{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,17]],"date-time":"2026-01-17T04:04:15Z","timestamp":1768622655816,"version":"3.49.0"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"S1","license":[{"start":{"date-parts":[[2024,5,4]],"date-time":"2024-05-04T00:00:00Z","timestamp":1714780800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,5,4]],"date-time":"2024-05-04T00:00:00Z","timestamp":1714780800000},"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":["SIViP"],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1007\/s11760-024-03207-z","type":"journal-article","created":{"date-parts":[[2024,5,4]],"date-time":"2024-05-04T11:01:33Z","timestamp":1714820493000},"page":"953-963","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Mind-bridge: reconstructing visual images based on diffusion model from human brain activity"],"prefix":"10.1007","volume":"18","author":[{"given":"Qing","family":"Liu","sequence":"first","affiliation":[]},{"given":"Hongqing","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Ning","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Bingcang","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Weiping","family":"Lu","sequence":"additional","affiliation":[]},{"given":"Ying","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,5,4]]},"reference":[{"key":"3207_CR1","doi-asserted-by":"publisher","first-page":"332","DOI":"10.1016\/j.neucom.2020.05.113","volume":"469","author":"W Yin","year":"2022","unstructured":"Yin, W., Li, L., Wu, F.-X.: Deep learning for brain disorder diagnosis based on fMRI images. Neurocomputing 469, 332\u2013345 (2022)","journal-title":"Neurocomputing"},{"issue":"1","key":"3207_CR2","doi-asserted-by":"publisher","first-page":"1006633","DOI":"10.1371\/journal.pcbi.1006633","volume":"15","author":"G Shen","year":"2019","unstructured":"Shen, G., Horikawa, T., Majima, K., Kamitani, Y.: Deep image reconstruction from human brain activity. PLoS Comput. Biol. 15(1), 1006633 (2019)","journal-title":"PLoS Comput. Biol."},{"key":"3207_CR3","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"3207_CR4","unstructured":"Gu, Z., Jamison, K., Kuceyeski, A., Sabuncu, M.: Decoding natural image stimuli from fMRI data with a surface-based convolutional network (2022). arXiv preprint arXiv:2212.02409"},{"key":"3207_CR5","doi-asserted-by":"crossref","unstructured":"Mozafari, M., Reddy, L., VanRullen, R.: Reconstructing natural scenes from fMRI patterns using bigbigan. In: 2020 International Joint Conference on Neural Networks (IJCNN), pp. 1\u20138. IEEE (2020)","DOI":"10.1109\/IJCNN48605.2020.9206960"},{"key":"3207_CR6","first-page":"27517","volume":"34","author":"A Casanova","year":"2021","unstructured":"Casanova, A., Careil, M., Verbeek, J., Drozdzal, M., Romero Soriano, A.: Instance-conditioned GAN. Adv. Neural. Inf. Process. Syst. 34, 27517\u201327529 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3207_CR7","unstructured":"Scotti, P., Banerjee, A., Goode, J., Shabalin, S., Nguyen, A., Dempster, A., Verlinde, N., Yundler, E., Weisberg, D., Norman, K., et al.: Reconstructing the mind\u2019s eye: fMRI-to-image with contrastive learning and diffusion priors. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"3207_CR8","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3207_CR9","unstructured":"Sun, J., Li, M., Chen, Z., Zhang, Y., Wang, S., Moens, M.-F.: Contrast, attend and diffuse to decode high-resolution images from brain activities. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"3207_CR10","doi-asserted-by":"crossref","unstructured":"Lu, Y., Du, C., Zhou, Q., Wang, D., He, H.: Minddiffuser: controlled image reconstruction from human brain activity with semantic and structural diffusion. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 5899\u20135908 (2023)","DOI":"10.1145\/3581783.3613832"},{"key":"3207_CR11","unstructured":"Van Den\u00a0Oord, A., Vinyals, O., et al.: Neural discrete representation learning. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"3207_CR12","unstructured":"Liu, Y., Ma, Y., Zhou, W., Zhu, G., Zheng, N.: Brainclip: bridging brain and visual-linguistic representation via clip for generic natural visual stimulus decoding from fMRI (2023). arXiv preprint arXiv:2302.12971"},{"key":"3207_CR13","unstructured":"Child, R.: Very deep vaes generalize autoregressive models and can outperform them on images (2020). arXiv preprint arXiv:2011.10650"},{"key":"3207_CR14","doi-asserted-by":"crossref","unstructured":"Xu, X., Wang, Z., Zhang, G., Wang, K., Shi, H.: Versatile diffusion: text, images and variations all in one diffusion model. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7754\u20137765 (2023)","DOI":"10.1109\/ICCV51070.2023.00713"},{"issue":"1","key":"3207_CR15","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1038\/s41593-021-00962-x","volume":"25","author":"EJ Allen","year":"2022","unstructured":"Allen, E.J., St-Yves, G., Wu, Y., Breedlove, J.L., Prince, J.S., Dowdle, L.T., Nau, M., Caron, B., Pestilli, F., Charest, I., et al.: A massive 7t fMRI dataset to bridge cognitive neuroscience and artificial intelligence. Nat. Neurosci. 25(1), 116\u2013126 (2022)","journal-title":"Nat. Neurosci."},{"key":"3207_CR16","first-page":"29624","volume":"35","author":"S Lin","year":"2022","unstructured":"Lin, S., Sprague, T., Singh, A.K.: Mind reader: reconstructing complex images from brain activities. Adv. Neural. Inf. Process. Syst. 35, 29624\u201329636 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3207_CR17","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T.: Analyzing and improving the image quality of stylegan. