{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T14:11:38Z","timestamp":1779372698351,"version":"3.53.1"},"reference-count":57,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100012542","name":"Sichuan Province Science and Technology Support Program","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100012542","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.eswa.2026.132836","type":"journal-article","created":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T04:18:33Z","timestamp":1778559513000},"page":"132836","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Enhancing visual decoding with dynamic alignment strategy"],"prefix":"10.1016","volume":"327","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7854-4006","authenticated-orcid":false,"given":"Wei","family":"Huang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4325-8849","authenticated-orcid":false,"given":"Jingpeng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7379-197X","authenticated-orcid":false,"given":"Fan","family":"Qin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8746-2496","authenticated-orcid":false,"given":"Luan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0722-6335","authenticated-orcid":false,"given":"Sizhuo","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7944-8990","authenticated-orcid":false,"given":"Hengjiang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1997-5089","authenticated-orcid":false,"given":"Yun-Shuang","family":"Fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4062-4753","authenticated-orcid":false,"given":"Huafu","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"1","key":"10.1016\/j.eswa.2026.132836_bib0001","doi-asserted-by":"crossref","first-page":"116","DOI":"10.1038\/s41593-021-00962-x","article-title":"A massive 7t fMRI dataset to bridge cognitive neuroscience and artificial intelligence","volume":"25","author":"Allen","year":"2022","journal-title":"Nature Neuroscience"},{"issue":"7753","key":"10.1016\/j.eswa.2026.132836_bib0002","doi-asserted-by":"crossref","first-page":"493","DOI":"10.1038\/s41586-019-1119-1","article-title":"Speech synthesis from neural decoding of spoken sentences","volume":"568","author":"Anumanchipalli","year":"2019","journal-title":"Nature"},{"key":"10.1016\/j.eswa.2026.132836_bib0003","series-title":"IOP conference series: Materials science and engineering","first-page":"032049","article-title":"A literature review of brain decoding research","volume":"vol. 830","author":"Awangga","year":"2020"},{"key":"10.1016\/j.eswa.2026.132836_bib0004","series-title":"Proceedings of the ACL workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization","first-page":"65","article-title":"Meteor: An automatic metric for MT evaluation with improved correlation with human judgments","author":"Banerjee","year":"2005"},{"key":"10.1016\/j.eswa.2026.132836_bib0005","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"14194","article-title":"Wills aligner: Multi-subject collaborative brain visual decoding","volume":"vol. 39","author":"Bao","year":"2025"},{"key":"10.1016\/j.eswa.2026.132836_bib0006","unstructured":"Chatterjee, S., & Samanta, D. (2023). Dreamcatcher: Revealing the language of the brain with fMRI using GPT embedding. arXiv preprint arXiv: 2306.10082."},{"key":"10.1016\/j.eswa.2026.132836_bib0007","doi-asserted-by":"crossref","DOI":"10.51628\/001c.38668","article-title":"Deep recurrent encoder: An end-to-end network to model magnetoencephalography at scale","author":"Chehab","year":"2022","journal-title":"Neurons, Behavior, Data Analysis, and Theory"},{"key":"10.1016\/j.eswa.2026.132836_bib0008","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"11302","article-title":"Bridging the semantic latent space between brain and machine: Similarity is all you need","volume":"vol. 38","author":"Chen","year":"2024"},{"key":"10.1016\/j.eswa.2026.132836_bib0009","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"27207","article-title":"Mind artist: Creating artistic snapshots with human thought","author":"Chen","year":"2024"},{"key":"10.1016\/j.eswa.2026.132836_bib0010","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"21938","article-title":"Bridging the gap between brain and machine in interpreting visual semantics: Towards self-adaptive brain-to-text