{"id":"https://openalex.org/W7162499270","doi":"https://doi.org/10.48550/arxiv.2605.26399","title":"OmniGF: A Dual-Branch Vision-Language Framework for Unified Gaze Following","display_name":"OmniGF: A Dual-Branch Vision-Language Framework for Unified Gaze Following","publication_year":2026,"publication_date":"2026-05-26","ids":{"openalex":"https://openalex.org/W7162499270","doi":"https://doi.org/10.48550/arxiv.2605.26399"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.26399","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.26399","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.26399","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007347641","display_name":"Qiaomu Miao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Miao, Qiaomu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137114676","display_name":"Haoyu Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Haoyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137136801","display_name":"Jingyi Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Jingyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137156174","display_name":"Minh Hoai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hoai, Minh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137093825","display_name":"Dimitris Samaras","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Samaras, Dimitris","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"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":0.659600019454956,"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":0.659600019454956,"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":0.1485999971628189,"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":0.12399999797344208,"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":0.8054999709129333},{"id":"https://openalex.org/keywords/orientation","display_name":"Orientation (vector space)","score":0.4742000102996826},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.45809999108314514},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4316999912261963},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.42730000615119934},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.38830000162124634},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.37689998745918274},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.3578000068664551}],"concepts":[{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.8054999709129333},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7470999956130981},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5834000110626221},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.4742000102996826},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.45809999108314514},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4316999912261963},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.42730000615119934},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.38830000162124634},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.37689998745918274},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3725999891757965},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.3578000068664551},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3517000079154968},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34540000557899475},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.31139999628067017},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.2815999984741211},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C197914299","wikidata":"https://www.wikidata.org/wiki/Q18650","display_name":"Semantic memory","level":3,"score":0.2687000036239624},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.26829999685287476},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2526000142097473},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.26399","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.26399","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.26399","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.26399","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Understanding":[0],"human":[1],"gaze":[2,14,85,106,142,202,206,211],"behavior":[3],"is":[4,228],"essential":[5],"for":[6,52,102,181],"complex":[7,34,209],"scene":[8,50],"comprehension":[9],"and":[10,178,189,208],"human-computer":[11],"interaction.":[12],"Traditional":[13],"following":[15],"models":[16,39],"are":[17],"typically":[18],"restricted":[19],"to":[20,28,66,155],"pure":[21],"spatial":[22,82,126,148,201],"localization,":[23],"lacking":[24],"the":[25,48,61,131,147,158,165,191],"high-level":[26],"capacity":[27],"reason":[29],"about":[30],"semantic":[31,63,69,193,205],"targets":[32],"or":[33],"social":[35,210],"contexts.":[36],"Furthermore,":[37,154],"these":[38,137],"often":[40],"process":[41],"individuals":[42,183,188],"sequentially,":[43],"requiring":[44],"redundant":[45],"computations":[46],"over":[47],"same":[49],"image":[51],"multi-person":[53,105,161],"inference.":[54],"While":[55],"recent":[56],"Vision-Language":[57],"Models":[58],"(VLMs)":[59],"offer":[60],"exceptional":[62],"reasoning":[64,121],"needed":[65],"address":[67],"gaze-related":[68],"tasks,":[70],"their":[71],"reliance":[72],"on":[73],"discrete":[74,120],"text":[75],"generation":[76],"inherently":[77],"limits":[78],"precision":[79],"in":[80,160],"continuous":[81,125],"tasks":[83],"like":[84],"localization.":[86],"To":[87],"bridge":[88],"this":[89],"gap,":[90],"we":[91,163],"propose":[92],"OmniGF,":[93],"a":[94,111,115,124],"unified":[95],"vision-language":[96],"framework":[97,218],"that":[98,216],"adapts":[99],"foundational":[100],"VLMs":[101],"highly":[103],"scalable":[104],"reasoning.":[107,212],"The":[108],"model":[109,159],"adopts":[110],"dual-branch":[112],"decoding":[113],"strategy:":[114],"structured":[116],"language":[117],"branch":[118,127],"generates":[119],"states,":[122],"while":[123],"directly":[128],"taps":[129],"into":[130],"VLM's":[132],"dense":[133],"hidden":[134],"states.":[135],"Supervising":[136],"extracted":[138],"representations":[139],"with":[140,167],"high-resolution":[141],"target":[143,203],"heatmaps":[144],"effectively":[145],"overcomes":[146],"bottleneck":[149],"of":[150,195],"text-only":[151],"coordinate":[152],"generation.":[153],"explicitly":[156],"ground":[157],"scenes,":[162],"augment":[164],"input":[166],"head":[168,173],"embeddings":[169],"encoded":[170],"from":[171],"cropped":[172],"images,":[174],"providing":[175],"fine-grained":[176],"appearance":[177],"orientation":[179],"cues":[180],"all":[182,187],"simultaneously.":[184],"By":[185],"modeling":[186],"leveraging":[190],"strong":[192],"capability":[194],"VLMs,":[196],"OmniGF":[197],"seamlessly":[198],"integrates":[199],"precise":[200],"estimation,":[204],"prediction,":[207],"Extensive":[213],"experiments":[214],"demonstrate":[215],"our":[217],"establishes":[219],"new":[220],"state-of-the-art":[221],"performance":[222],"across":[223],"multiple":[224],"standard":[225],"benchmarks.":[226],"Code":[227],"available":[229],"at":[230],"https://github.com/cvlab-stonybrook/omnigf.":[231]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-28T00:00:00"}