{"id":"https://openalex.org/W4417100024","doi":"https://doi.org/10.1007/s44267-025-00101-1","title":"GazeLLM: a plug-and-play zero-shot LLM reasoning framework for boosting gaze target detection","display_name":"GazeLLM: a plug-and-play zero-shot LLM reasoning framework for boosting gaze target detection","publication_year":2025,"publication_date":"2025-12-01","ids":{"openalex":"https://openalex.org/W4417100024","doi":"https://doi.org/10.1007/s44267-025-00101-1"},"language":"en","primary_location":{"id":"doi:10.1007/s44267-025-00101-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44267-025-00101-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44267-025-00101-1.pdf","source":{"id":"https://openalex.org/S4387289164","display_name":"Visual Intelligence","issn_l":"2731-9008","issn":["2731-9008","2097-3330"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Visual Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://link.springer.com/content/pdf/10.1007/s44267-025-00101-1.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005770370","display_name":"Yaokun Yang","orcid":"https://orcid.org/0000-0002-3340-8075"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaokun Yang","raw_affiliation_strings":["State Key Laboratory of VR Technology and Systems, Beihang University, Beijing, 100024, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of VR Technology and Systems, Beihang University, Beijing, 100024, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050527785","display_name":"Feng Lu","orcid":"https://orcid.org/0000-0001-9064-7964"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Feng Lu","raw_affiliation_strings":["State Key Laboratory of VR Technology and Systems, Beihang University, Beijing, 100024, China"],"raw_orcid":"https://orcid.org/0000-0001-9064-7964","affiliations":[{"raw_affiliation_string":"State Key Laboratory of VR Technology and Systems, Beihang University, Beijing, 100024, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5050527785"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":{"value":0,"currency":"USD","value_usd":0},"apc_paid":null,"fwci":0.8293,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.78802628,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"3","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.5424000024795532,"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":0.5424000024795532,"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":0.22540000081062317,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.11710000038146973,"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/gaze","display_name":"Gaze","score":0.8914999961853027},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.8104000091552734},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.486299991607666},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.4805000126361847},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.45840001106262207},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.450300008058548},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4496000111103058},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.3971000015735626}],"concepts":[{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.8914999961853027},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8104000091552734},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7699999809265137},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7206000089645386},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.486299991607666},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.4805000126361847},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.45840001106262207},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.450300008058548},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4496000111103058},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41110000014305115},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.3971000015735626},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36309999227523804},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32659998536109924},{"id":"https://openalex.org/C2778949103","wikidata":"https://www.wikidata.org/wiki/Q600717","display_name":"Staring","level":2,"score":0.31060001254081726},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30799999833106995},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.30630001425743103},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.305400013923645},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.287200003862381},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2858000099658966},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2849999964237213},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.258899986743927}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s44267-025-00101-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44267-025-00101-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44267-025-00101-1.pdf","source":{"id":"https://openalex.org/S4387289164","display_name":"Visual Intelligence","issn_l":"2731-9008","issn":["2731-9008","2097-3330"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Visual Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:50763298315041b5a31ff8dc0d4c04dc","is_oa":true,"landing_page_url":"https://doaj.org/article/50763298315041b5a31ff8dc0d4c04dc","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Visual Intelligence, Vol 3, Iss 1, Pp 1-15 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s44267-025-00101-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44267-025-00101-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44267-025-00101-1.pdf","source":{"id":"https://openalex.org/S4387289164","display_name":"Visual Intelligence","issn_l":"2731-9008","issn":["2731-9008","2097-3330"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Visual Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417100024.pdf","grobid_xml":"https://content.openalex.org/works/W4417100024.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W2001252859","https://openalex.org/W2951124636","https://openalex.org/W3198377975","https://openalex.org/W4387010030","https://openalex.org/W4390480861","https://openalex.org/W4395470955","https://openalex.org/W4400125901","https://openalex.org/W4402967467","https://openalex.org/W4404600626","https://openalex.org/W4405248620","https://openalex.org/W4405827891","https://openalex.org/W4408537129"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"In":[1],"the":[2,34,129,168,188,202],"gaze":[3,44,78,109,135,179,208],"behavior":[4,209],"understanding":[5,207],"task,":[6],"existing":[7],"vision-based":[8,134],"models":[9,19],"demonstrate":[10],"inherent":[11],"limitations":[12],"in":[13,23,206],"high-dimensional":[14],"semantic":[15,212],"understanding,":[16],"while":[17],"vision-language":[18],"(VLMs)":[20],"encounter":[21],"challenges":[22],"precise":[24],"object":[25,57,73,80],"localization.":[26],"To":[27],"address":[28],"this":[29],"issue,":[30],"we":[31,54,68,86,115],"propose":[32],"GazeLLM,":[33],"first":[35],"zero-shot":[36],"large":[37],"language":[38],"model":[39],"(LLM)":[40],"boosted":[41],"framework":[42,192],"for":[43,170],"target":[45],"reasoning.":[46],"Our":[47,191],"key":[48],"innovations":[49],"include":[50],"three":[51],"aspects.":[52],"First,":[53],"have":[55],"structured":[56],"extraction.":[58],"Using":[59],"off-the-shelf":[60],"detectors":[61],"(e.g.,":[62,181],"MM-GroundingDINO":[63],"and":[64,77,82,196],"Depth":[65],"Anything":[66],"V2),":[67],"convert":[69],"images":[70],"into":[71],"3D":[72],"representations,":[74],"including":[75],"head":[76],"direction,":[79],"categories,":[81,166],"metric":[83],"depth.":[84],"Second,":[85],"implemented":[87],"an":[88],"autonomous":[89],"chain-of-thought":[90],"(CoT)":[91],"reasoning":[92],"system.":[93],"We":[94,120],"designed":[95],"self-generated":[96],"CoT":[97],"prompts":[98],"to":[99,107,155,176,199],"guide":[100],"pretrained":[101],"LLMs,":[102],"such":[103,160],"as":[104,161],"ChatGPT":[105],"o3-mini-high,":[106],"predict":[108],"targets":[110,163],"via":[111,137],"spatial-semantic":[112],"analysis.":[113],"Third,":[114],"proposed":[116],"a":[117,122,182],"plug-and-play":[118],"module.":[119],"employed":[121],"novel":[123],"cross-modal":[124],"fusion":[125],"mechanism":[126],"that":[127,144],"combines":[128],"LLM\u2019s":[130],"probability":[131],"dictionaries":[132],"with":[133],"heatmaps":[136],"Gaussian-weighted":[138],"multi-hot":[139],"mapping.":[140],"Extensive":[141],"experiments":[142],"show":[143],"GazeLLM":[145],"significantly":[146],"improves":[147],"state-of-the-art":[148],"models,":[149],"increasing":[150],"their":[151],"performance":[152],"from":[153],"17%":[154],"34%":[156],"on":[157,187],"challenging":[158],"cases,":[159],"long-range":[162],"or":[164],"rare":[165],"without":[167],"need":[169],"retraining.":[171],"It":[172],"also":[173],"extends":[174],"seamlessly":[175],"multi-person":[177],"social":[178],"tasks":[180],"42%":[183],"LAEO":[184],"AP":[185],"gain":[186],"AVA-LAEO":[189],"benchmark).":[190],"demonstrates":[193],"superior":[194],"generalizability":[195],"interpretability":[197],"compared":[198],"VLMs,":[200],"validating":[201],"efficacy":[203],"of":[204],"LLMs":[205],"by":[210],"mining":[211],"cues.":[213]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-12-08T00:00:00"}