{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,17]],"date-time":"2026-10-17T11:41:01Z","timestamp":1792237261658,"version":"4.4.0"},"reference-count":93,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,5]],"date-time":"2026-09-05T00:00:00Z","timestamp":1788566400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376221"],"award-info":[{"award-number":["62376221"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076205"],"award-info":[{"award-number":["62076205"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["clinicalkey.com","clinicalkey.com.au","clinicalkey.es","clinicalkey.fr","clinicalkey.jp","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["NeuroImage"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.neuroimage.2026.122202","type":"journal-article","created":{"date-parts":[[2026,9,6]],"date-time":"2026-09-06T06:40:32Z","timestamp":1788676832000},"page":"122202","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Selective visuo-spatial attention revealed by fine-grained deep visual representations during naturalistic movie watching"],"prefix":"10.1016","volume":"340","author":[{"given":"Liting","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5927-9283","authenticated-orcid":false,"given":"Xin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengcheng","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shijie","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xintao","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neuroimage.2026.122202_bib1","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pbio.3003018","article-title":"Neural mechanisms for the attention-mediated propagation of conceptual information in the human brain","volume":"23","author":"Acunzo","year":"2025","journal-title":"PLoS Biol."},{"key":"10.1016\/j.neuroimage.2026.122202_bib2","doi-asserted-by":"crossref","first-page":"14675","DOI":"10.1073\/pnas.1202095109","article-title":"Top-down attention switches coupling between low-level and high-level areas of human visual cortex","volume":"109","author":"Al-Aidroos","year":"2012","journal-title":"Proc. Natl. Acad. Sci. U. S. A."},{"key":"10.1016\/j.neuroimage.2026.122202_bib3","doi-asserted-by":"crossref","DOI":"10.1038\/s41597-020-00680-2","article-title":"A naturalistic neuroimaging database for understanding the brain using ecological stimuli","volume":"7","author":"Aliko","year":"2020","journal-title":"Sci. Data"},{"key":"10.1016\/j.neuroimage.2026.122202_bib4","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":"Nat. Neurosci."},{"key":"10.1016\/j.neuroimage.2026.122202_bib5","series-title":"Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017","article-title":"Network dissection: quantifying interpretability of deep visual representations","author":"Bau","year":"2017"},{"key":"10.1016\/j.neuroimage.2026.122202_bib6","doi-asserted-by":"crossref","first-page":"30071","DOI":"10.1073\/pnas.1907375117","article-title":"Understanding the role of individual units in a deep neural network","volume":"117","author":"Bau","year":"2020","journal-title":"Proc. Natl. Acad. Sci. U. S. A."},{"key":"10.1016\/j.neuroimage.2026.122202_bib7","doi-asserted-by":"crossref","first-page":"832","DOI":"10.1016\/j.neuron.2015.10.001","article-title":"A source for feature-based attention in the prefrontal cortex","volume":"88","author":"Bichot","year":"2015","journal-title":"Neuron"},{"key":"10.1016\/j.neuroimage.2026.122202_bib8","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1146\/annurev-neuro-060909-152823","article-title":"Attention, intention, and priority in the parietal lobe","volume":"33","author":"Bisley","year":"2010","journal-title":"Annu. Rev. Neurosci."