{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T20:29:18Z","timestamp":1782160158188,"version":"3.54.5"},"reference-count":60,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T00:00:00Z","timestamp":1699833600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T00:00:00Z","timestamp":1699833600000},"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":["Nat Mach Intell"],"DOI":"10.1038\/s42256-023-00753-y","type":"journal-article","created":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T17:02:08Z","timestamp":1699894928000},"page":"1415-1426","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":86,"title":["Better models of human high-level visual cortex emerge from natural language supervision with a large and diverse dataset"],"prefix":"10.1038","volume":"5","author":[{"given":"Aria Y.","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kendrick","family":"Kay","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas","family":"Naselaris","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4724-1744","authenticated-orcid":false,"given":"Michael J.","family":"Tarr","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8545-2062","authenticated-orcid":false,"given":"Leila","family":"Wehbe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,11,13]]},"reference":[{"key":"753_CR1","doi-asserted-by":"publisher","first-page":"8619","DOI":"10.1073\/pnas.1403112111","volume":"111","author":"DLK Yamins","year":"2014","unstructured":"Yamins, D. L. K. et al. Performance-optimized hierarchical models predict neural responses in higher visual cortex. Proc. Natl Acad. Sci. USA 111, 8619\u20138624 (2014).","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"753_CR2","doi-asserted-by":"publisher","first-page":"356","DOI":"10.1038\/nn.4244","volume":"19","author":"DLK Yamins","year":"2016","unstructured":"Yamins, D. L. K. & DiCarlo, J. J. Using goal-driven deep learning models to understand sensory cortex. Nat. Neurosci. 19, 356\u2013365 (2016).","journal-title":"Nat. Neurosci."},{"key":"753_CR3","doi-asserted-by":"publisher","first-page":"745","DOI":"10.1038\/s43588-022-00354-6","volume":"2","author":"M Toneva","year":"2022","unstructured":"Toneva, M., Mitchell, T. M. & Wehbe, L. Combining computational controls with natural text reveals aspects of meaning composition. Nat. Comput. Sci. 2, 745\u2013757 (2022).","journal-title":"Nat. Comput. Sci."},{"key":"753_CR4","doi-asserted-by":"crossref","unstructured":"Deng, J. et al. ImageNet: a large-scale hierarchical image database. In IEEE Conference on Computer Vision and Pattern Recognition 248\u2013255 (IEEE, 2009).","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"753_CR5","doi-asserted-by":"publisher","first-page":"e0128840","DOI":"10.1371\/journal.pone.0128840","volume":"10","author":"EM Aminoff","year":"2015","unstructured":"Aminoff, E. M. & Tarr, M. J. Associative processing is inherent in scene perception. PLoS ONE 10, e0128840 (2015).","journal-title":"PLoS ONE"},{"key":"753_CR6","doi-asserted-by":"publisher","first-page":"507","DOI":"10.1080\/02643290244000275","volume":"20","author":"I Gauthier","year":"2003","unstructured":"Gauthier, I., James, T. W., Curby, K. M. & Tarr, M. J. The influence of conceptual knowledge on visual discrimination. Cogn Neuropsychol. 20, 507\u2013523 (2003).","journal-title":"Cogn Neuropsychol."},{"key":"753_CR7","doi-asserted-by":"crossref","unstructured":"Schaffner, J., Bao, S. D., Tobler, P. N., Hare, T. A. & Polania, R. Sensory perception relies on fitness-maximizing codes. Nat. Hum. Behav. 7, 1135\u20131151 (2023).","DOI":"10.1038\/s41562-023-01584-y"},{"key":"753_CR8","doi-asserted-by":"publisher","first-page":"682","DOI":"10.1177\/0956797610366099","volume":"21","author":"G Lupyan","year":"2010","unstructured":"Lupyan, G., Thompson-Schill, S. L. & Swingley, D. Conceptual penetration of visual processing. Psychol. Sci. 21, 682\u2013691 (2010).","journal-title":"Psychol. Sci."},{"key":"753_CR9","unstructured":"Radford, A. et al. Learning transferable visual models from natural language supervision. In International Conference on Machine Learning (eds. Meila, M. & Zhang, T.) 8748\u20138763 (PMLR, 2021)."