{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T16:16:38Z","timestamp":1771604198960,"version":"3.50.1"},"reference-count":91,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":["Int J Comput Vis"],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1007\/s11263-025-02617-x","type":"journal-article","created":{"date-parts":[[2026,1,4]],"date-time":"2026-01-04T10:02:31Z","timestamp":1767520951000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["COBRA: A Continual Learning Approach to Vision-Brain Understanding"],"prefix":"10.1007","volume":"134","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8495-5469","authenticated-orcid":false,"given":"Xuan-Bac","family":"Nguyen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manuel","family":"Serna-Aguilera","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arabinda Kumar","family":"Choudhary","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pawan","family":"Sinha","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Khoa","family":"Luu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,4]]},"reference":[{"key":"2617_CR1","doi-asserted-by":"crossref","unstructured":"Wang, S., Liu, S., Tan, Z., & Wang, X. Mindbridge: A cross-subject brain decoding framework. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11333\u201311342 (2024)","DOI":"10.1109\/CVPR52733.2024.01077"},{"key":"2617_CR2","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 (2022). IEEE","DOI":"10.1109\/IJCNN55064.2022.9892673"},{"issue":"1","key":"2617_CR3","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. (2019). Deep image reconstruction from human brain activity. PLoS computational biology,15(1), 1006633.","journal-title":"PLoS computational biology"},{"key":"2617_CR4","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"},{"key":"2617_CR5","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. Advances in Neural Information Processing Systems 36 (2024)"},{"key":"2617_CR6","doi-asserted-by":"crossref","unstructured":"Quan, R., Wang, W., Tian, Z., Ma, F., & Yang, Y. Psychometry: An omnifit model for image reconstruction from human brain activity. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 233\u2013243 (2024)","DOI":"10.1109\/CVPR52733.2024.00030"},{"key":"2617_CR7","doi-asserted-by":"crossref","unstructured":"Huo, J., Wang, Y., Qian, X., Wang, Y., Li, C., Feng, J., & , Y. Neuropictor: Refining fmri-to-image reconstruction via multi-individual pretraining and multi-level modulation. arXiv preprint arXiv:2403.18211 (2024)","DOI":"10.1007\/978-3-031-72983-6_4"},{"key":"2617_CR8","unstructured":"Scotti, P.S., Tripathy, M., Villanueva, C.K.T., Kneeland, R., Chen, T., Narang, A., Santhirasegaran, C., Xu, J., Naselaris, T., Norman, K.A., & et al. Mindeye2: Shared-subject models enable fmri-to-image with 1 hour of data. arXiv preprint arXiv:2403.11207 (2024)"},{"key":"2617_CR9","doi-asserted-by":"crossref","unstructured":"Thrun, S. Lifelong learning algorithms. In: Learning to Learn, pp. 181\u2013209. Springer, ??? (1998)","DOI":"10.1007\/978-1-4615-5529-2_8"},{"issue":"4","key":"2617_CR10","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1016\/S1364-6613(99)01294-2","volume":"3","author":"RM French","year":"1999","unstructured":"French, R. M. (1999). Catastrophic forgetting in connectionist networks. Trends in cognitive sciences,3(4), 128\u2013135.","journal-title":"Trends in cognitive sciences"},{"issue":"2","key":"2617_CR11","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1080\/09540099550039318","volume":"7","author":"A Robins","year":"1995","unstructured":"Robins, A. (1995). Catastrophic