},{"key":"10.1016\/j.neuroimage.2026.122202_bib9","doi-asserted-by":"crossref","first-page":"4504","DOI":"10.1109\/TPAMI.2024.3355155","article-title":"B-cos alignment for inherently interpretable CNNs and vision transformers","volume":"46","author":"Bohle","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neuroimage.2026.122202_bib10","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1016\/j.neuroimage.2012.11.031","article-title":"Sensory processing during viewing of cinematographic material: computational modeling and functional neuroimaging","volume":"67","author":"Bordier","year":"2013","journal-title":"Neuroimage"},{"key":"10.1016\/j.neuroimage.2026.122202_bib11","doi-asserted-by":"crossref","first-page":"864","DOI":"10.3758\/s13428-011-0092-x","article-title":"iMap: a novel method for statistical fixation mapping of eye movement data","volume":"43","author":"Caldara","year":"2011","journal-title":"Behav. Res. Methods"},{"key":"10.1016\/j.neuroimage.2026.122202_bib12","series-title":"Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition","article-title":"Explaining knowledge distillation by quantifying the knowledge","author":"Cheng","year":"2020"},{"key":"10.1016\/j.neuroimage.2026.122202_bib13","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1016\/j.bbr.2012.09.027","article-title":"Two cognitive and neural systems for endogenous and exogenous spatial attention","volume":"237","author":"Chica","year":"2013","journal-title":"Behav. Brain Res."},{"key":"10.1016\/j.neuroimage.2026.122202_bib14","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1009356","article-title":"AIM: a network model of attention in auditory cortex","volume":"17","author":"Chou","year":"2021","journal-title":"PLoS Comput. Biol."},{"key":"10.1016\/j.neuroimage.2026.122202_bib15","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1162\/imag_a_00327","article-title":"High-resolution 7T fMRI reveals the visual zone of the human claustrum","volume":"2","author":"Coates","year":"2024","journal-title":"Imaging Neurosci."},{"key":"10.1016\/j.neuroimage.2026.122202_bib16","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1038\/nrn755","article-title":"Control of goal-directed and stimulus-driven attention in the brain","volume":"3","author":"Corbetta","year":"2002","journal-title":"Nat. Rev. Neurosci."},{"key":"10.1016\/j.neuroimage.2026.122202_bib17","doi-asserted-by":"crossref","first-page":"763","DOI":"10.1038\/nn.3381","article-title":"Attention during natural vision warps semantic representation across the human brain","volume":"16","author":"\u00c7ukur","year":"2013","journal-title":"Nat. Neurosci."},{"key":"10.1016\/j.neuroimage.2026.122202_bib18","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1146\/annurev.ne.18.030195.001205","article-title":"Neural mechanisms of selective visual attention","volume":"18","author":"Desimone","year":"1995","journal-title":"Annu. Rev. Neurosci."},{"key":"10.1016\/j.neuroimage.2026.122202_bib19","doi-asserted-by":"crossref","DOI":"10.1126\/sciadv.abl8913","article-title":"Brain-like functional specialization emerges spontaneously in deep neural networks","volume":"8","author":"Dobs","year":"2022","journal-title":"Sci. Adv."},{"key":"10.1016\/j.neuroimage.2026.122202_bib20","doi-asserted-by":"crossref","first-page":"431","DOI":"10.1038\/s41583-023-00705-w","article-title":"The neuroconnectionist research programme","volume":"24","author":"Doerig","year":"2023","journal-title":"Nat. Rev. Neurosci."},{"key":"10.1016\/j.neuroimage.2026.122202_bib21","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"2758","article-title":"FlowNet: learning optical flow with convolutional networks","author":"Dosovitskiy","year":"2015"},{"key":"10.1016\/j.neuroimage.2026.122202_bib22","doi-asserted-by":"crossref","DOI":"10.1162\/imag_a_00575","article-title":"The Voxelwise encoding model framework: a tutorial introduction to fitting encoding models to fMRI data","volume":"3","author":"Dupr\u00e9 la Tour","year":"2025","journal-title":"Imaging Neurosci."},{"key":"10.1016\/j.neuroimage.2026.122202_bib23","doi-asserted-by":"crossref","first-page":"184","DOI":"10.1016\/j.neuroimage.2016.10.001","article-title":"Seeing it all: convolutional network layers map the function of the human visual system","volume":"152","author":"Eickenberg","year":"2017","journal-title":"Neuroimage"},{"key":"10.1016\/j.neuroimage.2026.122202_bib24","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1011792","article-title":"High-performing neural network models of visual cortex benefit from high latent dimensionality","volume":"20","author":"Elmoznino","year":"2024","journal-title":"PLoS Comput. Biol."