{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T21:01:06Z","timestamp":1768942866337,"version":"3.49.0"},"reference-count":72,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T00:00:00Z","timestamp":1760659200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100020963","name":"Japan Science and Technology Agency Moonshot Research and Development Program","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020963","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1016\/j.neunet.2025.108222","type":"journal-article","created":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T06:47:45Z","timestamp":1760683665000},"page":"108222","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Investigating fine- and coarse-grained structural correspondences between deep neural networks and human object image similarity judgments using unsupervised alignment"],"prefix":"10.1016","volume":"195","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-4648-2487","authenticated-orcid":false,"given":"Soh","family":"Takahashi","sequence":"first","affiliation":[]},{"given":"Masaru","family":"Sasaki","sequence":"additional","affiliation":[]},{"given":"Ken","family":"Takeda","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8802-2607","authenticated-orcid":false,"given":"Masafumi","family":"Oizumi","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2025.108222_bib0001","series-title":"Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining","article-title":"Optuna: A next-generation hyperparameter optimization framework","author":"Akiba","year":"2019"},{"key":"10.1016\/j.neunet.2025.108222_bib0002","doi-asserted-by":"crossref","first-page":"1881","DOI":"10.18653\/v1\/D18-1214","article-title":"Gromov-wasserstein alignment of word embedding spaces","author":"Alvarez-Melis","year":"2018","journal-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing"},{"key":"10.1016\/j.neunet.2025.108222_bib0003","first-page":"25164","article-title":"The functional specialization of visual cortex emerges from training parallel pathways with self-supervised predictive learning","volume":"33","author":"Bakhtiari","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.108222_bib0004","series-title":"Proc. Natl. Acad. Sci. U. S. A.","first-page":"3253","article-title":"At 6\u20139 months, human infants know the meanings of many common nouns","volume":"109","author":"Bergelson","year":"2012"},{"issue":"1","key":"10.1016\/j.neunet.2025.108222_bib0005","first-page":"115","article-title":"Making a science of model search: Hyperparameter optimization in hundreds of dimensions for vision architectures","volume":"28","author":"Bergstra","year":"2013","journal-title":"ICML"},{"issue":"4","key":"10.1016\/j.neunet.2025.108222_bib0006","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1006111","article-title":"Computational mechanisms underlying cortical responses to the affordance properties of visual scenes","volume":"14","author":"Bonner","year":"2018","journal-title":"PLoS Computational Biology"},{"issue":"33","key":"10.1016\/j.neunet.2025.108222_bib0007","doi-asserted-by":"crossref","first-page":"6513","DOI":"10.1523\/JNEUROSCI.1714-18.2019","article-title":"The ventral visual pathway represents animal appearance over animacy, unlike human behavior and deep neural networks","volume":"39","author":"Bracci","year":"2019","journal-title":"The Journal of Neuroscience"},{"issue":"1","key":"10.1016\/j.neunet.2025.108222_bib0008","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1016\/j.cognition.2011.06.010","article-title":"Visual statistical learning in the newborn infant","volume":"121","author":"Bulf","year":"2011","journal-title":"Cognition"},{"issue":"12","key":"10.1016\/j.neunet.2025.108222_bib0009","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1003963","article-title":"Deep neural networks rival the representation of primate IT cortex for core visual object recognition","volume":"10","author":"Cadieu","year":"2014","journal-title":"PLoS Computational Biology"},{"key":"10.1016\/j.neunet.2025.108222_bib0010","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume":"33","author":"Caron","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.108222_bib0011","first-page":"3558","article-title":"Conceptual 12M: Pushing web-scale image-text pre-training to recognize long-tail visual concepts","author":"Changpinyo","year":"2021","journal-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"10.1016\/j.neunet.2025.108222_bib0012","unstructured":"Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020a). A simple framework for contrastive learning of visual representations. arXiv [cs.LG]."