{"id":"https://openalex.org/W4415047721","doi":"https://doi.org/10.1109/tai.2025.3612905","title":"Contrastive Language-Image Pretrained Models are Zero-Shot Human Scanpath Predictors","display_name":"Contrastive Language-Image Pretrained Models are Zero-Shot Human Scanpath Predictors","publication_year":2025,"publication_date":"2025-10-10","ids":{"openalex":"https://openalex.org/W4415047721","doi":"https://doi.org/10.1109/tai.2025.3612905"},"language":"en","primary_location":{"id":"doi:10.1109/tai.2025.3612905","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2025.3612905","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023645490","display_name":"Dario Zanca","orcid":"https://orcid.org/0000-0001-5886-0597"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dario Zanca","raw_affiliation_strings":["Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany","Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany"],"raw_orcid":"https://orcid.org/0000-0001-5886-0597","affiliations":[{"raw_affiliation_string":"Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]},{"raw_affiliation_string":"Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052833772","display_name":"Andrea Zugarini","orcid":"https://orcid.org/0000-0003-0344-1656"},"institutions":[{"id":"https://openalex.org/I102064193","display_name":"University of Siena","ror":"https://ror.org/01tevnk56","country_code":"IT","type":"education","lineage":["https://openalex.org/I102064193"]},{"id":"https://openalex.org/I4210134440","display_name":"Expert System (Italy)","ror":"https://ror.org/032av0b93","country_code":"IT","type":"company","lineage":["https://openalex.org/I4210134440"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Andrea Zugarini","raw_affiliation_strings":["Expert.AI, Siena, Italy","Expert.ai, Italy"],"raw_orcid":"https://orcid.org/0000-0003-0344-1656","affiliations":[{"raw_affiliation_string":"Expert.AI, Siena, Italy","institution_ids":["https://openalex.org/I102064193","https://openalex.org/I4210134440"]},{"raw_affiliation_string":"Expert.ai, Italy","institution_ids":["https://openalex.org/I4210134440"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Simon Dietz","orcid":"https://orcid.org/0009-0004-8963-6220"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Simon Dietz","raw_affiliation_strings":["Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany","Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany"],"raw_orcid":"https://orcid.org/0009-0004-8963-6220","affiliations":[{"raw_affiliation_string":"Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]},{"raw_affiliation_string":"Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066328216","display_name":"Thomas Altstidl","orcid":"https://orcid.org/0000-0002-2326-4258"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas R. Altstidl","raw_affiliation_strings":["Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany","Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany"],"raw_orcid":"https://orcid.org/0000-0002-2326-4258","affiliations":[{"raw_affiliation_string":"Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]},{"raw_affiliation_string":"Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092022911","display_name":"Mark A. Turban Ndjeuha","orcid":null},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Mark A. Turban Ndjeuha","raw_affiliation_strings":["Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany","Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany"],"raw_orcid":"https://orcid.org/0009-0006-2304-6601","affiliations":[{"raw_affiliation_string":"Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]},{"raw_affiliation_string":"Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Moumita Chakraborty","orcid":"https://orcid.org/0009-0005-9242-6248"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Moumita Chakraborty","raw_affiliation_strings":["Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany","Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany"],"raw_orcid":"https://orcid.org/0009-0005-9242-6248","affiliations":[{"raw_affiliation_string":"Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]},{"raw_affiliation_string":"Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093529104","display_name":"Naga Venkata Sai Jitin Jami","orcid":"https://orcid.org/0000-0002-3292-6225"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Naga Venkata Sai Jitin Jami","raw_affiliation_strings":["Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany","Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany"],"raw_orcid":"https://orcid.org/0000-0002-3292-6225","affiliations":[{"raw_affiliation_string":"Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]},{"raw_affiliation_string":"Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028233502","display_name":"Leo Schwinn","orcid":"https://orcid.org/0000-0003-3967-2202"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Leo Schwinn","raw_affiliation_strings":["Technische Universität München, Munich, Germany","Technische Universität München, Germany"],"raw_orcid":"https://orcid.org/0000-0003-3967-2202","affiliations":[{"raw_affiliation_string":"Technische Universität München, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Technische Universität München, Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014144494","display_name":"Bjoern M. Eskofier","orcid":"https://orcid.org/0000-0002-0417-0336"},"institutions":[{"id":"https://openalex.org/I2799978770","display_name":"X-Fab (Germany)","ror":"https://ror.org/030bh9196","country_code":"DE","type":"company","lineage":["https://openalex.org/I2799978770"]},{"id":"https://openalex.org/I3018134672","display_name":"Helmholtz Zentrum M\u00fcnchen","ror":"https://ror.org/00cfam450","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I3018134672"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bjoern M. Eskofier","raw_affiliation_strings":["Friedrich-Alexander-Universität Erlangen-Nürnberg and Helmholtz Zentrum München, Munich, Germany","Friedrich-Alexander-Universität Erlangen-Nürnberg and Helmholtz Zentrum München, Germany"],"raw_orcid":"https://orcid.org/0000-0002-0417-0336","affiliations":[{"raw_affiliation_string":"Friedrich-Alexander-Universität Erlangen-Nürnberg and Helmholtz Zentrum München, Munich, Germany","institution_ids":["https://openalex.org/I3018134672"]},{"raw_affiliation_string":"Friedrich-Alexander-Universität