{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T03:56:39Z","timestamp":1781150199203,"version":"3.54.1"},"reference-count":51,"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":[[2026,3,27]],"date-time":"2026-03-27T00:00:00Z","timestamp":1774569600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100014440","name":"Gobierno de Espana Ministerio de Ciencia e Innovacion","doi-asserted-by":"publisher","award":["PID2023-152133NB-I00"],"award-info":[{"award-number":["PID2023-152133NB-I00"]}],"id":[{"id":"10.13039\/100014440","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100023561","name":"Government of Spain Ministry of Universities","doi-asserted-by":"publisher","award":["FPU21\/02256"],"award-info":[{"award-number":["FPU21\/02256"]}],"id":[{"id":"10.13039\/501100023561","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007406","name":"Fundacion BBVA","doi-asserted-by":"publisher","award":["VIS4NN"],"award-info":[{"award-number":["VIS4NN"]}],"id":[{"id":"10.13039\/100007406","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003359","name":"Generalitat Valenciana","doi-asserted-by":"publisher","award":["CIPROM\/2021\/056"],"award-info":[{"award-number":["CIPROM\/2021\/056"]}],"id":[{"id":"10.13039\/501100003359","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003359","name":"Generalitat Valenciana","doi-asserted-by":"publisher","award":["GV\/2021\/074"],"award-info":[{"award-number":["GV\/2021\/074"]}],"id":[{"id":"10.13039\/501100003359","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004837","name":"Ministerio de Ciencia e Innovaci\u00f3n","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004837","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000780","name":"European Commission","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008530","name":"European Regional Development Fund","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100008530","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":[[2026,9]]},"DOI":"10.1016\/j.neunet.2026.108903","type":"journal-article","created":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T00:42:29Z","timestamp":1774658549000},"page":"108903","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Contrast sensitivity in multimodal large language models: A psychophysics-inspired evaluation"],"prefix":"10.1016","volume":"201","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2957-844X","authenticated-orcid":false,"given":"Pablo","family":"Hern\u00e1ndez-C\u00e1mara","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0469-3425","authenticated-orcid":false,"given":"Alexandra","family":"Gomez-Villa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jose Manuel","family":"Ja\u00e9n-Lorites","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8246-0195","authenticated-orcid":false,"given":"Jorge","family":"Vila-Tom\u00e1s","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Valero","family":"Laparra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jes\u00fas","family":"Malo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.108903_bib0001","doi-asserted-by":"crossref","first-page":"228","DOI":"10.1016\/j.neunet.2023.04.032","article-title":"Contrast sensitivity function in deep networks","volume":"164","author":"Akbarinia","year":"2023","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.108903_bib0002","unstructured":"Alabau-Bosque, N., Daud\u00e9n-Oliver, P., Vila-Tom\u00e1s, J., Laparra, V., & Malo, J. (2024). Invariance of deep image quality metrics to affine transformations. arXiv preprint arXiv: 2407.17927."},{"issue":"2","key":"10.1016\/j.neunet.2026.108903_bib0003","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1111\/j.2044-8317.1965.tb00341.x","article-title":"A learning model for forced-choice detection experiments 1","volume":"18","author":"Atkinson","year":"1965","journal-title":"British Journal of Mathematical and Statistical Psychology"},{"key":"10.1016\/j.neunet.2026.108903_bib0004","unstructured":"Bai, S., Chen, K., Liu, X., Wang, J., Ge, W., Song, S., Dang, K., Wang, P., Wang, S., Tang, J. et al. (2025). Qwen2. 5-vl technical report. arXiv preprint arXiv: 2502.13923."