forgetting, rehearsal and pseudorehearsal. Connection Science,7(2), 123\u2013146.","journal-title":"Connection Science"},{"issue":"5539","key":"2617_CR12","doi-asserted-by":"publisher","first-page":"2470","DOI":"10.1126\/science.1063414","volume":"293","author":"PE Downing","year":"2001","unstructured":"Downing, P. E., Jiang, Y., Shuman, M., & Kanwisher, N. (2001). A cortical area selective for visual processing of the human body. Science,293(5539), 2470\u20132473.","journal-title":"Science"},{"issue":"5","key":"2617_CR13","doi-asserted-by":"publisher","first-page":"821","DOI":"10.1016\/j.neuropsychologia.2011.01.034","volume":"49","author":"M Costantini","year":"2011","unstructured":"Costantini, M., Urgesi, C., Galati, G., Romani, G. L., & Aglioti, S. M. (2011). Haptic perception and body representation in lateral and medial occipito-temporal cortices. Neuropsychologia,49(5), 821\u2013829.","journal-title":"Neuropsychologia"},{"issue":"6676","key":"2617_CR14","doi-asserted-by":"publisher","first-page":"598","DOI":"10.1038\/33402","volume":"392","author":"R Epstein","year":"1998","unstructured":"Epstein, R., & Kanwisher, N. (1998). A cortical representation of the local visual environment. Nature,392(6676), 598\u2013601.","journal-title":"Nature"},{"issue":"1","key":"2617_CR15","doi-asserted-by":"publisher","first-page":"146","DOI":"10.1093\/cercor\/bhw361","volume":"27","author":"KS Weiner","year":"2017","unstructured":"Weiner, K. S., Barnett, M. A., Lorenz, S., Caspers, J., Stigliani, A., Amunts, K., Zilles, K., Fischl, B., & Grill-Spector, K. (2017). The cytoarchitecture of domain-specific regions in human high-level visual cortex. Cerebral cortex,27(1), 146\u2013161.","journal-title":"Cerebral cortex"},{"issue":"1","key":"2617_CR16","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1016\/S0896-6273(00)80758-8","volume":"23","author":"R Epstein","year":"1999","unstructured":"Epstein, R., Harris, A., Stanley, D., & Kanwisher, N. (1999). The parahippocampal place area: recognition, navigation, or encoding? Neuron,23(1), 115\u2013125.","journal-title":"Neuron"},{"issue":"1","key":"2617_CR17","doi-asserted-by":"publisher","first-page":"373","DOI":"10.1146\/annurev-vision-091718-014809","volume":"5","author":"RA Epstein","year":"2019","unstructured":"Epstein, R. A., & Baker, C. I. (2019). Scene perception in the human brain. Annual review of vision science,5(1), 373\u2013397.","journal-title":"Annual review of vision science"},{"issue":"1","key":"2617_CR18","doi-asserted-by":"publisher","first-page":"393","DOI":"10.1146\/annurev-vision-082114-035518","volume":"1","author":"B Duchaine","year":"2015","unstructured":"Duchaine, B., & Yovel, G. (2015). A revised neural framework for face processing. Annual review of vision science,1(1), 393\u2013416.","journal-title":"Annual review of vision science"},{"issue":"2","key":"2617_CR19","doi-asserted-by":"publisher","first-page":"922","DOI":"10.1073\/pnas.93.2.922","volume":"93","author":"JV Haxby","year":"1996","unstructured":"Haxby, J. V., Ungerleider, L. G., Horwitz, B., Maisog, J. M., Rapoport, S. I., & Grady, C. L. (1996). Face encoding and recognition in the human brain. Proceedings of the National Academy of Sciences,93(2), 922\u2013927.","journal-title":"Proceedings of the National Academy of Sciences"},{"issue":"2","key":"2617_CR20","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1002\/hbm.460030204","volume":"3","author":"JV Haxby","year":"1995","unstructured":"Haxby, J. V., Ungerleider, L. G., Horwitz, B., Rapoport, S. I., & Grady, C. L. (1995). Hemispheric differences in neural systems for face working memory: A pet-rcbf study. Human Brain Mapping,3(2), 68\u201382.","journal-title":"Human Brain Mapping"},{"issue":"1","key":"2617_CR21","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1146\/annurev-vision-102016-061214","volume":"3","author":"K Grill-Spector","year":"2017","unstructured":"Grill-Spector, K., Weiner, K. S., Kay, K., & Gomez, J. (2017). The functional neuroanatomy of human face perception. Annual review of vision science,3(1), 167\u2013196.","journal-title":"Annual review of vision science"},{"key":"2617_CR22","unstructured":"Nguyen, H.