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8110\u20138119 (2020)","DOI":"10.1109\/CVPR42600.2020.00813"},{"issue":"1","key":"3207_CR18","doi-asserted-by":"publisher","first-page":"15666","DOI":"10.1038\/s41598-023-42891-8","volume":"13","author":"F Ozcelik","year":"2023","unstructured":"Ozcelik, F., VanRullen, R.: Natural scene reconstruction from fMRI signals using generative latent diffusion. Sci. Rep. 13(1), 15666 (2023)","journal-title":"Sci. Rep."},{"key":"3207_CR19","unstructured":"Mai, W., Zhang, Z.: Unibrain: unify image reconstruction and captioning all in one diffusion model from human brain activity (2023). arXiv preprint arXiv:2308.07428"},{"key":"3207_CR20","unstructured":"Ferrante, M., Ozcelik, F., Boccato, T., VanRullen, R., Toschi, N.: Brain captioning: decoding human brain activity into images and text (2023). arXiv preprint arXiv:2305.11560"},{"key":"3207_CR21","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"3207_CR22","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3836\u20133847 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"3207_CR23","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents 1(2), 3 (2022) . arXiv preprint arXiv:2204.06125"},{"key":"3207_CR24","doi-asserted-by":"crossref","unstructured":"Galatolo, F.A., Cimino, M.G., Vaglini, G.: Generating images from caption and vice versa via clip-guided generative latent space search (2021). arXiv preprint arXiv:2102.01645","DOI":"10.5220\/0010503701660174"},{"key":"3207_CR25","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, vol. 27 (2014)"},{"key":"3207_CR26","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes (2013). arXiv preprint arXiv:1312.6114"},{"key":"3207_CR27","unstructured":"Dinh, L., Krueger, D., Bengio, Y.: Nice: Non-linear independent components estimation (2014). arXiv preprint arXiv:1410.8516"},{"key":"3207_CR28","doi-asserted-by":"crossref","unstructured":"Chen, Z., Qing, J., Xiang, T., Yue, W.L., Zhou, J.H.: Seeing beyond the brain: conditional diffusion model with sparse masked modeling for vision decoding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22710\u201322720 (2023)","DOI":"10.1109\/CVPR52729.2023.02175"},{"key":"3207_CR29","unstructured":"Takagi, Y., Nishimoto, S.: Improving visual image reconstruction from human brain activity using latent diffusion models via multiple decoded inputs (2023). arXiv preprint arXiv:2306.11536"},{"key":"3207_CR30","doi-asserted-by":"crossref","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: Computer Vision\u2014ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6\u201312, 2014, Proceedings, Part V 13, pp. 740\u2013755. Springer, Berlin (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"3207_CR31","doi-asserted-by":"crossref","unstructured":"Ozcelik, F., Choksi, B., Mozafari, M., Reddy, L., VanRullen, R.: Reconstruction of perceived images from fMRI patterns and semantic brain exploration using instance-conditioned gans. In: 2022 International Joint Conference on Neural Networks (IJCNN), pp. 1\u20138. IEEE (2022)","DOI":"10.1109\/IJCNN55064.2022.9892673"},{"key":"3207_CR32","doi-asserted-by":"crossref","unstructured":"Takagi, Y., Nishimoto, S.: High-resolution image reconstruction with latent diffusion models from human brain activity. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14453\u201314463 (2023)","DOI":"10.1109\/CVPR52729.2023.01389"},{"issue":"4","key":"3207_CR33","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600\u2013612 (2004)","journal-title":"IEEE Trans. Image Process."},{"key":"3207_CR34","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, vol. 25 (2012)"},{"key":"3207_CR35","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132826 (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"3207_CR36","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":"3207_CR37","first-page":"9912","volume":"33","author":"M Caron","year":"2020","unstructured":"Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., Joulin, A.: Unsupervised learning of visual features by contrasting cluster assignments. Adv. Neural. Inf. Process. Syst. 33, 9912\u20139924 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-024-03207-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-024-03207-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-024-03207-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,25]],"date-time":"2024-06-25T12:32:54Z","timestamp":1719318774000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-024-03207-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,4]]},"references-count":37,"journal-issue":{"issue":"S1","published-print":{"date-parts":[[2024,8]]}},"alternative-id":["3207"],"URL":"https:\/\/doi.org\/10.1007\/s11760-024-03207-z","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"value":"1863-1703","type":"print"},{"value":"1863-1711","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,4]]},"assertion":[{"value":"8 March 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 March 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 April 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 May 2024","order":4,"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"}}]}}