decoding","author":"Chen","year":"2025"},{"key":"10.1016\/j.eswa.2026.132836_bib0011","doi-asserted-by":"crossref","first-page":"3281","DOI":"10.1109\/TIP.2025.3572784","article-title":"MindGPT: Interpreting what you see with non-invasive brain recordings","volume":"34","author":"Chen","year":"2025","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.eswa.2026.132836_bib0012","series-title":"2017\u202fIEEE 60th international midwest symposium on circuits and systems (MWSCAS)","first-page":"1597","article-title":"Gate-variants of gated recurrent unit (GRU) neural networks","author":"Dey","year":"2017"},{"key":"10.1016\/j.eswa.2026.132836_sbref0013","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"CoRR"},{"issue":"9","key":"10.1016\/j.eswa.2026.132836_bib0014","doi-asserted-by":"crossref","first-page":"10760","DOI":"10.1109\/TPAMI.2023.3263181","article-title":"Decoding visual neural representations by multimodal learning of brain-visual-linguistic features","volume":"45","author":"Du","year":"2023","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.eswa.2026.132836_bib0015","series-title":"Unireps: The first workshop on unifying representations in neural models","article-title":"Multimodal decoding of human brain activity into images and text","author":"Ferrante","year":"2023"},{"issue":"7615","key":"10.1016\/j.eswa.2026.132836_bib0016","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1038\/nature18933","article-title":"A multi-modal parcellation of human cerebral cortex","volume":"536","author":"Glasser","year":"2016","journal-title":"Nature"},{"key":"10.1016\/j.eswa.2026.132836_bib0017","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"14247","article-title":"Mindtuner: Cross-subject visual decoding with visual fingerprint and semantic correction","volume":"vol. 39","author":"Gong","year":"2025"},{"key":"10.1016\/j.eswa.2026.132836_bib0018","unstructured":"Goyal, T., Li, J. J., & Durrett, G. (2022). News summarization and evaluation in the era of GPT-3. arXiv preprint arXiv: 2209.12356."},{"key":"10.1016\/j.eswa.2026.132836_bib0019","unstructured":"Gu, Z., Jamison, K., Kuceyeski, A., & Sabuncu, M. (2022). Decoding natural image stimuli from fMRI data with a surface-based convolutional network. arXiv preprint arXiv: 2212.02409."},{"key":"10.1016\/j.eswa.2026.132836_bib0020","unstructured":"Han, I., Lee, J., & Ye, J. C. (2024). Mindformer: Semantic alignment of multi-subject fMRI for brain decoding. arXiv: 2405.17720."},{"issue":"5","key":"10.1016\/j.eswa.2026.132836_bib0021","doi-asserted-by":"crossref","first-page":"686","DOI":"10.1038\/nn1445","article-title":"Predicting the orientation of invisible stimuli from activity in human primary visual cortex","volume":"8","author":"Haynes","year":"2005","journal-title":"Nature Neuroscience"},{"key":"10.1016\/j.eswa.2026.132836_bib0022","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.eswa.2026.132836_bib0023","unstructured":"Hendy, A., Abdelrehim, M., Sharaf, A., Raunak, V., Gabr, M., Matsushita, H., Kim, Y. J., Afify, M., & Awadalla, H. H. (2023). How good are GPT models at machine translation? A comprehensive evaluation. arXiv preprint arXiv: 2302.09210."},{"key":"10.1016\/j.eswa.2026.132836_bib0024","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.132836_bib0025","article-title":"MFA-NRM : A novel framework for multimodal fusion and semantic alignment in visual neural decoding","volume":"127","author":"Huang","year":"2025","journal-title":"Information Fusion"},{"key":"10.1016\/j.eswa.2026.132836_bib0026","doi-asserted-by":"crossref","DOI":"10.1142\/S0129065725500091","article-title":"Unraveling the differential efficiency of dorsal and ventral pathways in visual semantic decoding","volume":"35","author":"Huang","year":"2025","journal-title":"International Journal of Neural Systems"},{"key":"10.1016\/j.eswa.2026.132836_bib0027","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1016\/j.neunet.2021.08.006","article-title":"A neural decoding algorithm that generates language from visual activity evoked by natural images","volume":"144","author":"Huang","year":"2021","journal-title":"Neural Networks"},{"issue":"15","key":"10.1016\/j.eswa.2026.132836_bib0028","doi-asserted-by":"crossref","first-page":"5089","DOI":"10.1002\/hbm.25603","article-title":"A dual-channel language