-Q., Nguyen, X.-B., Churchill, H., Choudhary, A.K., Sinha, P., Khan, S.U., & Luu, K. Quantum-brain: Quantum-inspired neural network approach to vision-brain understanding. arXiv preprint arXiv:2411.13378 (2024)"},{"key":"2617_CR23","doi-asserted-by":"crossref","unstructured":"Nguyen, X.-B., Nguyen, H.-Q., Churchill, H., Khan, S. U., & Luu, K. (2024). Quantum visual feature encoding revisited. Quantum Machine Intelligence,6(2), 61.","DOI":"10.1007\/s42484-024-00192-x"},{"key":"2617_CR24","doi-asserted-by":"crossref","unstructured":"Truong, T.-D., Nguyen, H.-Q., Nguyen, X.-B., Dowling, A., Li, X., & Luu, K. Insect-foundation: A foundation model and large multimodal dataset for vision-language insect understanding. International Journal of Computer Vision, 1\u201326 (2025)","DOI":"10.1007\/s11263-025-02521-4"},{"issue":"9","key":"2617_CR25","first-page":"1","volume":"55","author":"P Liu","year":"2023","unstructured":"Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., & Neubig, G. (2023). Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing. ACM Computing Surveys,55(9), 1\u201335.","journal-title":"ACM Computing Surveys"},{"key":"2617_CR26","doi-asserted-by":"crossref","unstructured":"Xia, W., Charette, R., \u00d6ztireli, C., & Xue, J.-H. UMBRAE: Unified Multimodal Brain Decoding (2024). arxiv:2404.07202","DOI":"10.1007\/978-3-031-72667-5_14"},{"key":"2617_CR27","unstructured":"Sohl-Dickstein, J., Weiss, E.A., Maheswaranathan, N., & Ganguli, S. Deep unsupervised learning using nonequilibrium thermodynamics. CoRR abs\/1503.03585 (2015) 1503.03585"},{"key":"2617_CR28","unstructured":"Ho, J., Jain, A., & Abbeel, P. Denoising diffusion probabilistic models. arXiv preprint arxiv:2006.11239 (2020)"},{"key":"2617_CR29","unstructured":"Dhariwal, P., & Nichol, A. Diffusion models beat gans on image synthesis. CoRR abs\/2105.05233 (2021) 2105.05233"},{"key":"2617_CR30","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. High-Resolution Image Synthesis with Latent Diffusion Models (2022). arxiv:2112.10752","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"2617_CR31","unstructured":"Xu, X., Wang, Z., Zhang, E., Wang, K., & Shi, H. Versatile Diffusion: Text, Images and Variations All in One Diffusion Model (2024). arxiv:2211.08332"},{"key":"2617_CR32","doi-asserted-by":"crossref","unstructured":"Wang, Z., Zhang, Z., Lee, C.-Y., Zhang, H., Sun, R., Ren, X., Su, G., Perot, V., Dy, J., & Pfister, T. Learning to Prompt for Continual Learning (2022). arxiv:2112.08654","DOI":"10.1109\/CVPR52688.2022.00024"},{"key":"2617_CR33","doi-asserted-by":"crossref","unstructured":"Hayes, T.L., Cahill, N.D., & Kanan, C. Memory Efficient Experience Replay for Streaming Learning (2019). arxiv:1809.05922","DOI":"10.1109\/ICRA.2019.8793982"},{"key":"2617_CR34","unstructured":"Chaudhry, A., Rohrbach, M., Elhoseiny, M., Ajanthan, T., Dokania, P.K., Torr, P.H.S., & Ranzato, M. On Tiny Episodic Memories in Continual Learning (2019). arxiv:1902.10486"},{"key":"2617_CR35","doi-asserted-by":"crossref","unstructured":"Chaudhry, A., Gordo, A., Dokania, P.K., Torr, P., & Lopez-Paz, D. Using