},{"key":"753_CR10","doi-asserted-by":"crossref","unstructured":"Li, L. H. et al. Grounded language-image pre-training. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition 10955\u201310965 (IEEE, 2022).","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"753_CR11","doi-asserted-by":"publisher","unstructured":"Yuan, L. et al. Florence: a new foundation model for computer vision. Preprint at https:\/\/doi.org\/10.48550\/arxiv.2111.11432 (2021).","DOI":"10.48550\/arxiv.2111.11432"},{"key":"753_CR12","unstructured":"Jia, C. et al. Scaling up visual and vision-language representation learning with noisy text supervision. In International Conference on Machine Learning (eds. Meila, M. & Zhang, T.) 4904\u20134916 (PMLR, 2021)."},{"key":"753_CR13","unstructured":"Wu dao 2.0. https:\/\/gpt3demo.com\/apps\/wu-dao-20 (accessed 20 October 2022)."},{"key":"753_CR14","unstructured":"Pinker, S.The language Instinct: How the Mind Creates Language (HarperCollins, 2007)."},{"key":"753_CR15","unstructured":"Fang, A. et al. Data determines distributional robustness in contrastive language image pre-training (CLIP). In Proceedings of international Conference on Machine Learning (eds. Chaudhuri, K. et al.) 6216\u20136234 (PMLR, 2022)."},{"key":"753_CR16","doi-asserted-by":"crossref","unstructured":"Mu, N., Kirillov, A., Wagner, D. & Xie, S. SLIP: self-supervision meets language-image pre-training. In Proceedings 17th European Conference on Computer Vision (eds. Avidan, S. & Brostow, G.) 529\u2013544 (Springer Nature, 2022).","DOI":"10.1007\/978-3-031-19809-0_30"},{"key":"753_CR17","doi-asserted-by":"publisher","unstructured":"Li, L. H., Yatskar, M., Yin, D., Hsieh, C.-J. & Chang, K.-W. VisualBERT: a simple and performant baseline for vision and language. Preprint at https:\/\/doi.org\/10.48550\/arXiv.1908.03557 (2019).","DOI":"10.48550\/arXiv.1908.03557"},{"key":"753_CR18","doi-asserted-by":"crossref","unstructured":"Tan, H. & Bansal, M. LXMERT: learning cross-modality encoder representations from transformers. In Conference on Emperical Natural Language Processing (eds Inui, K. et al.) 5099\u20135110 (Association for Computational Linguistics, 2019).","DOI":"10.18653\/v1\/D19-1514"},{"key":"753_CR19","doi-asserted-by":"publisher","first-page":"429","DOI":"10.1038\/nn1641","volume":"9","author":"SO Murray","year":"2006","unstructured":"Murray, S. O., Boyaci, H. & Kersten, D. The representation of perceived angular size in human primary visual cortex. Nat. Neurosci. 9, 429\u2013434 (2006).","journal-title":"Nat. Neurosci."},{"key":"753_CR20","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1038\/nrn3476","volume":"14","author":"CD Gilbert","year":"2013","unstructured":"Gilbert, C. D. & Li, W. Top-down influences on visual processing. Nat. Rev. Neurosci. 14, 350\u2013363 (2013).","journal-title":"Nat. Rev. Neurosci."},{"key":"753_CR21","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 770\u2013778 (IEEE, 2016).","DOI":"10.1109\/CVPR.2016.90"},{"key":"753_CR22","unstructured":"Devlin, J., Chang, M., Lee, K. & Toutanova, K. BERT: pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) (eds. Burstein, J. et al.) 4171\u20134186 (Association for Computational Linguistics, 2019)."},{"key":"753_CR23","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1016\/j.neuroimage.2010.07.073","volume":"56","author":"T Naselaris","year":"2011","unstructured":"Naselaris, T., Kay, K. N., Nishimoto, S. & Gallant, J. L. Encoding and decoding in fMRI. Neuroimage 56, 400\u2013410 (2011).","journal-title":"Neuroimage"},{"key":"753_CR24","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. et al. A massive 7T fMRI dataset to bridge cognitive neuroscience and artificial intelligence. Nat. Neurosci. 25, 116\u2013126 (2022).","journal-title":"Nat. Neurosci."},{"key":"753_CR25","unstructured":"Chen, T., Kornblith, S., Norouzi, M. & Hinton, G. A simple framework for contrastive learning of visual representations. In International Conference on Machine Learning (eds. Daum\u00e9 III, H. & Singh, A.) 1597-1607 (PMLR, 2020)."},{"key":"753_CR26","unstructured":"Schuhmann, C. et al. LAION-5B: an open large-scale dataset for training next generation image-text models. Adv. Neural Inf. Process. Syst. 35, 25278\u201325294 (2022)."