decoding from brain activity with progressive transfer training","volume":"42","author":"Huang","year":"2021","journal-title":"Human Brain Mapping"},{"key":"10.1016\/j.eswa.2026.132836_bib0029","doi-asserted-by":"crossref","first-page":"202","DOI":"10.1016\/j.neucom.2018.07.068","article-title":"F-score feature selection based Bayesian reconstruction of visual image from human brain activity","volume":"316","author":"Huang","year":"2018","journal-title":"Neurocomputing"},{"key":"10.1016\/j.eswa.2026.132836_bib0030","doi-asserted-by":"crossref","first-page":"2323","DOI":"10.1007\/s10439-020-02502-3","article-title":"Perception-to-image: Reconstructing natural images from the brain activity of visual perception","volume":"48","author":"Huang","year":"2020","journal-title":"Annals of Biomedical Engineering"},{"key":"10.1016\/j.eswa.2026.132836_bib0031","doi-asserted-by":"crossref","first-page":"369","DOI":"10.1007\/s12264-020-00613-4","article-title":"Deep natural image reconstruction from human brain activity based on conditional progressively growing generative adversarial networks","volume":"37","author":"Huang","year":"2021","journal-title":"Neuroscience Bulletin"},{"key":"10.1016\/j.eswa.2026.132836_bib0032","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102573","article-title":"From sight to insight: A multi-task approach with the visual language decoding model","volume":"112","author":"Huang","year":"2024","journal-title":"Information Fusion"},{"key":"10.1016\/j.eswa.2026.132836_bib0033","doi-asserted-by":"crossref","first-page":"81","DOI":"10.3389\/fnsys.2016.00081","article-title":"Decoding the semantic content of natural movies from human brain activity","volume":"10","author":"Huth","year":"2016","journal-title":"Frontiers in Systems Neuroscience"},{"issue":"5","key":"10.1016\/j.eswa.2026.132836_bib0034","doi-asserted-by":"crossref","first-page":"679","DOI":"10.1038\/nn1444","article-title":"Decoding the visual and subjective contents of the human brain","volume":"8","author":"Kamitani","year":"2005","journal-title":"Nature Neuroscience"},{"key":"10.1016\/j.eswa.2026.132836_bib0035","unstructured":"Lei, J., Dai, L., Jiang, H., Wu, C., Zhang, X., Zhang, Y., Yao, J., Xie, W., Zhang, Y., Li, Y. et al. (2023). Unibrain: Universal brain MRI diagnosis with hierarchical knowledge-enhanced pre-training. arXiv preprint arXiv: 2309.06828."},{"key":"10.1016\/j.eswa.2026.132836_bib0036","series-title":"Text summarization branches out","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004"},{"key":"10.1016\/j.eswa.2026.132836_bib0037","series-title":"Computer vision\u2013ECCV 2014: 13th European conference, Zurich, Switzerland, September 6\u201312, 2014, proceedings, Part V 13","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.eswa.2026.132836_bib0038","unstructured":"Liu, A., Feng, B., Xue, B., Wang, B., Wu, B., Lu, C., Zhao, C., Deng, C., Zhang, C., Ruan, C. et al. (2024). Deepseek-v3 technical report. arXiv preprint arXiv: 2412.19437."},{"key":"10.1016\/j.eswa.2026.132836_bib0039","unstructured":"Liu, Y., Ma, Y., Zhou, W., Zhu, G., & Zheng, N. (2023). BrainCLIP: Bridging brain and visual-linguistic representation via CLIP for generic natural visual stimulus decoding. arXiv preprint arXiv: 2302.12971."},{"key":"10.1016\/j.eswa.2026.132836_bib0040","unstructured":"Mai, W., & Zhang, Z. (2023). Unibrain: Unify image reconstruction and captioning all in one diffusion model from human brain activity. arXiv preprint arXiv: 2308.07428."},{"issue":"4","key":"10.1016\/j.eswa.2026.132836_bib0041","doi-asserted-by":"crossref","first-page":"575","DOI":"10.1038\/s41593-020-0608-8","article-title":"Machine translation of cortical activity to text with an encoder\u2013decoder framework","volume":"23","author":"Makin","year":"2020","journal-title":"Nature Neuroscience"},{"key":"10.1016\/j.eswa.2026.132836_bib0042","doi-asserted-by":"crossref","first-page":"232","DOI":"10.1016\/j.neuroimage.2017.08.017","article-title":"Decoding naturalistic experiences from human brain activity via distributed representations of words","volume":"180","author":"Nishida","year":"2018","journal-title":"Neuroimage"},{"key":"10.1016\/j.eswa.2026.132836_bib0043","unstructured":"Pandya, K., & Holia, M. (2023). Automating customer service using langchain: Building custom open-source GPT chatbot for organizations. arXiv preprint arXiv: 2310.05421."