},{"key":"10.1016\/j.neuroimage.2026.122202_bib25","doi-asserted-by":"crossref","DOI":"10.1016\/j.cognition.2019.104119","article-title":"The role of selective attention in cross-modal interactions between auditory and visual features","volume":"196","author":"Evans","year":"2020","journal-title":"Cognition"},{"key":"10.1016\/j.neuroimage.2026.122202_bib26","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1109\/TCSVT.2013.2273613","article-title":"A video saliency detection model in compressed domain","volume":"24","author":"Fang","year":"2014","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neuroimage.2026.122202_bib27","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1146\/annurev-psych-010418-103429","article-title":"Functional specialization in the attention network","volume":"71","author":"Fiebelkorn","year":"2020","journal-title":"Annu. Rev. Psychol."},{"key":"10.1016\/j.neuroimage.2026.122202_bib28","series-title":"The Interface of Language, Vision, and Action: Eye Movements and the Visual World","article-title":"Eye scanning and visual search","author":"Findlay","year":"2004"},{"key":"10.1016\/j.neuroimage.2026.122202_bib29","series-title":"Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition","article-title":"Net2Vec: quantifying and explaining how concepts are encoded by filters in deep neural networks","author":"Fong","year":"2018"},{"key":"10.1016\/j.neuroimage.2026.122202_bib30","doi-asserted-by":"crossref","first-page":"9673","DOI":"10.1073\/pnas.0504136102","article-title":"The human brain is intrinsically organized into dynamic, anticorrelated functional networks","volume":"102","author":"Fox","year":"2005","journal-title":"Proc. Natl. Acad. Sci. U. S. A."},{"key":"10.1016\/j.neuroimage.2026.122202_bib31","doi-asserted-by":"crossref","DOI":"10.3389\/fnint.2020.00010","article-title":"What can computational models learn from Human selective attention? A review from an audiovisual unimodal and crossmodal perspective","volume":"14","author":"Fu","year":"2020","journal-title":"Front. Integr. Neurosci."},{"key":"10.1016\/j.neuroimage.2026.122202_bib32","series-title":"12th International Conference on Learning Representations, ICLR 2024","article-title":"Interpreting clip\u2019S image representation via text-based decomposition","author":"Gandelsman","year":"2024"},{"key":"10.1016\/j.neuroimage.2026.122202_bib33","doi-asserted-by":"crossref","first-page":"R22","DOI":"10.1016\/j.cub.2009.11.046","article-title":"Multisensory integration: vision boosts information through suppression in auditory cortex","volume":"20","author":"Ghazanfar","year":"2010","journal-title":"Curr. Biol."},{"key":"10.1016\/j.neuroimage.2026.122202_bib34","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1016\/j.neuroimage.2013.04.127","article-title":"The minimal preprocessing pipelines for the human connectome project","volume":"80","author":"Glasser","year":"2013","journal-title":"Neuroimage"},{"key":"10.1016\/j.neuroimage.2026.122202_bib35","doi-asserted-by":"crossref","first-page":"10005","DOI":"10.1523\/JNEUROSCI.5023-14.2015","article-title":"Deep neural networks reveal a gradient in the complexity of neural representations across the ventral stream","volume":"35","author":"G\u00fc\u00e7l\u00fc","year":"2015","journal-title":"J. Neurosci."},{"key":"10.1016\/j.neuroimage.2026.122202_bib36","doi-asserted-by":"crossref","first-page":"495","DOI":"10.1146\/annurev-vision-101322-011902","article-title":"Decoding covert visual attention in space and time from neural signals","volume":"11","author":"Hamed","year":"2025","journal-title":"Annu. Rev. Vis. Sci."},{"key":"10.1016\/j.neuroimage.2026.122202_bib37","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1016\/j.neuropsychologia.2017.02.024","article-title":"Functional connectivity between prefrontal and parietal cortex drives visuo-spatial attention shifts","volume":"99","author":"Heinen","year":"2017","journal-title":"Neuropsychologia"},{"key":"10.1016\/j.neuroimage.2026.122202_bib38","doi-asserted-by":"crossref","first-page":"498","DOI":"10.1016\/j.tics.2003.09.006","article-title":"Human gaze control during real-world scene perception","volume":"7","author":"Henderson","year":"2003","journal-title":"Trends Cogn. Sci."