},{"key":"10.1016\/j.neunet.2025.108222_bib0013","first-page":"22243","article-title":"Big self-supervised models are strong semi-supervised learners","volume":"33","author":"Chen","year":"2020","journal-title":"Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.108222_bib0014","doi-asserted-by":"crossref","DOI":"10.1038\/srep27755","article-title":"Comparison of deep neural networks to spatio-temporal cortical dynamics of human visual object recognition reveals hierarchical correspondence","volume":"6","author":"Cichy","year":"2016","journal-title":"Scientific Reports"},{"key":"10.1016\/j.neunet.2025.108222_bib0015","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1016\/j.neuroimage.2019.03.031","article-title":"The spatiotemporal neural dynamics underlying perceived similarity for real-world objects","volume":"194","author":"Cichy","year":"2019","journal-title":"NeuroImage"},{"issue":"1","key":"10.1016\/j.neunet.2025.108222_bib0016","doi-asserted-by":"crossref","first-page":"9383","DOI":"10.1038\/s41467-024-53147-y","article-title":"A large-scale examination of inductive biases shaping high-level visual representation in brains and machines","volume":"15","author":"Conwell","year":"2024","journal-title":"Nature Communications"},{"issue":"8","key":"10.1016\/j.neunet.2025.108222_bib0017","doi-asserted-by":"crossref","first-page":"726","DOI":"10.1016\/j.tics.2024.05.001","article-title":"Helpless infants are learning a foundation model","volume":"28","author":"Cusack","year":"2024","journal-title":"Trends In Cognitive Sciences"},{"issue":"1","key":"10.1016\/j.neunet.2025.108222_bib0018","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1089\/cmb.2021.0446","article-title":"SCOT: Single-cell multi-omics alignment with optimal transport","volume":"29","author":"Demetci","year":"2022","journal-title":"Journal of Computational Biology"},{"key":"10.1016\/j.neunet.2025.108222_bib0019","doi-asserted-by":"crossref","unstructured":"Demetci, P., Santorella, R., Sandstede, B., & Singh, R. (2021). Unsupervised integration of single-cell multi-omics datasets with disparities in cell-type representation. arXiv: 2021.11.09, (467903).","DOI":"10.1101\/2021.11.09.467903"},{"key":"10.1016\/j.neunet.2025.108222_bib0020","first-page":"122406","article-title":"Evaluating alignment between humans and neural network representations in image-based learning tasks","volume":"37","author":"Demircan","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.108222_bib0021","series-title":"2009\u202fIEEE Conference on computer vision and pattern recognition","first-page":"248","article-title":"ImageNet: A large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"10.1016\/j.neunet.2025.108222_bib0022","series-title":"Proc. Natl. Acad. Sci. U. S. A.","first-page":"15822","article-title":"Statistical learning of new visual feature combinations by infants","volume":"99","author":"Fiser","year":"2002"},{"issue":"78","key":"10.1016\/j.neunet.2025.108222_bib0023","first-page":"78:1","article-title":"POT: Python optimal transport","volume":"22","author":"Flamary","year":"2021","journal-title":"Journal of Machine Learning Research : JMLR"},{"issue":"3","key":"10.1016\/j.neunet.2025.108222_bib0024","doi-asserted-by":"crossref","first-page":"677","DOI":"10.1017\/S0305000916000209","article-title":"Wordbank: An open repository for developmental vocabulary data","volume":"44","author":"Frank","year":"2017","journal-title":"Journal of Child Language"},{"key":"10.1016\/j.neunet.2025.108222_bib0025","first-page":"27092","article-title":"Datacomp: In search of the next generation of multimodal datasets","volume":"abs\/2304.14108","author":"Gadre","year":"2023","journal-title":"Neural Information Processing System"},{"key":"10.1016\/j.neunet.2025.108222_bib0026","first-page":"23885","article-title":"Partial success in closing the gap between human and machine vision","volume":"34","author":"Geirhos","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.108222_bib0027","unstructured":"Goyal, P., Caron, M., Lefaudeux, B., Xu, M., Wang, P., Pai, V., Singh, M., Liptchinsky, V., Misra, I., Joulin, A., & Bojanowski, P. (2021). Self-supervised pretraining of visual features in the wild. arXiv [cs.CV],."