{"id":"https://openalex.org/W4394593006","doi":"https://doi.org/10.1109/wacv57701.2024.00122","title":"Multi-Modal Gaze Following in Conversational Scenarios","display_name":"Multi-Modal Gaze Following in Conversational Scenarios","publication_year":2024,"publication_date":"2024-01-03","ids":{"openalex":"https://openalex.org/W4394593006","doi":"https://doi.org/10.1109/wacv57701.2024.00122"},"language":"en","primary_location":{"id":"doi:10.1109/wacv57701.2024.00122","doi":"https://doi.org/10.1109/wacv57701.2024.00122","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv57701.2024.00122","pdf_url":null,"source":{"id":"https://openalex.org/S4393918690","display_name":"IEEE Winter Conference on Applications of Computer Vision","issn_l":"2472-6737","issn":["2472-6737"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2311.05669","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081759736","display_name":"Yuqi Hou","orcid":"https://orcid.org/0009-0000-4473-0898","observed_orcids":["https://orcid.org/0009-0000-4473-0898"]},"institutions":[{"id":"https://openalex.org/I79619799","display_name":"University of Birmingham","ror":"https://ror.org/03angcq70","country_code":"GB","type":"education","lineage":["https://openalex.org/I79619799"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yuqi Hou","raw_affiliation_strings":["University of Birmingham, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Birmingham, United Kingdom","institution_ids":["https://openalex.org/I79619799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034357624","display_name":"Zhongqun Zhang","orcid":"https://orcid.org/0000-0003-0884-8711","observed_orcids":["https://orcid.org/0000-0003-0884-8711"]},"institutions":[{"id":"https://openalex.org/I79619799","display_name":"University of Birmingham","ror":"https://ror.org/03angcq70","country_code":"GB","type":"education","lineage":["https://openalex.org/I79619799"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhongqun Zhang","raw_affiliation_strings":["University of Birmingham, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Birmingham, United Kingdom","institution_ids":["https://openalex.org/I79619799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005688747","display_name":"N\u00f3ra Hor\u00e1nyi","orcid":"https://orcid.org/0000-0002-7135-0222","observed_orcids":["https://orcid.org/0000-0002-7135-0222"]},"institutions":[{"id":"https://openalex.org/I79619799","display_name":"University of Birmingham","ror":"https://ror.org/03angcq70","country_code":"GB","type":"education","lineage":["https://openalex.org/I79619799"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nora Horanyi","raw_affiliation_strings":["University of Birmingham, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Birmingham, United Kingdom","institution_ids":["https://openalex.org/I79619799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066921632","display_name":"Jaewon Moon","orcid":"https://orcid.org/0000-0001-7451-6411","observed_orcids":["https://orcid.org/0000-0001-7451-6411"]},"institutions":[{"id":"https://openalex.org/I4210131650","display_name":"Korea Electronics Technology Institute","ror":"https://ror.org/039k6f508","country_code":"KR","type":"facility","lineage":["https://openalex.org/I2801339556","https://openalex.org/I4210089395","https://openalex.org/I4210131650"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaewon Moon","raw_affiliation_strings":["KETI, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KETI, Korea","institution_ids":["https://openalex.org/I4210131650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004850046","display_name":"Yihua Cheng","orcid":"https://orcid.org/0009-0006-3924-6886","observed_orcids":["https://orcid.org/0009-0006-3924-6886"]},"institutions":[{"id":"https://openalex.org/I79619799","display_name":"University of Birmingham","ror":"https://ror.org/03angcq70","country_code":"GB","type":"education","lineage":["https://openalex.org/I79619799"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yihua Cheng","raw_affiliation_strings":["University of Birmingham, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Birmingham, United Kingdom","institution_ids":["https://openalex.org/I79619799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004895698","display_name":"Hyung Jin Chang","orcid":"https://orcid.org/0000-0001-7495-9677","observed_orcids":["https://orcid.org/0000-0001-7495-9677"]},"institutions":[{"id":"https://openalex.org/I79619799","display_name":"University of Birmingham","ror":"https://ror.org/03angcq70","country_code":"GB","type":"education","lineage":["https://openalex.org/I79619799"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hyung Jin Chang","raw_affiliation_strings":["University of Birmingham, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Birmingham, United