},{"key":"753_CR27","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1145\/2812802","volume":"59","author":"B Thomee","year":"2016","unstructured":"Thomee, B. et al. YFCC100M: the new data in multimedia research. Commun. ACM 59, 64\u201373 (2016).","journal-title":"Commun. ACM"},{"key":"753_CR28","doi-asserted-by":"publisher","first-page":"10005","DOI":"10.1523\/JNEUROSCI.5023-14.2015","volume":"35","author":"U G\u00fc\u00e7l\u00fc","year":"2015","unstructured":"G\u00fc\u00e7l\u00fc, U. & van Gerven, M. A. Deep neural networks reveal a gradient in the complexity of neural representations across the ventral stream. J. Neurosci. 35, 10005\u201310014 (2015).","journal-title":"J. Neurosci."},{"key":"753_CR29","doi-asserted-by":"publisher","first-page":"453","DOI":"10.1038\/nature17637","volume":"532","author":"AG Huth","year":"2016","unstructured":"Huth, A. G., De Heer, W. A., Griffiths, T. L., Theunissen, F. E. & Gallant, J. L. Natural speech reveals the semantic maps that tile human cerebral cortex. Nature 532, 453\u2013458 (2016).","journal-title":"Nature"},{"key":"753_CR30","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. Scene perception in the human brain. Annu. Rev. Vis. Sci. 5, 373\u2013397 (2019).","journal-title":"Annu. Rev. Vis. Sci."},{"key":"753_CR31","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. A cortical area selective for visual processing of the human body. Science 293, 2470\u20132473 (2001).","journal-title":"Science"},{"key":"753_CR32","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1093\/brain\/115.1.15","volume":"115","author":"J Sergent","year":"1992","unstructured":"Sergent, J., Ohta, S. & MacDonald, B. Functional neuroanatomy of face and object processing: a positron emission tomography study. Brain 115, 15\u201336 (1992).","journal-title":"Brain"},{"key":"753_CR33","doi-asserted-by":"publisher","first-page":"4302","DOI":"10.1523\/JNEUROSCI.17-11-04302.1997","volume":"17","author":"N Kanwisher","year":"1997","unstructured":"Kanwisher, N., McDermott, J. & Chun, M. M. The fusiform face area: a module in human extrastriate cortex specialized for face perception. J. Neurosci. 17, 4302\u20134311 (1997).","journal-title":"J. Neurosci."},{"key":"753_CR34","doi-asserted-by":"publisher","first-page":"135","DOI":"10.3389\/fncom.2015.00135","volume":"9","author":"MD Lescroart","year":"2015","unstructured":"Lescroart, M. D., Stansbury, D. E. & Gallant, J. L. Fourier power, subjective distance, and object categories all provide plausible models of bold responses in scene-selective visual areas. Front. Comput. Neurosci. 9, 135 (2015).","journal-title":"Front. Comput. Neurosci."},{"key":"753_CR35","doi-asserted-by":"publisher","first-page":"6539","DOI":"10.1523\/JNEUROSCI.3267-16.2017","volume":"37","author":"WA de Heer","year":"2017","unstructured":"de Heer, W. A., Huth, A. G., Griffiths, T. L., Gallant, J. L. & Theunissen, F. E. The hierarchical cortical organization of human speech processing. J. Neurosci. 37, 6539\u20136557 (2017).","journal-title":"J. Neurosci."},{"key":"753_CR36","doi-asserted-by":"crossref","unstructured":"Saxe, R. & Kanwisher, N. People thinking about thinking people: the role of the temporo-parietal junction in \u201ctheory of mind\". NeuroImage. 19, 1835\u20131842 (2003).","DOI":"10.1016\/S1053-8119(03)00230-1"},{"key":"753_CR37","doi-asserted-by":"publisher","first-page":"763","DOI":"10.1038\/nn.3381","volume":"16","author":"T \u00c7ukur","year":"2013","unstructured":"\u00c7ukur, T., Nishimoto, S., Huth, A. G. & Gallant, J. L. Attention during natural vision warps semantic representation across the human brain. Nat. Neurosci. 16, 763\u2013770 (2013).","journal-title":"Nat. Neurosci."},{"key":"753_CR38","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1038\/s42003-023-04546-2","volume":"6","author":"N Jain","year":"2023","unstructured":"Jain, N. et al. Selectivity for food in human ventral visual cortex. Commun. Biol. 6, 175 (2023).","journal-title":"Commun. Biol."