{"id":"https://openalex.org/W4414983863","doi":"https://doi.org/10.1145/3745900.3746075","title":"GazeLLM: Multimodal LLMs incorporating Human Visual Attention","display_name":"GazeLLM: Multimodal LLMs incorporating Human Visual Attention","publication_year":2025,"publication_date":"2025-03-16","ids":{"openalex":"https://openalex.org/W4414983863","doi":"https://doi.org/10.1145/3745900.3746075"},"language":"en","primary_location":{"id":"doi:10.1145/3745900.3746075","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3745900.3746075","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3745900.3746075","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Augmented Humans International Conference 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3745900.3746075","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082649952","display_name":"Jun Rekimoto","orcid":"https://orcid.org/0000-0002-3629-2514"},"institutions":[{"id":"https://openalex.org/I4210122684","display_name":"Sony Computer Science Laboratories","ror":"https://ror.org/02nc46417","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210122684"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Jun Rekimoto","raw_affiliation_strings":["The University of Tokyo, Tokyo, Japan and Sony Computer Science Laboratories, Inc., Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-3629-2514","affiliations":[{"raw_affiliation_string":"The University of Tokyo, Tokyo, Japan and Sony Computer Science Laboratories, Inc., Tokyo, Japan","institution_ids":["https://openalex.org/I4210122684","https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5082649952"],"corresponding_institution_ids":["https://openalex.org/I4210122684","https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"302","last_page":"311"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9994999766349792,"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":0.9994999766349792,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9973999857902527,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.988099992275238,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/visual-attention","display_name":"Visual attention","score":0.5139999985694885},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.32589998841285706},{"id":"https://openalex.org/keywords/visual-search","display_name":"Visual search","score":0.32179999351501465},{"id":"https://openalex.org/keywords/visual-perception","display_name":"Visual perception","score":0.2946999967098236},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.2890999913215637}],"concepts":[{"id":"https://openalex.org/C2986089797","wikidata":"https://www.wikidata.org/wiki/Q6501338","display_name":"Visual attention","level":3,"score":0.5139999985694885},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.47540000081062317},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.45739999413490295},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.34369999170303345},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.32589998841285706},{"id":"https://openalex.org/C158495155","wikidata":"https://www.wikidata.org/wiki/Q2369151","display_name":"Visual search","level":2,"score":0.32179999351501465},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.2946999967098236},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2890999913215637},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.267300009727478}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3745900.3746075","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3745900.3746075","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3745900.3746075","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Augmented Humans International Conference 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3745900.3746075","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3745900.3746075","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3745900.3746075","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Augmented Humans International Conference 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1063213209","display_name":null,"funder_award_id":"JPMJMS2012","funder_id":"https://openalex.org/F4320338247","funder_display_name":"Moonshot Research and Development Program"}],"funders":[{"id":"https://openalex.org/F4320338247","display_name":"Moonshot Research and Development Program","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414983863.pdf","grobid_xml":"https://content.openalex.org/works/W4414983863.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W2070719266","https://openalex.org/W2101105183","https://openalex.org/W2510850444","https://openalex.org/W2610201393","https://openalex.org/W2963341956","https://openalex.org/W2970641574","https://openalex.org/W3202258049","https://openalex.org/W3202670445","https://openalex.org/W4378675697","https://openalex.org/W4392878111","https://openalex.org/W4396938940","https://openalex.org/W4402727748"],"related_works":[],"abstract_inverted_index":{"Video":[0],"encoder":[1],"A":[2],"user":[3],"With":[4],"1":[5,15],"st":[6,16],"person":[7,17],"vision":[8],"&":[9],"eye":[10],"tracker":[11],"Gaze":[12],"focused":[13],"video":[14],"viewFigure":[18],"1:":[19],"GazeLLM":[20],"achieves":[21],"task":[22],"descriptions":[23],"of":[24,36],"equal":[25],"or":[26],"superior":[27],"quality":[28],"to":[29],"full-sized":[30],"videos,":[31],"despite":[32],"using":[33],"only":[34],"one-tenth":[35],"the":[37,40],"pixels":[38],"around":[39],"user's":[41],"gaze":[42],"point.":[43]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}