},{"key":"10.1016\/j.neunet.2025.108222_bib0028","doi-asserted-by":"crossref","DOI":"10.7554\/eLife.32962","article-title":"Distinct contributions of functional and deep neural network features to representational similarity of scenes in human brain and behavior","volume":"7","author":"Groen","year":"2018","journal-title":"eLife"},{"key":"10.1016\/j.neunet.2025.108222_bib0029","doi-asserted-by":"crossref","first-page":"434","DOI":"10.1016\/j.neuroimage.2018.02.044","article-title":"Multivariate pattern analysis for MEG: A comparison of dissimilarity measures","volume":"173","author":"Guggenmos","year":"2018","journal-title":"NeuroImage"},{"key":"10.1016\/j.neunet.2025.108222_bib0030","first-page":"16000","article-title":"Masked autoencoders are scalable vision learners","author":"He","year":"2022","journal-title":"In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition"},{"key":"10.1016\/j.neunet.2025.108222_bib0031","doi-asserted-by":"crossref","DOI":"10.7554\/eLife.82580","article-title":"THINGS-data, a multimodal collection of large-scale datasets for investigating object representations in human brain and behavior","volume":"12","author":"Hebart","year":"2023","journal-title":"eLife"},{"issue":"10","key":"10.1016\/j.neunet.2025.108222_bib0032","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0223792","article-title":"THINGS: A database of 1,854 object concepts and more than 26,000 naturalistic object images","volume":"14","author":"Hebart","year":"2019","journal-title":"PloS One"},{"issue":"11","key":"10.1016\/j.neunet.2025.108222_bib0033","doi-asserted-by":"crossref","first-page":"1173","DOI":"10.1038\/s41562-020-00951-3","article-title":"Revealing the multidimensional mental representations of natural objects underlying human similarity judgements","volume":"4","author":"Hebart","year":"2020","journal-title":"Nature Human Behaviour"},{"key":"10.1016\/j.neunet.2025.108222_bib0034","doi-asserted-by":"crossref","first-page":"1726","DOI":"10.3389\/fpsyg.2017.01726","article-title":"Deep convolutional neural networks outperform feature-based but not categorical models in explaining object similarity judgments","volume":"8","author":"Jozwik","year":"2017","journal-title":"Frontiers in Psychology"},{"key":"10.1016\/j.neunet.2025.108222_bib0035","doi-asserted-by":"crossref","DOI":"10.3389\/fncom.2025.1613291","article-title":"Exploring internal representation of self-supervised networks: Few-shot learning abilities and comparison with human semantics and recognition of objects","volume":"19","author":"Kataoka","year":"2025","journal-title":"Frontiers in Computational Neuroscience"},{"issue":"112029","key":"10.1016\/j.neunet.2025.108222_bib0036","article-title":"Is my \u201cred\u201d your \u201cred\u201d?: Evaluating structural correspondences between color similarity judgments using unsupervised alignment","volume":"28","author":"Kawakita","year":"2025","journal-title":"iScience"},{"issue":"1","key":"10.1016\/j.neunet.2025.108222_bib0037","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-024-65604-1","article-title":"Gromov\u2013Wasserstein unsupervised alignment reveals structural correspondences between the color similarity structures of humans and large language models","volume":"14","author":"Kawakita","year":"2023","journal-title":"Scientific Reports"},{"issue":"11","key":"10.1016\/j.neunet.2025.108222_bib0038","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1003915","article-title":"Deep supervised, but not unsupervised, models may explain IT cortical representation","volume":"10","author":"Khaligh-Razavi","year":"2014","journal-title":"PLoS Computational Biology"},{"issue":"1","key":"10.1016\/j.neunet.2025.108222_bib0039","doi-asserted-by":"crossref","DOI":"10.1038\/srep32672","article-title":"Deep networks can resemble human feed-forward vision in invariant object recognition","volume":"6","author":"Kheradpisheh","year":"2016","journal-title":"Scientific Reports"},{"key":"10.1016\/j.neunet.2025.108222_bib0040","series-title":"Proc. Natl. Acad. Sci. U S A","first-page":"21854","article-title":"Recurrence is required to capture the representational dynamics of the human visual system","volume":"116","author":"Kietzmann","year":"2019"},{"key":"10.1016\/j.neunet.2025.108222_bib0041","doi-asserted-by":"crossref","first-page":"368","DOI":"10.1016\/j.neuroimage.2019.04.079","article-title":"Similarity judgments and cortical visual responses reflect different properties of object and scene categories in naturalistic images","volume":"197","author":"King","year":"2019","journal-title":"NeuroImage"},{"issue":"2","key":"10.1016\/j.neunet.2025.108222_bib0042","doi-asserted-by":"crossref","first-page":"B35","DOI":"10.1016\/S0010-0277(02)00004-5","article-title":"Visual statistical learning in infancy: Evidence for a domain general learning mechanism","volume":"83","author":"Kirkham","year":"2002","journal-title":"Cognition"},{"issue":"1","key":"10.1016\/j.neunet.2025.108222_bib0043","doi-asserted-by":"crossref","first-page":"491","DOI":"10.1038\/s41467-022-28091-4","article-title":"A self-supervised domain-general learning framework for human ventral stream representation","volume":"13","author":"Konkle","year":"2022","journal-title":"Nature