},{"key":"10.1016\/j.neunet.2026.108903_bib0005","doi-asserted-by":"crossref","unstructured":"Barten, P. G. J. (1999). Contrast sensitivity of the human eye and its effects on image quality. (1 ed.) SPIE press.","DOI":"10.1117\/3.353254"},{"key":"10.1016\/j.neunet.2026.108903_bib0006","unstructured":"Biscione, V., Yin, D., Malhotra, G., Dujmovic, M., Montero, M. L., Puebla, G., Adolfi, F., Heaton, R. F., Hummel, J. E., Evans, B. D. et al. (2024). Mindset: Vision. a toolbox for testing DNNs on key psychological experiments. arXiv preprint arXiv: 2404.05290."},{"issue":"4","key":"10.1016\/j.neunet.2026.108903_bib0007","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1163\/156856897X00357","article-title":"The psychophysics toolbox","volume":"10","author":"Brainard","year":"1997","journal-title":"Spatial Vision"},{"key":"10.1016\/j.neunet.2026.108903_bib0008","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"20039","article-title":"Do computer vision foundation models learn the low-level characteristics of the human visual system?","author":"Cai","year":"2025"},{"issue":"3","key":"10.1016\/j.neunet.2026.108903_bib0009","doi-asserted-by":"crossref","first-page":"551","DOI":"10.1113\/jphysiol.1968.sp008574","article-title":"Application of fourier analysis to the visibility of gratings","volume":"197","author":"Campbell","year":"1968","journal-title":"Journal of Physiology"},{"key":"10.1016\/j.neunet.2026.108903_bib0010","unstructured":"Chen, Z., Wang, W., Cao, Y., Liu, Y., Gao, Z., Cui, E., Zhu, J., Ye, S., Tian, H., Liu, Z. et al. (2024). Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling. arXiv preprint arXiv: 2412.05271."},{"key":"10.1016\/j.neunet.2026.108903_bib0011","series-title":"Forty-first international conference on machine learning","article-title":"Chatbot arena: An open platform for evaluating LLMS by human preference","author":"Chiang","year":"2024"},{"issue":"8","key":"10.1016\/j.neunet.2026.108903_bib0012","doi-asserted-by":"crossref","first-page":"977","DOI":"10.1117\/12.55666","article-title":"Application of a noise-adaptive contrast sensitivity function to image data compression","volume":"29","author":"Daly","year":"1990","journal-title":"Optical Engineering"},{"key":"10.1016\/j.neunet.2026.108903_bib0013","unstructured":"Daud\u00e9n-Oliver, P., Agost-Beltran, D., Sansano-Sansano, E., Laparra, V., Malo, J., & Mart\u00ednez-Garcia, M. (2024). Raid-database: Human responses to affine image distortions. arXiv preprint arXiv: 2412.10211."},{"issue":"1","key":"10.1016\/j.neunet.2026.108903_bib0014","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1113\/jphysiol.1984.sp015498","article-title":"Spatial and temporal contrast sensitivities of neurones in lateral geniculate nucleus of macaque","volume":"357","author":"Derrington","year":"1984","journal-title":"Journal of Physiology"},{"issue":"19-20","key":"10.1016\/j.neunet.2026.108903_bib0015","doi-asserted-by":"crossref","first-page":"1736","DOI":"10.1080\/09500340.2011.606374","article-title":"Red-green vs. blue-yellow spatio-temporal contrast sensitivity across the visual field","volume":"58","author":"D\u00edez-Ajenjo","year":"2011","journal-title":"Journal of Modern Optics"},{"key":"10.1016\/j.neunet.2026.108903_bib0016","unstructured":"Dictionary.com. flat (2025a). https:\/\/www.thesaurus.com\/browse\/flat. Accessed: 05\/09\/2025."},{"key":"10.1016\/j.neunet.2026.108903_bib0017","unstructured":"Dictionary.com. pattern (2025b). https:\/\/www.thesaurus.com\/browse\/pattern. Accessed: 05\/09\/2025."},{"key":"10.1016\/j.neunet.2026.108903_bib0018","unstructured":"Dictionary.com. visible (2025c). https:\/\/www.thesaurus.com\/browse\/visible. Accessed: 05\/09\/2025."},{"key":"10.1016\/j.neunet.2026.108903_bib0019","unstructured":"Errica, F., Siracusano, G., Sanvito, D., & Bifulco, R. (2024). What did i do wrong? Quantifying LLMs\u2019 sensitivity and consistency to prompt engineering. arXiv preprint arXiv: 2406.12334."