},{"key":"10.1016\/j.neuroimage.2026.122202_bib40","article-title":"Neural processing of naturalistic audiovisual events in space and time","volume":"8","author":"Hu","year":"2025","journal-title":"Commun. Biol."},{"key":"10.1016\/j.neuroimage.2026.122202_bib39","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1109\/TAMD.2015.2409835","article-title":"Sparsity-constrained fMRI decoding of visual saliency in naturalistic video streams","volume":"7","author":"Hu","year":"2015","journal-title":"IEEE Trans. Auton. Ment. Dev."},{"key":"10.1016\/j.neuroimage.2026.122202_bib41","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"262","article-title":"SALICON: reducing the semantic gap in saliency prediction by adapting deep neural networks","author":"Huang","year":"2015"},{"key":"10.1016\/j.neuroimage.2026.122202_bib42","doi-asserted-by":"crossref","first-page":"1729","DOI":"10.1006\/nimg.2002.1330","article-title":"Visual imagery of famous faces: effects of memory and attention revealed by fMRI","volume":"17","author":"Ishai","year":"2002","journal-title":"Neuroimage"},{"key":"10.1016\/j.neuroimage.2026.122202_bib43","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":"Nat. Rev. Neurosci."},{"key":"10.1016\/j.neuroimage.2026.122202_bib44","doi-asserted-by":"crossref","first-page":"1254","DOI":"10.1109\/34.730558","article-title":"A model of saliency-based visual attention for rapid scene analysis","volume":"20","author":"Itti","year":"1998","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neuroimage.2026.122202_bib45","series-title":"Lecture Notes in Computer Science (Including Subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics","first-page":"625","article-title":"Deepvs: a deep learning based video saliency prediction approach","author":"Jiang","year":"2018"},{"key":"10.1016\/j.neuroimage.2026.122202_bib46","series-title":"International Speech Communication Association - 8th Annual Conference of the International Speech Communication Association, Interspeech 2007","article-title":"A saliency-based auditory attention model with applications to unsupervised prominent syllable detection in speech","author":"Kalinli","year":"2007"},{"key":"10.1016\/j.neuroimage.2026.122202_bib47","doi-asserted-by":"crossref","first-page":"315","DOI":"10.1146\/annurev.neuro.23.1.315","article-title":"Mechanisms of visual attention in the human cortex","volume":"23","author":"Kastner","year":"2000","journal-title":"Annu. Rev. Neurosci."},{"key":"10.1016\/j.neuroimage.2026.122202_bib48","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 Comput. Biol."},{"key":"10.1016\/j.neuroimage.2026.122202_bib49","doi-asserted-by":"crossref","first-page":"2175","DOI":"10.1162\/jocn.2008.20152","article-title":"Visual processing affects the neural basis of auditory discrimination","volume":"20","author":"Kislyuk","year":"2008","journal-title":"J. Cogn. Neurosci."},{"key":"10.1016\/j.neuroimage.2026.122202_bib50","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1146\/annurev-vision-082114-035447","article-title":"Deep Neural networks: a new framework for modeling biological vision and brain information processing","volume":"1","author":"Kriegeskorte","year":"2015","journal-title":"Annu. Rev. Vis. Sci."},{"key":"10.1016\/j.neuroimage.2026.122202_bib51","doi-asserted-by":"crossref","DOI":"10.1126\/sciadv.ade6049","article-title":"Toward naturalistic neuroscience: mechanisms underlying the flattening of brain hierarchy in movie-watching compared to rest and task","volume":"9","author":"Kringelbach","year":"2023","journal-title":"Sci. Adv."},{"key":"10.1016\/j.neuroimage.2026.122202_bib52","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"4799","article-title":"Understanding low- and high-level contributions to fixation prediction","author":"Kummerer","year":"2017"},{"issue":"80\u2013","key":"10.1016\/j.neuroimage.2026.122202_bib53","doi-asserted-by":"crossref","first-page":"581","DOI":"10.1126\/science.abi6671","article-title":"A fast link between face perception and memory in the temporal pole","volume":"373","author":"Landi","year":"2021","journal-title":"Science"},{"key":"10.1016\/j.neuroimage.2026.122202_bib54","doi-asserted-by":"crossref","first-page":"420","DOI":"10.1162\/089892902317361930","article-title":"Deactivation of sensory-specific cortex by cross-modal stimuli","volume":"14","author":"Laurienti","year":"2002","journal-title":"J. Cogn. Neurosci."