},{"key":"753_CR39","doi-asserted-by":"publisher","first-page":"134\u2013146.e4","DOI":"10.1016\/j.cub.2022.11.063","volume":"33","author":"IML Pennock","year":"2023","unstructured":"Pennock, I. M. L. et al. Color-biased regions in the ventral visual pathway are food selective. Curr. Biol. 33, 134\u2013146.e4 (2023).","journal-title":"Curr. Biol."},{"key":"753_CR40","doi-asserted-by":"publisher","first-page":"4159","DOI":"10.1016\/j.cub.2022.08.009","volume":"32","author":"M Khosla","year":"2022","unstructured":"Khosla, M., Apurva Ratan Murty, N. & Kanwisher, N. A highly selective response to food in human visual cortex revealed by hypothesis-free voxel decomposition. Curr. Biol. 32, 4159\u20134171.e9 (2022).","journal-title":"Curr. Biol."},{"key":"753_CR41","unstructured":"Conwell, C., Prince, J. S., Hamblin, C. J. & Alvarez, G. A. Controlled assessment of CLIP-style language-aligned vision models in prediction of brain & behavioral data. In ICLR 2023 Workshop on Mathematical and Empirical Understanding of Foundation Models (eds. Kumar, A. et al.) (2023)."},{"key":"753_CR42","doi-asserted-by":"publisher","unstructured":"Conwell, C., Prince, J. S., Alvarez, G. A. & Konkle, T. Large-scale benchmarking of diverse artificial vision models in prediction of 7T human neuroimaging data. Preprint at https:\/\/doi.org\/10.1101\/2022.03.28.485868 (2022).","DOI":"10.1101\/2022.03.28.485868"},{"key":"753_CR43","doi-asserted-by":"crossref","unstructured":"Conwell, C., Prince, J., Alvarez, G., Konkle, T. & Kay, K. Opportunistic experiments on a large-scale survey of diverse artificial vision models in prediction of 7T human fMRI data. In Conference on Cognitive Computational Neuroscience (2022).","DOI":"10.32470\/CCN.2022.1238-0"},{"key":"753_CR44","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1146\/annurev-psych-032720-041031","volume":"74","author":"S Bracci","year":"2023","unstructured":"Bracci, S. & Op de Beeck, H. P. Understanding human object vision: a picture is worth a thousand representations. Annu. Rev. Psychol. 74, 113\u2013135 (2023).","journal-title":"Annu. Rev. Psychol."},{"key":"753_CR45","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-019-0052-3","volume":"6","author":"N Chang","year":"2019","unstructured":"Chang, N., Pyles, J. A., Marcus, A., Gupta, A., Tarr, M. J. & Aminoff, E. M. BOLD5000, a public fMRI dataset while viewing 5000 visual images. Sci. Data 6, 49 (2019).","journal-title":"Sci. Data"},{"key":"753_CR46","doi-asserted-by":"publisher","first-page":"e82580","DOI":"10.7554\/eLife.82580","volume":"12","author":"MN Hebart","year":"2023","unstructured":"Hebart, M. N., Contier, O., Teichmann, L., Rockter, A. H., Zheng, C. Y., Kidder, A., Corriveau, A., Vaziri-Pashkam, M. & Baker, C. I. THINGS-data, a multimodal collection of large-scale datasets for investigating object representations in human brain and behavior. eLife 12, e82580 (2023).","journal-title":"eLife"},{"key":"753_CR47","doi-asserted-by":"publisher","first-page":"859","DOI":"10.3758\/s13415-018-00679-8","volume":"19","author":"M Maier","year":"2019","unstructured":"Maier, M. & Abdel Rahman, R. No matter how: top-down effects of verbal and semantic category knowledge on early visual perception. Cogn. Affect. Behav. Neurosci. 19, 859\u2013876 (2019).","journal-title":"Cogn. Affect. Behav. Neurosci."},{"key":"753_CR48","doi-asserted-by":"publisher","first-page":"539","DOI":"10.1167\/jov.20.11.539","volume":"20","author":"I Charest","year":"2020","unstructured":"Charest, I., Allen, E., Wu, Y., Naselaris, T. & Kay, K. Precise identification of semantic representations in the human brain. J. Vis. 20, 539\u2013539 (2020).","journal-title":"J. Vis."},{"key":"753_CR49","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-018-28865-1","volume":"8","author":"BJ Devereux","year":"2018","unstructured":"Devereux, B. J., Clarke, A. & Tyler, L. K. Integrated deep visual and semantic attractor neural networks predict fMRI pattern-information along the ventral object processing pathway. Sci. Rep. 8, 10636 (2018).","journal-title":"Sci. Rep."