Communications"},{"key":"10.1016\/j.neunet.2025.108222_bib0044","first-page":"249","article-title":"Representational similarity analysis-connecting the branches of systems neuroscience","volume":"2","author":"Kriegeskorte","year":"2008","journal-title":"Frontiers in Systems Neuroscience"},{"issue":"4","key":"10.1016\/j.neunet.2025.108222_bib0045","doi-asserted-by":"crossref","first-page":"210","DOI":"10.1038\/s42256-020-0170-9","article-title":"A neural network trained for prediction mimics diverse features of biological neurons and perception","volume":"2","author":"Lotter","year":"2020","journal-title":"Nature Machine Intelligence"},{"issue":"6","key":"10.1016\/j.neunet.2025.108222_bib0046","doi-asserted-by":"crossref","first-page":"848","DOI":"10.1038\/s42256-025-01041-7","article-title":"Dimensions underlying the representational alignment of deep neural networks with humans","volume":"7","author":"Mahner","year":"2024","journal-title":"Nature Machine Intelligence"},{"key":"10.1016\/j.neunet.2025.108222_bib0047","series-title":"Proc. Natl. Acad. Sci. U. S. A.","article-title":"An ecologically motivated image dataset for deep learning yields better models of human vision","volume":"118","author":"Mehrer","year":"2021"},{"key":"10.1016\/j.neunet.2025.108222_bib0048","article-title":"Human alignment of neural network representations","author":"Muttenthaler","year":"2022","journal-title":"The Eleventh International Conference on Learning Representations"},{"key":"10.1016\/j.neunet.2025.108222_bib0049","doi-asserted-by":"crossref","DOI":"10.3389\/fninf.2021.679838","article-title":"THINGSvision: A python toolbox for streamlining the extraction of activations from deep neural networks","volume":"15","author":"Muttenthaler","year":"2021","journal-title":"Frontiers in Neuroinformatics"},{"issue":"4","key":"10.1016\/j.neunet.2025.108222_bib0050","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1007\/s10208-011-9093-5","article-title":"Gromov\u2013Wasserstein distances and the metric approach to object matching","volume":"11","author":"M\u00e9moli","year":"2011","journal-title":"Foundations of Computational Mathematics"},{"key":"10.1016\/j.neunet.2025.108222_bib0051","article-title":"What do self-supervised vision transformers learn?","author":"Park","year":"2023","journal-title":"International Conference on Learning Representations"},{"issue":"8","key":"10.1016\/j.neunet.2025.108222_bib0052","doi-asserted-by":"crossref","first-page":"2648","DOI":"10.1111\/cogs.12670","article-title":"Evaluating (and improving) the correspondence between deep neural networks and human representations","volume":"42","author":"Peterson","year":"2018","journal-title":"Cognitive Science"},{"issue":"5-6","key":"10.1016\/j.neunet.2025.108222_bib0053","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1561\/2200000073","article-title":"Computational optimal transport: With applications to data science","volume":"11","author":"Peyr\u00e9","year":"2019","journal-title":"Foundations and Trends\u00ae in Machine Learning"},{"key":"10.1016\/j.neunet.2025.108222_bib0054","series-title":"Proceedings of the 33rd international conference on machine learning","first-page":"2664","article-title":"Gromov-wasserstein averaging of kernel and distance matrices","volume":"vol. 48","author":"Peyr\u00e9","year":"2016"},{"issue":"39","key":"10.1016\/j.neunet.2025.108222_bib0055","doi-asserted-by":"crossref","DOI":"10.1126\/sciadv.adl1776","article-title":"Contrastive learning explains the emergence and function of visual category-selective regions","volume":"10","author":"Prince","year":"2024","journal-title":"Science Advances"},{"key":"10.1016\/j.neunet.2025.108222_bib0056","series-title":"Proceedings of the 38th international conference on machine learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume":"vol. 139","author":"Radford","year":"2021"},{"key":"10.1016\/j.neunet.2025.108222_bib0057","series-title":"2021\u202fIEEE\/CVF Conference on computer vision and pattern recognition (CVPR)","first-page":"3547","article-title":"Enriching imageNet with human similarity judgments and psychological embeddings","author":"Roads","year":"2021"},{"issue":"3","key":"10.1016\/j.neunet.2025.108222_bib0058","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"Imagenet large scale visual recognition challenge","volume":"115","author":"Russakovsky","year":"2015","journal-title":"International Journal of Computer Vision"},{"issue":"Volume 69, 2018","key":"10.1016\/j.neunet.2025.108222_bib0059","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1146\/annurev-psych-122216-011805","article-title":"Infant statistical learning","volume":"69","author":"Saffran","year":"2018","journal-title":"Annual