},{"key":"10.1016\/j.neuroimage.2026.122202_bib55","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"10.1016\/j.neuroimage.2026.122202_bib56","doi-asserted-by":"crossref","first-page":"5012","DOI":"10.1109\/TIP.2016.2602079","article-title":"Visual saliency detection based on multiscale deep CNN features","volume":"25","author":"Li","year":"2016","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.neuroimage.2026.122202_bib57","series-title":"Proceedings - International Conference on Image Processing, ICIP","first-page":"3066","article-title":"How sound affects visual attention in omnidirectional videos","author":"Li","year":"2022"},{"key":"10.1016\/j.neuroimage.2026.122202_bib58","doi-asserted-by":"crossref","DOI":"10.1016\/j.buildenv.2020.107177","article-title":"Effect of sound on visual attention in large railway stations: a case study of St. Pancras railway station in London","volume":"185","author":"Liu","year":"2020","journal-title":"Build. Environ."},{"key":"10.1016\/j.neuroimage.2026.122202_bib59","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1016\/j.neucom.2022.04.080","article-title":"TranSalNet: towards perceptually relevant visual saliency prediction","volume":"494","author":"Lou","year":"2022","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neuroimage.2026.122202_bib60","series-title":"12th International Conference on Learning Representations, ICLR 2024","article-title":"Brainscuba: fine-grained natural language captions of visual cortex selectivity","author":"Luo","year":"2024"},{"key":"10.1016\/j.neuroimage.2026.122202_bib61","doi-asserted-by":"crossref","first-page":"2469","DOI":"10.1016\/j.neuron.2023.04.023","article-title":"20 years of the default mode network: a review and synthesis","volume":"111","author":"Menon","year":"2023","journal-title":"Neuron"},{"key":"10.1016\/j.neuroimage.2026.122202_bib62","series-title":"MM\u201911 - Proceedings of the 2011 ACM Multimedia Conference and Co-Located Workshops","first-page":"373","article-title":"Prediction of the inter-observer visual congruency (IOVC) and application to image ranking","author":"Meur","year":"2011"},{"key":"10.1016\/j.neuroimage.2026.122202_bib63","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1146\/annurev-psych-122414-033400","article-title":"Neural mechanisms of selective visual attention","volume":"68","author":"Moore","year":"2017","journal-title":"Annu. Rev. Psychol."},{"key":"10.1016\/j.neuroimage.2026.122202_bib64","doi-asserted-by":"crossref","DOI":"10.1186\/1471-2377-8-35","article-title":"Cross-modal deactivations during modality-specific selective attention","volume":"8","author":"Mozolic","year":"2008","journal-title":"BMC Neurol."},{"key":"10.1016\/j.neuroimage.2026.122202_bib65","doi-asserted-by":"crossref","first-page":"393","DOI":"10.1016\/j.neuroimage.2018.01.017","article-title":"Distant from input: evidence of regions within the default mode network supporting perceptually-decoupled and conceptually-guided cognition","volume":"171","author":"Murphy","year":"2018","journal-title":"Neuroimage"},{"key":"10.1016\/j.neuroimage.2026.122202_bib66","doi-asserted-by":"crossref","first-page":"1015","DOI":"10.1016\/j.neuron.2011.02.020","article-title":"Stimulus-driven orienting of visuo-spatial attention in complex dynamic environments","volume":"69","author":"Nardo","year":"2011","journal-title":"Neuron"},{"key":"10.1016\/j.neuroimage.2026.122202_bib67","doi-asserted-by":"crossref","DOI":"10.1038\/s41597-021-01033-3","article-title":"The \u201cNarratives\u201d fMRI dataset for evaluating models of naturalistic language comprehension","volume":"8","author":"Nastase","year":"2021","journal-title":"Sci. Data"},{"key":"10.1016\/j.neuroimage.2026.122202_bib68","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1016\/j.visres.2004.07.042","article-title":"Modeling the influence of task on attention","volume":"45","author":"Navalpakkam","year":"2005","journal-title":"Vision Res."