Hindsight to Anchor Past Knowledge in Continual Learning (2021). arxiv:2002.08165","DOI":"10.1609\/aaai.v35i8.16861"},{"key":"2617_CR36","unstructured":"Chaudhry, A., Ranzato, M., Rohrbach, M., & Elhoseiny, M. Efficient Lifelong Learning with A-GEM (2019). arxiv:1812.00420"},{"key":"2617_CR37","unstructured":"Buzzega, P., Boschini, M., Porrello, A., Abati, D., & Calderara, S. Dark Experience for General Continual Learning: a Strong, Simple Baseline (2020). arxiv:2004.07211"},{"key":"2617_CR38","doi-asserted-by":"crossref","unstructured":"Rebuffi, S.-A., Kolesnikov, A., Sperl, G., & Lampert, C.H. iCaRL: Incremental Classifier and Representation Learning (2017). arxiv:1611.07725","DOI":"10.1109\/CVPR.2017.587"},{"key":"2617_CR39","doi-asserted-by":"publisher","unstructured":"Shokri, R., & Shmatikov, V. Privacy-preserving deep learning. In: 2015 53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton), pp. 909\u2013910 (2015). https:\/\/doi.org\/10.1109\/ALLERTON.2015.7447103","DOI":"10.1109\/ALLERTON.2015.7447103"},{"key":"2617_CR40","unstructured":"Pham, Q., Liu, C., & Hoi, S. DualNet: Continual Learning, Fast and Slow (2021). arxiv:2110.00175"},{"key":"2617_CR41","doi-asserted-by":"crossref","unstructured":"Cha, H., Lee, J., & Shin, J. Co2l: Contrastive continual learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9516\u20139525 (2021)","DOI":"10.1109\/ICCV48922.2021.00938"},{"key":"2617_CR42","doi-asserted-by":"crossref","unstructured":"Wu, Y., Chen, Y., Wang, L., Ye, Y., Liu, Z., Guo, Y., & Fu, Y. Large Scale Incremental Learning (2019). arxiv:1905.13260","DOI":"10.1109\/CVPR.2019.00046"},{"key":"2617_CR43","doi-asserted-by":"crossref","unstructured":"Nguyen, X.-B., Lee, G.-S., Kim, S.-H., & Yang, H.-J. Audio-video based emotion recognition using minimum cost flow algorithm. In: 2019 IEEE\/CVF International Conference on Computer Vision Workshop (ICCVW), pp. 3737\u20133741 (2019). IEEE","DOI":"10.1109\/ICCVW.2019.00464"},{"key":"2617_CR44","unstructured":"Nguyen-Xuan, B., & Lee, G.-S. (2019). Sketch recognition using lstm with attention mechanism and minimum cost flow algorithm. International Journal of Contents,15(4), 8\u201315."},{"key":"2617_CR45","doi-asserted-by":"publisher","first-page":"162973","DOI":"10.1109\/ACCESS.2020.3021469","volume":"8","author":"X-B Nguyen","year":"2020","unstructured":"Nguyen, X.-B., Lee, G. S., Kim, S. H., & Yang, H. J. (2020). Self-supervised learning based on spatial awareness for medical image analysis. IEEE Access,8, 162973\u2013162981.","journal-title":"IEEE Access"},{"key":"2617_CR46","doi-asserted-by":"crossref","unstructured":"Nguyen, X.-B., Bui, D.T., Duong, C.N., Bui, T.D., & Luu, K. Clusformer: A transformer based clustering approach to unsupervised large-scale face and visual landmark recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10847\u201310856 (2021)","DOI":"10.1109\/CVPR46437.2021.01070"},{"key":"2617_CR47","doi-asserted-by":"crossref","unstructured":"Nguyen, P., Quach, K.G., Duong, C.N., Le, N., Nguyen, X.-B., & Luu, K. Multi-camera multiple 3d object tracking on the move for autonomous vehicles. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2569\u20132578 (2022)","DOI":"10.1109\/CVPRW56347.2022.00289"},{"key":"2617_CR48","unstructured":"Nguyen, X.B., Bisht, A., Churchill, H., & Luu, K. Two-dimensional quantum material identification via self-attention and soft-labeling in deep learning. arXiv preprint arXiv:2205.15948 (2022)"},{"key":"2617_CR49","unstructured":"Nguyen, X.-B., Liu, X., Li, X., & Luu, K. The algonauts project 2023 challenge: Uark-ualbany team solution. arXiv preprint arXiv:2308.00262 (2023)"},{"key":"2617_CR50","unstructured":"Nguyen, X.