{"id":"https://openalex.org/W7151443787","doi":"https://doi.org/10.1016/j.neucom.2026.133584","title":"GazeCLIP: Enhancing gaze estimation through text-guided multimodal learning","display_name":"GazeCLIP: Enhancing gaze estimation through text-guided multimodal learning","publication_year":2026,"publication_date":"2026-04-07","ids":{"openalex":"https://openalex.org/W7151443787","doi":"https://doi.org/10.1016/j.neucom.2026.133584"},"language":"en","primary_location":{"id":"doi:10.1016/j.neucom.2026.133584","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.neucom.2026.133584","pdf_url":null,"source":{"id":"https://openalex.org/S45693802","display_name":"Neurocomputing","issn_l":"0925-2312","issn":["0925-2312","1872-8286"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neurocomputing","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/A5133127718","display_name":"Jun Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jun Wang","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-2613-2752","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102473660","display_name":"Hao Ruan","orcid":"https://orcid.org/0009-0005-5369-9462"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Ruan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106317489","display_name":"Jun Weng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liangjian Wen","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0000-3493-6403","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133147370","display_name":"Yong Dai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yong Dai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Mingjie Wang","orcid":"https://orcid.org/0000-0002-7346-1110"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mingjie Wang","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-7346-1110","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5133127718"],"corresponding_institution_ids":[],"apc_list":{"value":2470,"currency":"USD","value_usd":2470},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.73475004,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"685","issue":null,"first_page":"133584","last_page":"133584"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9936000108718872,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9936000108718872,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.0007999999797903001,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.0005000000237487257,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/gaze","display_name":"Gaze","score":0.6686999797821045},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.5048999786376953},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.4512999951839447},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.4253000020980835},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.41359999775886536},{"id":"https://openalex.org/keywords/multimodal-interaction","display_name":"Multimodal interaction","score":0.2913999855518341}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7595999836921692},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6894999742507935},{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.6686999797821045},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5115000009536743},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.5048999786376953},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.4512999951839447},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.4253000020980835},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.41359999775886536},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3824000060558319},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3801000118255615},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.28610000014305115},{"id":"https://openalex.org/C2982736386","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Statistical learning","level":2,"score":0.2784000039100647},{"id":"https://openalex.org/C4441509","wikidata":"https://www.wikidata.org/wiki/Q6418787","display_name":"Multimodal therapy","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.25029999017715454},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.25}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.neucom.2026.133584","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.neucom.2026.133584","pdf_url":null,"source":{"id":"https://openalex.org/S45693802","display_name":"Neurocomputing","issn_l":"0925-2312","issn":["0925-2312","1872-8286"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neurocomputing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2112796928","https://openalex.org/W2158363907","https://openalex.org/W2612135493","https://openalex.org/W2765629358","https://openalex.org/W2957357336","https://openalex.org/W3013897564","https://openalex.org/W4210532635","https://openalex.org/W4391853794","https://openalex.org/W4395470955"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-04-25T08:17:42.794288","created_date":"2026-04-08T00:00:00"}