},{"key":"10.1016\/j.neuroimage.2026.122202_bib69","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1016\/j.neulet.2015.12.039","article-title":"The effects of selective and divided attention on sensory precision and integration","volume":"614","author":"Odegaard","year":"2016","journal-title":"Neurosci. Lett."},{"key":"10.1016\/j.neuroimage.2026.122202_bib70","doi-asserted-by":"crossref","DOI":"10.1093\/cercor\/bhaf284","article-title":"Temporal propagation of neural state boundaries in naturalistic context","volume":"35","author":"Oetringer","year":"2025","journal-title":"Cereb. Cortex"},{"key":"10.1016\/j.neuroimage.2026.122202_bib71","series-title":"13th International Conference on Learning Representations, ICLR 2025","first-page":"363","article-title":"Multi-modal brain encoding models for Multi-modal stimuli","author":"Oota","year":"2025"},{"key":"10.1016\/j.neuroimage.2026.122202_bib72","doi-asserted-by":"crossref","first-page":"3478","DOI":"10.1093\/cercor\/bhac285","article-title":"Brain areas associated with visual spatial attention display topographic organization during auditory spatial attention","volume":"33","author":"Popov","year":"2023","journal-title":"Cereb. Cortex"},{"key":"10.1016\/j.neuroimage.2026.122202_bib73","doi-asserted-by":"crossref","first-page":"676","DOI":"10.1073\/pnas.98.2.676","article-title":"A default mode of brain function","volume":"98","author":"Raichle","year":"2001","journal-title":"Proc. Natl. Acad. Sci. U. S. A."},{"key":"10.1016\/j.neuroimage.2026.122202_bib74","series-title":"Proceedings of the IEEE Computer Society 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.neuroimage.2026.122202_bib75","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1111\/j.1749-6632.2010.05448.x","article-title":"The neural mechanisms of visual selection: the view from neuropsychology","volume":"1191","author":"Riddoch","year":"2010","journal-title":"Ann. N. Y. Acad. Sci."},{"key":"10.1016\/j.neuroimage.2026.122202_bib76","doi-asserted-by":"crossref","DOI":"10.1111\/psyp.13585","article-title":"Selective visual attention to emotional pictures: interactions of task-relevance and emotion are restricted to the late positive potential","volume":"57","author":"Schindler","year":"2020","journal-title":"Psychophysiology"},{"key":"10.1016\/j.neuroimage.2026.122202_bib77","doi-asserted-by":"crossref","DOI":"10.1038\/ncomms12141","article-title":"Dynamic reconfiguration of the default mode network during narrative comprehension","volume":"7","author":"Simony","year":"2016","journal-title":"Nat. Commun."},{"key":"10.1016\/j.neuroimage.2026.122202_bib78","doi-asserted-by":"crossref","first-page":"S208","DOI":"10.1016\/j.neuroimage.2004.07.051","article-title":"Advances in functional and structural MR image analysis and implementation as FSL","volume":"23","author":"Smith","year":"2004","journal-title":"Neuroimage"},{"key":"10.1016\/j.neuroimage.2026.122202_bib79","doi-asserted-by":"crossref","first-page":"766","DOI":"10.1037\/0033-295X.113.4.766","article-title":"Contextual guidance of eye movements and attention in real-world scenes: the role of global features in object search","volume":"113","author":"Torralba","year":"2006","journal-title":"Psychol. Rev."},{"key":"10.1016\/j.neuroimage.2026.122202_bib80","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1016\/j.neuroimage.2013.05.041","article-title":"The WU-minn human connectome project: an overview","volume":"80","author":"Van Essen","year":"2013","journal-title":"Neuroimage"},{"key":"10.1016\/j.neuroimage.2026.122202_bib81","doi-asserted-by":"crossref","DOI":"10.1523\/ENEURO.0200-20.2020","article-title":"Correspondence between monkey visual cortices and layers of a saliency map model based on a deep convolutional neural network for representations of natural images","volume":"8","author":"Wagatsuma","year":"2021","journal-title":"eNeuro"},{"key":"10.1016\/j.neuroimage.2026.122202_bib82","doi-asserted-by":"crossref","first-page":"162","DOI":"10.1016\/j.neunet.2017.09.007","article-title":"Visualizing deep neural network by alternately image blurring and deblurring","volume":"97","author":"Wang","year":"2018","journal-title":"Neural Netw."