggregating global and local representation for face hallucination. IEEE Trans. Circuits Syst. Video Technol. 33(6), 2533\u20132545 (2022)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"7","key":"3837_CR20","doi-asserted-by":"publisher","first-page":"2969","DOI":"10.1007\/s00371-022-02503-4","volume":"39","author":"G Wang","year":"2023","unstructured":"Wang, G., Gan, X., Cao, Q., Zhai, Q.: MFANet: multi-scale feature fusion network with attention mechanism. Visual Comput. 39(7), 2969\u20132980 (2023)","journal-title":"Visual Comput."},{"key":"3837_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2023.105534","volume":"87","author":"X Huo","year":"2024","unstructured":"Huo, X., Sun, G., Tian, S., Wang, Y., Yu, L., Long, J., Zhang, W., Li, A.: HiFuse: Hierarchical multi-scale feature fusion network for medical image classification. Biomed. Signal Process. Control 87, 105534 (2024)","journal-title":"Biomed. Signal Process. Control"},{"key":"3837_CR22","doi-asserted-by":"crossref","unstructured":"Cho, S.-J., Ji, S.-W., Hong, J.-P., Jung, S.-W., Ko, S.-J.: Rethinking coarse-to-fine approach in single image deblurring. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4641\u20134650 (2021)","DOI":"10.1109\/ICCV48922.2021.00460"},{"key":"3837_CR23","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.123179","volume":"246","author":"BA Kumar","year":"2024","unstructured":"Kumar, B.A., Misra, N.K.: Masked face age and gender identification using caffe-modified mobilenetv2 on photo and real-time video images by transfer learning and deep learning techniques. Expert Syst. Appl. 246, 123179 (2024)","journal-title":"Expert Syst. Appl."},{"issue":"2","key":"3837_CR24","doi-asserted-by":"publisher","first-page":"935","DOI":"10.3390\/app13020935","volume":"13","author":"BA Kumar","year":"2023","unstructured":"Kumar, B.A., Bansal, M.: Face mask detection on photo and real-time video images using caffe-mobilenetv2 transfer learning. Appl. Sci. 13(2), 935 (2023)","journal-title":"Appl. Sci."},{"key":"3837_CR25","doi-asserted-by":"publisher","first-page":"1013","DOI":"10.1007\/s11263-020-01407-x","volume":"129","author":"Y Zhang","year":"2021","unstructured":"Zhang, Y., Guo, X., Ma, J., Liu, W., Zhang, J.: Beyond brightening low-light images. Int. J. Comput. Vis. 129, 1013\u20131037 (2021)","journal-title":"Int. J. Comput. Vis."},{"key":"3837_CR26","doi-asserted-by":"crossref","unstructured":"Wang, Y., Wan, R., Yang, W., Li, H., Chau, L.-P., Kot, A.: Low-light image enhancement with normalizing flow. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp. 2604\u20132612 (2022)","DOI":"10.1609\/aaai.v36i3.20162"},{"issue":"7","key":"3837_CR27","doi-asserted-by":"publisher","first-page":"0711002","DOI":"10.3788\/AOS201939.0711002","volume":"39","author":"T Yu","year":"2019","unstructured":"Yu, T., Qiao, M., Liu, H., Han, S.: Non-line-of-sight imaging through deep learning. Acta Opt. Sinica 39(7), 0711002 (2019)","journal-title":"Acta Opt. Sinica"},{"issue":"1","key":"3837_CR28","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1038\/s42005-021-00588-2","volume":"4","author":"Y Wang","year":"2021","unstructured":"Wang, Y., Zhang, Y., Huang, M., Chen, Z., Jia, Y., Weng, Y., Xiao, L., Xiang, X.: Accurate but fragile passive non-line-of-sight recognition. Commun. Phys. 4(1), 88 (2021)","journal-title":"Commun. Phys."},{"key":"3837_CR29","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1109\/TIP.2021.3128312","volume":"31","author":"R Geng","year":"2021","unstructured":"Geng, R., Hu, Y., Lu, Z., Yu, C., Li, H., Zhang, H., Chen, Y.: Passive non-line-of-sight imaging using optimal transport. IEEE Trans. Image Process. 31, 110\u2013124 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"3837_CR30","unstructured":"Zhang, J., Geng, R., Du, X., Chen, Y., Li, H., Hu, Y.: Passive non-line-of-sight imaging with light transport modulation. arXiv preprint arXiv:2312.16014 (2023)"},{"issue":"1","key":"3837_CR31","doi-asserted-by":"publisher","first-page":"2201","DOI":"10.1002\/cav.2201","volume":"35","author":"X Zhu","year":"2024","unstructured":"Zhu, X., Yao, X., Zhang, J., Zhu, M., You, L., Yang, X., Zhang, J., Zhao, H., Zeng, D.: TMSDNet: Transformer with multi-scale dense network for single and multi-view 3D reconstruction. Comput. Anim. Virtual Worlds 35(1), 2201 (2024)","journal-title":"Comput. Anim. Virtual Worlds"},{"issue":"10","key":"3837_CR32","doi-asserted-by":"publisher","first-page":"7399","DOI":"10.1007\/s00371-024-03598-7","volume":"40","author":"Y Sun","year":"2024","unstructured":"Sun, Y., Xie, X., Li, Z., Yang, K.: Batch-transformer for scene text image super-resolution. Visual Comput. 