},{"key":"10.1016\/j.eswa.2026.132836_bib0044","series-title":"International conference on machine learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.eswa.2026.132836_bib0045","series-title":"International conference on machine learning","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2023"},{"key":"10.1016\/j.eswa.2026.132836_bib0046","series-title":"International conference on machine learning","first-page":"8821","article-title":"Zero-shot text-to-image generation","author":"Ramesh","year":"2021"},{"key":"10.1016\/j.eswa.2026.132836_bib0047","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"779","article-title":"You only look once: Unified, real-time object detection","author":"Redmon","year":"2016"},{"key":"10.1016\/j.eswa.2026.132836_bib0048","doi-asserted-by":"crossref","unstructured":"Reimers, N., & Gurevych, I. (2020). Making monolingual sentence embeddings multilingual using knowledge distillation. arXiv preprint arXiv: 2004.09813.","DOI":"10.18653\/v1\/2020.emnlp-main.365"},{"key":"10.1016\/j.eswa.2026.132836_bib0049","series-title":"Medical image computing and computer-assisted intervention\u2013MICCAI 2015: 18th International conference, Munich, Germany, October 5\u20139, 2015, proceedings, Part III 18","first-page":"234","article-title":"U-Net: Convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"10.1016\/j.eswa.2026.132836_bib0050","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. (2024). Mindeye2: Shared-subject models enable fMRI-to-image with 1 hour of data. arXiv preprint arXiv: 2403.11207."},{"key":"10.1016\/j.eswa.2026.132836_bib0051","unstructured":"G. Team, Kamath, A., Ferret, J., Pathak, S., Vieillard, N., Merhej, R., Perrin, S., Matejovicova, T., Ram\u00e9, A., Rivi\u00e8re, M. et al. (2025). Gemma 3 technical report. arXiv preprint arXiv: 2503.19786."},{"issue":"4","key":"10.1016\/j.eswa.2026.132836_bib0052","doi-asserted-by":"crossref","first-page":"1104","DOI":"10.1016\/j.neuroimage.2006.06.062","article-title":"Inverse retinotopy: Inferring the visual content of images from brain activation patterns","volume":"33","author":"Thirion","year":"2006","journal-title":"Neuroimage"},{"key":"10.1016\/j.eswa.2026.132836_bib0053","unstructured":"Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Lacroix, T., Rozi\u00e8re, B., Goyal, N., Hambro, E., Azhar, F. et al. (2023). Llama: Open and efficient foundation language models. arXiv preprint arXiv: 2302.13971."},{"key":"10.1016\/j.eswa.2026.132836_bib0054","series-title":"2015 Fifth international conference on advanced computing & communication technologies","first-page":"143","article-title":"Eeg signal analysis for BCI interface: A review","author":"Vaid","year":"2015"},{"issue":"1","key":"10.1016\/j.eswa.2026.132836_bib0055","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1038\/s42003-019-0438-y","article-title":"Reconstructing faces from fMRI patterns using deep generative neural networks","volume":"2","author":"VanRullen","year":"2019","journal-title":"Communications Biology"},{"key":"10.1016\/j.eswa.2026.132836_bib0056","unstructured":"Wu, Z., Chen, X., Pan, Z., Liu, X., Liu, W., Dai, D., Gao, H., Ma, Y., Wu, C., Wang, B. et al. (2024). Deepseek-vl2: Mixture-of-experts vision-language models for advanced multimodal understanding. arXiv preprint arXiv: 2412.10302."},{"key":"10.1016\/j.eswa.2026.132836_bib0057","series-title":"The twelfth international conference on learning representations","article-title":"CLIP-MUSED: CLIP-Guided multi-subject visual neural information semantic decoding","author":"Zhou","year":"2024"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426017495?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426017495?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T13:37:38Z","timestamp":1779370658000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426017495"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":57,"alternative-id":["S0957417426017495"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132836","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Enhancing visual decoding with dynamic alignment strategy","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132836","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"132836"}}