},{"key":"10.1016\/j.neuroimage.2026.122202_bib83","doi-asserted-by":"crossref","first-page":"971","DOI":"10.1038\/nn1727","article-title":"The neural bases of momentary lapses in attention","volume":"9","author":"Weissman","year":"2006","journal-title":"Nat. Neurosci."},{"key":"10.1016\/j.neuroimage.2026.122202_bib84","doi-asserted-by":"crossref","first-page":"1308","DOI":"10.1016\/j.cub.2023.02.042","article-title":"Engaging in word recognition elicits highly specific modulations in visual cortex","volume":"33","author":"White","year":"2023","journal-title":"Curr. Biol."},{"key":"10.1016\/j.neuroimage.2026.122202_bib85","article-title":"Spontaneously emerging patterns in human visual cortex reflect responses to naturalistic sensory stimuli","volume":"27","author":"Wilf","year":"2017","journal-title":"Cereb. Cortex"},{"key":"10.1016\/j.neuroimage.2026.122202_bib86","doi-asserted-by":"crossref","first-page":"S173","DOI":"10.1016\/j.neuroimage.2008.10.055","article-title":"Bayesian analysis of neuroimaging data in FSL","volume":"45","author":"Woolrich","year":"2009","journal-title":"Neuroimage"},{"key":"10.1016\/j.neuroimage.2026.122202_bib87","doi-asserted-by":"crossref","first-page":"369","DOI":"10.1109\/TIP.2016.2628583","article-title":"Learning to detect video saliency with HEVC features","volume":"26","author":"Xu","year":"2017","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.neuroimage.2026.122202_bib88","doi-asserted-by":"crossref","first-page":"356","DOI":"10.1038\/nn.4244","article-title":"Using goal-driven deep learning models to understand sensory cortex","volume":"19","author":"Yamins","year":"2016","journal-title":"Nat. Neurosci."},{"key":"10.1016\/j.neuroimage.2026.122202_bib89","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1038\/s41583-020-00420-w","article-title":"The default mode network: where the idiosyncratic self meets the shared social world","volume":"22","author":"Yeshurun","year":"2021","journal-title":"Nat. Rev. Neurosci."},{"key":"10.1016\/j.neuroimage.2026.122202_bib90","doi-asserted-by":"crossref","DOI":"10.3389\/fnins.2025.1516070","article-title":"An fMRI study of crossmodal emotional congruency and the role of semantic content in the aesthetic appreciation of naturalistic art","volume":"19","author":"Yilmaz","year":"2025","journal-title":"Front. Neurosci."},{"key":"10.1016\/j.neuroimage.2026.122202_bib92","series-title":"Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition","article-title":"Interpre convolutional Neural networks","author":"Zhang","year":"2018"},{"key":"10.1016\/j.neuroimage.2026.122202_bib91","doi-asserted-by":"crossref","first-page":"3863","DOI":"10.1109\/TPAMI.2020.2992207","article-title":"Extraction of an explanatory graph to interpret a CNN","volume":"43","author":"Zhang","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neuroimage.2026.122202_bib93","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pbio.3003210","article-title":"Understanding human brain function in real-world environments","volume":"23","author":"Zhou","year":"2025","journal-title":"PLOS Biol."}],"container-title":["NeuroImage"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1053811926005173?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1053811926005173?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,10,17]],"date-time":"2026-10-17T10:53:44Z","timestamp":1792234424000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1053811926005173"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":93,"alternative-id":["S1053811926005173"],"URL":"https:\/\/doi.org\/10.1016\/j.neuroimage.2026.122202","relation":{},"ISSN":["1053-8119"],"issn-type":[{"value":"1053-8119","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Selective visuo-spatial attention revealed by fine-grained deep visual representations during naturalistic movie watching","name":"articletitle","label":"Article Title"},{"value":"NeuroImage","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neuroimage.2026.122202","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier Inc.","name":"copyright","label":"Copyright"}],"article-number":"122202"}}