},{"key":"753_CR50","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1080\/15475440903167528","volume":"5","author":"R Nappa","year":"2009","unstructured":"Nappa, R., Wessel, A., McEldoon, K. L., Gleitman, L. R. & Trueswell, J. C. Use of Speaker\u2019s Gaze and Syntax in Verb Learning. Lang. Learn. Dev. 5, 203\u2013234 (2009).","journal-title":"Lang. Learn. Dev."},{"key":"753_CR51","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1006\/cogp.1995.1016","volume":"29","author":"SR Waxman","year":"1995","unstructured":"Waxman, S. R. & Markow, D. B. Words as invitations to form categories: evidence from 12- to 13-month-old infants. Cogn. Psychol. 29, 257\u2013302 (1995).","journal-title":"Cogn. Psychol."},{"key":"753_CR52","doi-asserted-by":"publisher","first-page":"1077","DOI":"10.1111\/j.1467-9280.2007.02028.x","volume":"18","author":"G Lupyan","year":"2007","unstructured":"Lupyan, G., Rakison, D. H. & McClelland, J. L. Language is not just for talking: redundant labels facilitate learning of novel categories. Psychol. Sci. 18, 1077\u20131083 (2007).","journal-title":"Psychol. Sci."},{"key":"753_CR53","doi-asserted-by":"crossref","unstructured":"Shusterman, A. & Spelke, E. in The Innate Mind: Structure and Contents (eds Carruthers, P. et al.) Ch. 6, 89\u2013106 (Oxford Univ. Press, 2005).","DOI":"10.1093\/acprof:oso\/9780195179675.003.0006"},{"key":"753_CR54","doi-asserted-by":"crossref","unstructured":"Lin, T. Y. et al. Microsoft COCO: common objects in context. In European Conference on Computer Vision \u2013 ECCV 2014. Lecture Notes in Computer Science, 8693 (eds. Fleet, D., Pajdla, T., Schiele, B., & Tuytelaars, T.) 740\u2013755 (Springer, 2014).","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"753_CR55","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1006\/nimg.1998.0395","volume":"9","author":"AM Dale","year":"1999","unstructured":"Dale, A. M., Fischl, B. & Sereno, M. I. Cortical surface-based analysis: I. segmentation and surface reconstruction. NeuroImage 9, 179\u2013194 (1999).","journal-title":"NeuroImage"},{"key":"753_CR56","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1006\/nimg.1998.0396","volume":"9","author":"B Fischl","year":"1999","unstructured":"Fischl, B., Sereno, M. I. & Dale, A. M. Cortical surface-based analysis: II. Inflation, flattening, and a surface-based coordinate system. NeuroImage 9, 195\u2013207 (1999).","journal-title":"NeuroImage"},{"key":"753_CR57","doi-asserted-by":"crossref","unstructured":"Gao, J. S., Huth, A. G., Lescroart, M. D. & Gallant, J. L. Pycortex: an interactive surface visualizer for fMRI. Front. Neuroinform. 9 (2015).","DOI":"10.3389\/fninf.2015.00023"},{"key":"753_CR58","unstructured":"Koushik, J. torch-gel. GitHub https:\/\/github.com\/jayanthkoushik\/torch-gel (2017)."},{"key":"753_CR59","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1111\/j.2517-6161.1995.tb02031.x","volume":"57","author":"Y Benjamini","year":"1995","unstructured":"Benjamini, Y. & Hochberg, Y. Controlling the false discovery rate: a practical and powerful approach to multiple testing. J. R. Stat. Soc. Series B Methodol. 57, 289\u2013300 (1995).","journal-title":"J. R. Stat. Soc. Series B Methodol."},{"key":"753_CR60","doi-asserted-by":"publisher","unstructured":"Wang, A. ariaaay\/clip2brain: initial release. Zenodo https:\/\/doi.org\/10.5281\/zenodo.8234313 (2023).","DOI":"10.5281\/zenodo.8234313"}],"container-title":["Nature Machine Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s42256-023-00753-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s42256-023-00753-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s42256-023-00753-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T22:44:39Z","timestamp":1730501079000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s42256-023-00753-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,13]]},"references-count":60,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["753"],"URL":"https:\/\/doi.org\/10.1038\/s42256-023-00753-y","relation":{},"ISSN":["2522-5839"],"issn-type":[{"value":"2522-5839","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,13]]},"assertion":[{"value":"9 November 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 October 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 November 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}