Review of Psychology"},{"issue":"10","key":"10.1016\/j.neunet.2025.108222_bib0060","doi-asserted-by":"crossref","first-page":"1402","DOI":"10.1038\/s41562-021-01097-6","article-title":"Unsupervised learning predicts human perception and misperception of gloss","volume":"5","author":"Storrs","year":"2021","journal-title":"Nature Human Behaviour"},{"issue":"10","key":"10.1016\/j.neunet.2025.108222_bib0061","first-page":"2044","article-title":"Diverse deep neural networks all predict human inferior temporal cortex well, after training and fitting","volume":"33","author":"Storrs","year":"2021","journal-title":"Journal of Cognitive Neuroscience"},{"issue":"5","key":"10.1016\/j.neunet.2025.108222_bib0062","doi-asserted-by":"crossref","DOI":"10.1016\/j.isci.2025.112427","article-title":"Unsupervised alignment reveals structural commonalities and differences in neural representations of natural scenes across individuals and brain areas","volume":"28","author":"Takeda","year":"2025","journal-title":"iScience"},{"issue":"110443","key":"10.1016\/j.neunet.2025.108222_bib0063","article-title":"Unsupervised alignment in neuroscience: Introducing a toolbox for gromov-wasserstein optimal transport","author":"Takeda","year":"2025","journal-title":"Journal of Neuroscience Methods"},{"key":"10.1016\/j.neunet.2025.108222_bib0064","series-title":"Proceedings of the 26th annual international conference on machine learning","article-title":"Information theoretic measures for clusterings comparison: Is a correction for chance necessary?","author":"Vinh","year":"2009"},{"issue":"6682","key":"10.1016\/j.neunet.2025.108222_bib0065","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1126\/science.adi1374","article-title":"Grounded language acquisition through the eyes and ears of a single child","volume":"383","author":"Vong","year":"2024","journal-title":"Science"},{"issue":"12","key":"10.1016\/j.neunet.2025.108222_bib0066","doi-asserted-by":"crossref","first-page":"1415","DOI":"10.1038\/s42256-023-00753-y","article-title":"Better models of human high-level visual cortex emerge from natural language supervision with a large and diverse dataset","volume":"5","author":"Wang","year":"2023","journal-title":"Nature Machine Intelligence"},{"key":"10.1016\/j.neunet.2025.108222_bib0067","first-page":"9653","article-title":"SimMIM: A simple framework for masked image modeling","author":"Xie","year":"2022","journal-title":"In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition"},{"issue":"1","key":"10.1016\/j.neunet.2025.108222_bib0068","doi-asserted-by":"crossref","first-page":"2065","DOI":"10.1038\/s41467-021-22244-7","article-title":"Limits to visual representational correspondence between convolutional neural networks and the human brain","volume":"12","author":"Xu","year":"2021","journal-title":"Nature Communications"},{"key":"10.1016\/j.neunet.2025.108222_bib0069","first-page":"3093","article-title":"Hierarchical modular optimization of convolutional networks achieves representations similar to macaque IT and human ventral stream","volume":"26","author":"Yamins","year":"2013","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.108222_bib0070","series-title":"Proc. Natl. Acad. Sci. U. S. A.","first-page":"8619","article-title":"Performance-optimized hierarchical models predict neural responses in higher visual cortex","volume":"111","author":"Yamins","year":"2014"},{"key":"10.1016\/j.neunet.2025.108222_bib0071","article-title":"Revealing interpretable object representations from human behavior","author":"Zheng","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"10.1016\/j.neunet.2025.108222_bib0072","series-title":"Proc. Natl. Acad. Sci. U. S. A.","article-title":"Unsupervised neural network models of the ventral visual stream","volume":"118","author":"Zhuang","year":"2021"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608025011037?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608025011037?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T07:27:45Z","timestamp":1768894065000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608025011037"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":72,"alternative-id":["S0893608025011037"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2025.108222","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Investigating fine- and coarse-grained structural correspondences between deep neural networks and human object image similarity judgments using unsupervised alignment","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2025.108222","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 The Authors. Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"108222"}}