-B., Li, X., Khan, S.U., & Luu, K. Brainformer: Modeling mri brain functions to machine vision. arXiv preprint arXiv:2312.00236 (2023)"},{"key":"2617_CR51","unstructured":"Nguyen, X.-B., Duong, C.N., Savvides, M., Roy, K., & Churchill, H., Luu, K. Fairness in visual clustering: A novel transformer clustering approach. arXiv preprint arXiv:2304.07408 (2023)"},{"key":"2617_CR52","unstructured":"Nguyen, X.-B., Jang, H., Li, X., Khan, S.U., Sinha, P., & Luu, K. Bractive: A brain activation approach to human visual brain learning. arXiv preprint arXiv:2405.18808 (2024)"},{"key":"2617_CR53","doi-asserted-by":"crossref","unstructured":"Nguyen, H.-Q., Nguyen, X.B., Chen, S.Y.-C., Churchill, H., Borys, N., Khan, S.U., & Luu, K. Diffusion-inspired quantum noise mitigation in parameterized quantum circuits. arXiv preprint arXiv:2406.00843 (2024)","DOI":"10.21203\/rs.3.rs-5335334\/v1"},{"key":"2617_CR54","doi-asserted-by":"crossref","unstructured":"Nguyen, X.-B., Nguyen, H.-Q., Churchill, H., Khan, S.U., & Luu, K. Hierarchical quantum control gates for functional mri understanding. arXiv preprint arXiv:2408.03596 (2024)","DOI":"10.1109\/SiPS62058.2024.00036"},{"key":"2617_CR55","doi-asserted-by":"crossref","unstructured":"Nguyen, H.-Q., Truong, T.-D., Nguyen, X.B., Dowling, A., Li, X., & Luu, K. Insect-foundation: A foundation model and large-scale 1m dataset for visual insect understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21945\u201321955 (2024)","DOI":"10.1109\/CVPR52733.2024.02072"},{"key":"2617_CR56","doi-asserted-by":"crossref","unstructured":"Nguyen, X.-B., Nguyen, H.-Q., Chen, S.Y.-C., Khan, S.U., Churchill, H., & Luu, K. Qclusformer: A quantum transformer-based framework for unsupervised visual clustering. arXiv preprint arXiv:2405.19722 (2024)","DOI":"10.1109\/QCE60285.2024.10304"},{"key":"2617_CR57","unstructured":"Zhao, T., Wang, Z., Masoomi, A., & Dy, J. Deep Bayesian Unsupervised Lifelong Learning (2021). arxiv:2106.07035"},{"key":"2617_CR58","unstructured":"Yoon, J., Yang, E., Lee, J., & Hwang, S.J. Lifelong Learning with Dynamically Expandable Networks (2018). arxiv:1708.01547"},{"key":"2617_CR59","unstructured":"Rusu, A.A., Rabinowitz, N.C., Desjardins, G., Soyer, H., Kirkpatrick, J., Kavukcuoglu, K., Pascanu, R., & Hadsell, R. Progressive Neural Networks (2022). arxiv:1606.04671"},{"key":"2617_CR60","unstructured":"Rao, D., Visin, F., Rusu, A.A., Teh, Y.W., Pascanu, R., & Hadsell, R. Continual Unsupervised Representation Learning (2019). arxiv:1910.14481"},{"key":"2617_CR61","unstructured":"Loo, N., Swaroop, S., & Turner, R.E. Generalized Variational Continual Learning (2020). arxiv:2011.12328"},{"key":"2617_CR62","unstructured":"Li, X., Zhou, Y., Wu, T., Socher, R., & Xiong, C. Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgetting (2019). arxiv:1904.00310"},{"key":"2617_CR63","unstructured":"Wortsman, M., Ramanujan, V., Liu, R., Kembhavi, A., Rastegari, M., Yosinski, J., & Farhadi, A. Supermasks in Superposition (2020). arxiv:2006.14769"},{"key":"2617_CR64","unstructured":"Serr\u00e0, J., Sur\u00eds, D., Miron, M., & Karatzoglou, A. Overcoming catastrophic forgetting with hard attention to the task (2018). arxiv:1801.01423"},{"key":"2617_CR65","doi-asserted-by":"crossref","unstructured":"Mallya, A., & Lazebnik, S. PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning (2018). arxiv:1711.05769","DOI":"10.1109\/CVPR.2018.00810"},{"key":"2617_CR66","unstructured":"Ke, Z., Liu, B., & Huang, X. Continual Learning of a Mixed Sequence of Similar and Dissimilar Tasks (2021). arxiv:2112.10017"},{"issue":"10","key":"2617_CR67","doi-asserted-by":"publisher","first-page":"1097","DOI":"10.1038\/s42256-023-00714-5","volume":"5","author":"A D\u00e9fossez","year":"2023","unstructured":"D\u00e9fossez, A., Caucheteux, C., Rapin, J., Kabeli, O., & King, J.