},{"issue":"12","key":"10.1016\/j.neunet.2026.108903_bib0020","doi-asserted-by":"crossref","first-page":"1643","DOI":"10.1038\/nn1608","article-title":"A natural approach to studying vision","volume":"8","author":"Felsen","year":"2005","journal-title":"Nature Neuroscience"},{"key":"10.1016\/j.neunet.2026.108903_bib0021","series-title":"The Thirteenth International Conference on Learning Representations","article-title":"Can We Talk Models Into Seeing the World Differently?","author":"Gavrikov","year":"2025"},{"issue":"3","key":"10.1016\/j.neunet.2026.108903_bib0022","doi-asserted-by":"crossref","first-page":"627","DOI":"10.1113\/jphysiol.1975.sp011162","article-title":"Contrast constancy: Deblurring in human vision by spatial frequency channels","volume":"252","author":"Georgeson","year":"1975","journal-title":"Journal of Physiology"},{"key":"10.1016\/j.neunet.2026.108903_bib0023","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1016\/j.visres.2020.07.010","article-title":"Color illusions also deceive CNNs for low-level vision tasks: Analysis and implications","volume":"176","author":"Gomez-Villa","year":"2020","journal-title":"Vision Research"},{"key":"10.1016\/j.neunet.2026.108903_bib0024","series-title":"Proceedings of the computer vision and pattern recognition conference","first-page":"18642","article-title":"The art of deception: Color visual illusions and diffusion models","author":"Gomez-Villa","year":"2025"},{"key":"10.1016\/j.neunet.2026.108903_bib0025","series-title":"Introduction to Fourier optics, 3rd ed","author":"Goodman","year":"2005"},{"key":"10.1016\/j.neunet.2026.108903_bib0026","series-title":"Signal detection theory and psychophysics","volume":"vol. 1","author":"Green","year":"1966"},{"key":"10.1016\/j.neunet.2026.108903_bib0027","unstructured":"Howard, J., Imagenette: A smaller subset of 10 easily classified classes from imagenet (March 2019). https:\/\/github.com\/fastai\/imagenette."},{"issue":"3","key":"10.1016\/j.neunet.2026.108903_bib0028","doi-asserted-by":"crossref","first-page":"194","DOI":"10.1038\/35058500","article-title":"Computational modelling of visual attention","volume":"2","author":"Itti","year":"2001","journal-title":"Nature Reviews Neuroscience"},{"issue":"1","key":"10.1016\/j.neunet.2026.108903_bib0029","doi-asserted-by":"crossref","first-page":"1872","DOI":"10.1038\/s41467-021-22078-3","article-title":"Qualitative similarities and differences in visual object representations between brains and deep networks","volume":"12","author":"Jacob","year":"2021","journal-title":"Nature Communications"},{"issue":"10","key":"10.1016\/j.neunet.2026.108903_bib0030","doi-asserted-by":"crossref","first-page":"1340","DOI":"10.1364\/JOSA.69.001340","article-title":"Motion and vision. II. stabilized spatio-temporal threshold surface","volume":"69","author":"Kelly","year":"1979","journal-title":"Journal of the Optical Society of America"},{"key":"10.1016\/j.neunet.2026.108903_bib0031","series-title":"Psychophysics (second edition)","first-page":"55","article-title":"Chapter 4 - psychometric functions","author":"Kingdom","year":"2016"},{"key":"10.1016\/j.neunet.2026.108903_bib0032","unstructured":"K\u00fcmmerer, M., Theis, L., & Bethge, M. (2014). Deep gaze I: Boosting saliency prediction with feature maps trained on imagenet. arXiv preprint arXiv: 1411.1045."},{"issue":"6","key":"10.1016\/j.neunet.2026.108903_bib0033","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1167\/jov.22.6.8","article-title":"Contrast sensitivity functions in autoencoders","volume":"22","author":"Li","year":"2022","journal-title":"Journal of Vision"},{"key":"10.1016\/j.neunet.2026.108903_bib0034","first-page":"34892","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"9","key":"10.1016\/j.neunet.2026.108903_bib0035","doi-asserted-by":"crossref","first-page":"1165","DOI":"10.1016\/S0042-6989(02)00045-7","article-title":"The role of spatial frequency channels in letter identification","volume":"42","author":"Majaj","year":"2002","journal-title":"Vision Research"},{"key":"10.1016\/j.neunet.2026.108903_bib0036","unstructured":"Malo, J., & Luque, M. J. (2002). ColorLab: A matlab toolbox for color science and calibrated color image processing. https:\/\/isp.uv.es\/code\/vision_and_color\/colorlab\/content\/."},{"issue":"7","key":"10.1016\/j.neunet.2026.108903_bib0037","doi-asserted-by":"crossref","first-page":"535","DOI":"10.1016\/S0262-8856(96)00004-2","article-title":"Subjective image fidelity metric based on bit allocation of the human visual system in the DCT domain","volume":"15","author":"Malo","year":"1997","journal-title":"Image and Vision Computing"},{"issue":"1","key":"10.1016\/j.neunet.2026.108903_bib0038","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1113\/jphysiol.1985.sp015591","article-title":"The contrast sensitivity of human colour vision to red-green and blue-yellow chromatic gratings","volume":"359","author":"Mullen","year":"1985","journal-title":"The Journal of