Erlangen-Nürnberg and Helmholtz Zentrum München, Germany","institution_ids":["https://openalex.org/I2799978770"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10701317,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"7","issue":"4","first_page":"2157","last_page":"2170"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9718000292778015,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9718000292778015,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9645000100135803,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8889999985694885},{"id":"https://openalex.org/keywords/computational-model","display_name":"Computational model","score":0.5253999829292297},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4837999939918518},{"id":"https://openalex.org/keywords/visual-attention","display_name":"Visual attention","score":0.4239000082015991},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.42289999127388},{"id":"https://openalex.org/keywords/conjunction","display_name":"Conjunction (astronomy)","score":0.4124999940395355},{"id":"https://openalex.org/keywords/human-visual-system-model","display_name":"Human visual system model","score":0.34619998931884766}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8889999985694885},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7817000150680542},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6920999884605408},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.5253999829292297},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4837999939918518},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4424999952316284},{"id":"https://openalex.org/C2986089797","wikidata":"https://www.wikidata.org/wiki/Q6501338","display_name":"Visual attention","level":3,"score":0.4239000082015991},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.42289999127388},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.4124999940395355},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4043000042438507},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.34619998931884766},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C158495155","wikidata":"https://www.wikidata.org/wiki/Q2369151","display_name":"Visual search","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.27730000019073486},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.26759999990463257}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tai.2025.3612905","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2025.3612905","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W164503247","https://openalex.org/W1497599070","https://openalex.org/W1510835000","https://openalex.org/W1934890906","https://openalex.org/W2003232287","https://openalex.org/W2012257307","https://openalex.org/W2092587010","https://openalex.org/W2119228922","https://openalex.org/W2122937454","https://openalex.org/W2126231638","https://openalex.org/W2128272608","https://openalex.org/W2164084182","https://openalex.org/W2890484038","https://openalex.org/W2895420168","https://openalex.org/W2914306086","https://openalex.org/W2949058392","https://openalex.org/W2955060956","https://openalex.org/W2962935746","https://openalex.org/W2963630207","https://openalex.org/W3023584964","https://openalex.org/W3048953431","https://openalex.org/W3049276812","https://openalex.org/W3108161363","https://openalex.org/W3154689434","https://openalex.org/W4225004727","https://openalex.org/W4312828237","https://openalex.org/W4409262176"],"related_works":[],"abstract_inverted_index":{"Understanding":[0],"human":[1,85,128,212,232],"attention":[2,61,129,200,213],"mechanisms":[3,28],"is":[4,24,179],"crucial":[5],"for":[6,44,126,228],"advancing":[7],"both":[8,131],"vision":[9],"science":[10],"and":[11,96,133,170,202,217,230],"artificial":[12],"intelligence.":[13],"While":[14],"numerous":[15],"computational":[16,162],"models":[17,54,163],"of":[18,68,196,210],"free-viewing":[19,119,132,171],"have":[20],"been":[21],"proposed,":[22],"less":[23],"known":[25],"about":[26],"the":[27,66,110,142,194,223],"underlying":[29],"task-driven":[30,134,211],"image":[31,98],"exploration.":[32],"To":[33],"address":[34],"this":[35],"gap,":[36],"we":[37,137,174],"introduce":[38],"NevaClip,":[39],"a":[40,91,105,123],"novel":[41],"zero-shot":[42],"method":[43],"predicting":[45],"visual":[46,60,70,78,149,233],"scanpaths.":[47],"NevaClip":[48,75,158,216],"leverages":[49],"contrastive":[50],"language-image":[51],"pretrained":[52],"(CLIP)":[53],"in":[55,104,164,199],"conjunction":[56],"with":[57,72,184],"human-inspired":[58],"neural":[59],"(NeVA)":[62],"algorithms.":[63],"By":[64],"aligning":[65],"representation":[67],"foveated":[69],"stimuli":[71],"associated":[73],"captions,":[74],"uses":[76],"gradient-driven":[77],"exploration":[79],"to":[80,181,188,206,222],"generate":[81],"scanpaths":[82],"that":[83,157,176],"simulate":[84],"attention.":[86,234],"We":[87],"also":[88],"present":[89],"CapMIT1003,":[90],"new":[92,226],"dataset":[93],"comprising":[94],"captions":[95,186],"click-contingent":[97],"explorations":[99],"collected":[100],"from":[101,118],"participants":[102],"engaged":[103],"captioning":[106],"task.":[107],"Based":[108],"on":[109,141],"established":[111],"MIT1003":[112],"benchmark,":[113],"which":[114,147],"includes":[115,148],"eye-tracking":[116],"data":[117],"conditions,":[120],"CapMIT1003":[121,218],"provides":[122],"valuable":[124],"resource":[125],"studying":[127,229],"across":[130,167],"contexts.":[135],"Additionally,":[136],"demonstrate":[138,175],"NevaClip\u2019s":[139,177,204],"performance":[140,178],"publicly":[143],"available":[144],"AiR-D":[145],"dataset,":[146],"question":[150],"answering":[151],"(VQA)":[152],"tasks.":[153,172],"Experimental":[154],"results":[155],"show":[156],"outperforms":[159],"existing":[160],"unsupervised":[161],"scanpath":[165,190],"plausibility":[166],"captioning,":[168],"VQA,":[169],"Furthermore,":[173],"sensitive":[180],"caption":[182,197],"accuracy,":[183],"misleading":[185],"leading":[187],"inaccurate":[189],"behaviors.":[191],"This":[192],"underscores":[193],"importance":[195],"guidance":[198],"prediction":[201],"highlights":[203],"potential":[205],"advance":[207],"our":[208],"understanding":[209],"mechanisms.":[214],"Together,":[215],"offer":[219],"significant":[220],"contributions":[221],"field,":[224],"providing":[225],"tools":[227],"simulating":[231]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-11T00:00:00"}