-R. (2023). Decoding speech perception from non-invasive brain recordings. Nature Machine Intelligence,5(10), 1097\u20131107.","journal-title":"Nature Machine Intelligence"},{"key":"2617_CR68","doi-asserted-by":"crossref","unstructured":"Yu, H., Wang, H., & Wu, J. Mixup without hesitation. In: Image and Graphics: 11th International Conference, ICIG 2021, Haikou, China, August 6\u20138, 2021, Proceedings, Part II 11, pp. 143\u2013154 (2021). Springer","DOI":"10.1007\/978-3-030-87358-5_12"},{"key":"2617_CR69","first-page":"17612","volume":"35","author":"VW Liang","year":"2022","unstructured":"Liang, V. W., Zhang, Y., Kwon, Y., Yeung, S., & Zou, J. Y. (2022). Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning. Advances in Neural Information Processing Systems,35, 17612\u201317625.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2617_CR70","unstructured":"Tan, M. Efficientnet: Rethinking model scaling for convolutional neural networks. arXiv preprint arXiv:1905.11946, 6105\u20136114 (2019)"},{"key":"2617_CR71","doi-asserted-by":"crossref","unstructured":"Caron, M., Touvron, H., Misra, I., J\u00e9gou, H., Mairal, J., Bojanowski, P., & Joulin, A. Emerging properties in self-supervised vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9650\u20139660 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"issue":"5539","key":"2617_CR72","doi-asserted-by":"publisher","first-page":"2425","DOI":"10.1126\/science.1063736","volume":"293","author":"JV Haxby","year":"2001","unstructured":"Haxby, J. V., Gobbini, M. I., Furey, M. L., Ishai, A., Schouten, J. L., & Pietrini, P. (2001). Distributed and overlapping representations of faces and objects in ventral temporal cortex. Science,293(5539), 2425\u20132430.","journal-title":"Science"},{"issue":"4","key":"2617_CR73","doi-asserted-by":"publisher","first-page":"272","DOI":"10.1002\/(SICI)1097-0193(1999)8:4<272::AID-HBM10>3.0.CO;2-4","volume":"8","author":"B Fischl","year":"1999","unstructured":"Fischl, B., Sereno, M. I., Tootell, R. B., & Dale, A. M. (1999). High-resolution intersubject averaging and a coordinate system for the cortical surface. Human brain mapping,8(4), 272\u2013284.","journal-title":"Human brain mapping"},{"issue":"1","key":"2617_CR74","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. (2022). A massive 7t fmri dataset to bridge cognitive neuroscience and artificial intelligence. Nature neuroscience,25(1), 116\u2013126.","journal-title":"Nature neuroscience"},{"key":"2617_CR75","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\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13, pp. 740\u2013755 (2014). Springer","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2617_CR76","doi-asserted-by":"crossref","unstructured":"Wang, Z., Zhang, Z., Ebrahimi, S., Sun, R., Zhang, H., Lee, C.-Y., Ren, X., Su, G., Perot, V., Dy, J., & et al.: Dualprompt: Complementary prompting for rehearsal-free continual learning. In: European Conference on Computer Vision, pp. 631\u2013648 (2022). Springer","DOI":"10.1007\/978-3-031-19809-0_36"},{"key":"2617_CR77","doi-asserted-by":"crossref","unstructured":"Wang, Z., Zhang, Z., Lee, C.