Physiology"},{"issue":"9","key":"10.1016\/j.neunet.2026.108903_bib0039","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1167\/9.9.4","article-title":"Scale dependence and channel switching in letter identification","volume":"9","author":"Oru\u00e7","year":"2009","journal-title":"Journal of Vision"},{"issue":"7","key":"10.1016\/j.neunet.2026.108903_bib0040","doi-asserted-by":"crossref","first-page":"689","DOI":"10.1016\/0042-6989(83)90210-9","article-title":"Contrast sensitivity throughout adulthood","volume":"23","author":"Owsley","year":"1983","journal-title":"Vision Research"},{"key":"10.1016\/j.neunet.2026.108903_bib0041","series-title":"International conference on machine learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"issue":"6479","key":"10.1016\/j.neunet.2026.108903_bib0042","doi-asserted-by":"crossref","first-page":"395","DOI":"10.1038\/369395a0","article-title":"The visual filter mediating letter identification","volume":"369","author":"Solomon","year":"1994","journal-title":"Nature"},{"key":"10.1016\/j.neunet.2026.108903_bib0043","series-title":"Advances in neural information processing systems","first-page":"4137","article-title":"Spatial-frequency channels, shape bias, and adversarial robustness","author":"Subramanian","year":"2023"},{"key":"10.1016\/j.neunet.2026.108903_bib0044","unstructured":"Tschannen, M., Gritsenko, A., Wang, X., Naeem, M. F., Alabdulmohsin, I., Parthasarathy, N., Evans, T., Beyer, L., Xia, Y., Mustafa, B. et al. (2025). Siglip 2: Multilingual vision-language encoders with improved semantic understanding, localization, and dense features. arXiv preprint arXiv: 2502.14786."},{"key":"10.1016\/j.neunet.2026.108903_bib0045","doi-asserted-by":"crossref","unstructured":"Vila-Tom\u00e1s, J., Hern\u00e1ndez-C\u00e1mara, P., Li, Q., Laparra, V., & Malo, J. (2025). A turing test for artificial nets devoted to model human vision. https:\/\/arxiv.org\/abs\/2502.00721.","DOI":"10.3389\/frai.2025.1665874"},{"key":"10.1016\/j.neunet.2026.108903_bib0046","series-title":"Proc. IEEE int. conf. im. proc. ICIP02","first-page":"41","article-title":"Video quality measures based on the standard spatial observer","author":"Watson","year":"2002"},{"issue":"9","key":"10.1016\/j.neunet.2026.108903_bib0047","doi-asserted-by":"crossref","first-page":"2379","DOI":"10.1364\/JOSAA.14.002379","article-title":"Model of visual contrast gain control and pattern masking","volume":"14","author":"Watson","year":"1997","journal-title":"Journal of the Optical Society of America A"},{"issue":"4","key":"10.1016\/j.neunet.2026.108903_bib0048","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1167\/jov.20.4.23","article-title":"Spatio-chromatic contrast sensitivity under mesopic and photopic light levels","volume":"20","author":"Wuerger","year":"2020","journal-title":"Journal of Vision"},{"key":"10.1016\/j.neunet.2026.108903_bib0049","series-title":"Proceedings of the computer vision and pattern recognition conference","first-page":"14203","article-title":"Magma: A foundation model for multimodal ai agents","author":"Yang","year":"2025"},{"key":"10.1016\/j.neunet.2026.108903_bib0050","series-title":"Proceedings of the computer vision and pattern recognition conference","first-page":"28790","article-title":"Are images indistinguishable to humans also indistinguishable to classifiers?","author":"You","year":"2025"},{"key":"10.1016\/j.neunet.2026.108903_bib0051","unstructured":"Zhu, J., Wang, W., Chen, Z., Liu, Z., Ye, S., Gu, L., Tian, H., Duan, Y., Su, W., Shao, J. et al. (2025). Internvl3: Exploring advanced training and test-time recipes for open-source multimodal models. arXiv preprint arXiv: 2504.10479."}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026003643?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026003643?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T03:01:33Z","timestamp":1781146893000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026003643"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":51,"alternative-id":["S0893608026003643"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108903","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Contrast sensitivity in multimodal large language models: A psychophysics-inspired evaluation","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108903","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Author(s). Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"108903"}}