40(10), 7399\u20137409 (2024)","journal-title":"Visual Comput."},{"issue":"4","key":"3837_CR33","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1016\/j.vrih.2023.06.011","volume":"6","author":"X Senhua","year":"2024","unstructured":"Senhua, X., Liqing, G., Liang, W., Wei, F.: Multi-scale context-aware network for continuous sign language recognition. Virtual Real. Intell. Hardw. 6(4), 323\u2013337 (2024)","journal-title":"Virtual Real. Intell. Hardw."},{"key":"3837_CR34","doi-asserted-by":"crossref","unstructured":"Wang, Z., Cun, X., Bao, J., Zhou, W., Liu, J., Li, H.: Uformer: A general u-shaped transformer for image restoration. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17683\u201317693 (2022)","DOI":"10.1109\/CVPR52688.2022.01716"},{"key":"3837_CR35","unstructured":"Peng, Y., Sonka, M., Chen, D.Z.: U-net v2: Rethinking the skip connections of u-net for medical image segmentation. arXiv preprint arXiv:2311.17791 (2023)"},{"key":"3837_CR36","doi-asserted-by":"crossref","unstructured":"Wu, H., Wang, M., Zhou, W., Lu, Z., Li, H.: Asymmetric feature fusion for image retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11082\u201311092 (2023)","DOI":"10.1109\/CVPR52729.2023.01066"},{"issue":"8","key":"3837_CR37","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":"3837_CR38","doi-asserted-by":"publisher","first-page":"6821","DOI":"10.1109\/TMM.2022.3214776","volume":"25","author":"J Zhu","year":"2022","unstructured":"Zhu, J., Zhang, Q., Fei, L., Cai, R., Xie, Y., Sheng, B., Yang, X.: FFFN: Frame-by-frame feedback fusion network for video super-resolution. IEEE Trans. Multimed. 25, 6821\u20136835 (2022)","journal-title":"IEEE Trans. Multimed."},{"key":"3837_CR39","doi-asserted-by":"publisher","first-page":"1002","DOI":"10.1109\/TIP.2024.3354108","volume":"33","author":"Z Chen","year":"2024","unstructured":"Chen, Z., He, Z., Lu, Z.-M.: DEA-Net: single image dehazing based on detail-enhanced convolution and content-guided attention. IEEE Trans. Image Process. 33, 1002 (2024)","journal-title":"IEEE Trans. Image Process."},{"key":"3837_CR40","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":"3837_CR41","doi-asserted-by":"crossref","unstructured":"Yuan, K., Guo, S., Liu, Z., Zhou, A., Yu, F., Wu, W.: Incorporating convolution designs into visual transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 579\u2013588 (2021)","DOI":"10.1109\/ICCV48922.2021.00062"},{"key":"3837_CR42","doi-asserted-by":"crossref","unstructured":"Wu, H., Xiao, B., Codella, N., Liu, M., Dai, X., Yuan, L., Zhang, L.: Cvt: Introducing convolutions to vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 22\u201331 (2021)","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"3837_CR43","unstructured":"Li, Y., Zhang, K., Cao, J., Timofte, R., Van\u00a0Gool, L.: Localvit: Bringing locality to vision transformers. arXiv preprint arXiv:2104.05707 (2021)"},{"key":"3837_CR44","unstructured":"Hendrycks, D., Gimpel, K.: Gaussian error linear units (gelus). arXiv preprint arXiv:1606.08415 (2016)"},{"key":"3837_CR45","doi-asserted-by":"crossref","unstructured":"Wu, G., Jiang, J., Jiang, K., Liu, X.: Fully 1$$\\times $$ 1 convolutional network for lightweight image super-resolution. Machine Intelligence Research, pp. 1\u201315 (2024)","DOI":"10.1007\/s11633-024-1501-9"},{"key":"3837_CR46","doi-asserted-by":"publisher","first-page":"1927","DOI":"10.1109\/TIP.2023.3256763","volume":"32","author":"Y Song","year":"2023","unstructured":"Song, Y., He, Z., Qian, H., Du, X.: Vision transformers for single image dehazing. IEEE Trans. Image Process. 32, 1927\u20131941 (2023)","journal-title":"IEEE Trans. Image Process."}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-03837-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-025-03837-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-03837-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T06:10:38Z","timestamp":1757139038000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-025-03837-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,20]]},"references-count":46,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2025,8]]}},"alternative-id":["3837"],"URL":"https:\/\/doi.org\/10.1007\/s00371-025-03837-5","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,20]]},"assertion":[{"value":"30 January 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 February 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 conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}