-Y., Zhang, H., Sun, R., Ren, X., Su, G., Perot, V., Dy, J., & Pfister, T. Learning to prompt for continual learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 139\u2013149 (2022)","DOI":"10.1109\/CVPR52688.2022.00024"},{"key":"2617_CR78","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G., & Sutskever, I. Learning Transferable Visual Models From Natural Language Supervision (2021)"},{"key":"2617_CR79","unstructured":"Martino, G., Barr\u00f3n-Cedeno, A., Wachsmuth, H., Petrov, R., & Nakov, P. Semeval-2020 task 11: Detection of propaganda techniques in news articles. arXiv preprint arXiv:2009.02696 (2020)"},{"key":"2617_CR80","unstructured":"Loshchilov, I.. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"2617_CR81","doi-asserted-by":"crossref","unstructured":"Douillard, A., Chen, Y., Dapogny, A., & Cord, M. Plop: Learning without forgetting for continual semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4040\u20134050 (2021)","DOI":"10.1109\/CVPR46437.2021.00403"},{"issue":"12","key":"2617_CR82","doi-asserted-by":"publisher","first-page":"2935","DOI":"10.1109\/TPAMI.2017.2773081","volume":"40","author":"Z Li","year":"2018","unstructured":"Li, Z., & Hoiem, D. (2018). Learning without forgetting. IEEE Transactions on Pattern Analysis and Machine Intelligence,40(12), 2935\u20132947. https:\/\/doi.org\/10.1109\/TPAMI.2017.2773081","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2617_CR83","unstructured":"Chen, K., Zhang, Z., Zeng, W., Zhang, R., Zhu, F., & Zhao, R. Shikra: Unleashing multimodal llm\u2019s referential dialogue magic. arXiv preprint arXiv:2306.15195 (2023)"},{"key":"2617_CR84","unstructured":"Lin, S., Sprague, T., & Singh, A.K. Mind Reader: Reconstructing complex images from brain activities (2022). arxiv:2210.01769"},{"key":"2617_CR85","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 (2023). arxiv:2211.06956","DOI":"10.1109\/CVPR52729.2023.02175"},{"key":"2617_CR86","unstructured":"Gu, Z., Jamison, K., Kuceyeski, A., & Sabuncu, M. Decoding natural image stimuli from fMRI data with a surface-based convolutional network (2023). arxiv: 2212.02409"},{"key":"2617_CR87","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"},{"key":"2617_CR88","doi-asserted-by":"crossref","unstructured":"Han, J., Gong, K., Zhang, Y., Wang, J., Zhang, K., Lin, D., Qiao, Y., Gao, P., & Yue, X. Onellm: One framework to align all modalities with language. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 26584\u201326595 (2024)","DOI":"10.1109\/CVPR52733.2024.02510"},{"key":"2617_CR89","unstructured":"Ferrante, M., Ozcelik, F., Boccato, T., VanRullen, R., & Toschi, N. Brain captioning: Decoding human brain activity into images and text. arXiv preprint arXiv:2305.11560 (2023)"},{"key":"2617_CR90","unstructured":"Mai, W., & Zhang, Z. Unibrain: Unify image reconstruction and captioning all in one diffusion model from human brain activity. arXiv preprint arXiv:2308.07428 (2023)"},{"key":"2617_CR91","unstructured":"Maaten, L., & Hinton, G. Visualizing data using t-sne. Journal of machine learning research 9(11) (2008)"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02617-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-025-02617-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02617-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T15:40:40Z","timestamp":1771602040000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-025-02617-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":91,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["2617"],"URL":"https:\/\/doi.org\/10.1007\/s11263-025-02617-x","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"20 February 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 November 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 January 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"30"}}