Kingdom","institution_ids":["https://openalex.org/I79619799"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4371,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.90322996,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1175","last_page":"1184"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.6176999807357788,"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":0.6176999807357788,"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/T10860","display_name":"Speech and Audio Processing","score":0.12489999830722809,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11448","display_name":"Face recognition and analysis","score":0.05429999902844429,"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-following","display_name":"gaze following","score":0.9850000143051147},{"id":"https://openalex.org/keywords/audio-cues","display_name":"audio cues","score":0.7279999852180481},{"id":"https://openalex.org/keywords/audiovisual-integration","display_name":"audiovisual integration","score":0.48399999737739563}],"concepts":[{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.7922152280807495},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7336701154708862},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7062181234359741},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.49974846839904785},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3357475996017456},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/wacv57701.2024.00122","doi":"https://doi.org/10.1109/wacv57701.2024.00122","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv57701.2024.00122","pdf_url":null,"source":{"id":"https://openalex.org/S4393918690","display_name":"IEEE Winter Conference on Applications of Computer Vision","issn_l":"2472-6737","issn":["2472-6737"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2311.05669","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.05669","pdf_url":"https://arxiv.org/pdf/2311.05669","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/4bf894b3-8f49-49d0-839f-7b2c44b7ce89","doi":null,"is_oa":true,"landing_page_url":"https://research.birmingham.ac.uk/en/publications/4bf894b3-8f49-49d0-839f-7b2c44b7ce89","pdf_url":"https://pure-oai.bham.ac.uk/ws/files/322209330/2311.05669v1.pdf","source":{"id":"https://openalex.org/S4306402634","display_name":"University of Birmingham Research Portal (University of Birmingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I79619799","host_organization_name":"University of Birmingham","host_organization_lineage":["https://openalex.org/I79619799"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Hou, Y, Zhang, Z, Horanyi, N, Moon, J, Cheng, Y & Chang, H J 2023 'Multi-Modal Gaze Following in Conversational Scenarios' arXiv. https://doi.org/10.48550/arXiv.2311.05669","raw_type":"info:eu-repo/semantics/preprint"},{"id":"pmh:oai:pure.atira.dk:openaire/c48ee5e1-995a-4bb7-b0d4-9d7b468b307d","doi":null,"is_oa":true,"landing_page_url":"https://research.birmingham.ac.uk/en/publications/c48ee5e1-995a-4bb7-b0d4-9d7b468b307d","pdf_url":null,"source":{"id":"https://openalex.org/S4306402634","display_name":"University of Birmingham Research Portal (University of Birmingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I79619799","host_organization_name":"University of Birmingham","host_organization_lineage":["https://openalex.org/I79619799"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.2311.05669","doi":"https://doi.org/10.48550/arxiv.2311.05669","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2311.05669","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2311.05669","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.05669","pdf_url":"https://arxiv.org/pdf/2311.05669","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1526478229","display_name":null,"funder_award_id":"2021-0-00034","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G4700831490","display_name":null,"funder_award_id":"2022-","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"}],"funders":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4394593006.pdf","grobid_xml":"https://content.openalex.org/works/W4394593006.grobid-xml"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W1971029019","https://openalex.org/W1975141679","https://openalex.org/W1988712925","https://openalex.org/W1996721809","https://openalex.org/W2056771075","https://openalex.org/W2067373059","https://openalex.org/W2099329509","https://openalex.org/W2148154194","https://openalex.org/W2184540135","https://openalex.org/W2194775991","https://openalex.org/W2549139847","https://openalex.org/W2567215512","https://openalex.org/W2604379605","https://openalex.org/W2605289374","https://openalex.org/W2776312359","https://openalex.org/W2782140824","https://openalex.org/W2798558457","https://openalex.org/W2798685833","https://openalex.org/W2804567257","https://openalex.org/W2897890508","https://openalex.org/W2963150697","https://openalex.org/W2963307811","https://openalex.org/W2981785948","https://openalex.org/W2985588979","https://openalex.org/W2986953233","https://openalex.org/W2990616379","https://openalex.org/W2998355285","https://openalex.org/W2999173367","https://openalex.org/W3011727199","https://openalex.org/W3033504107","https://openalex.org/W3035735638","https://openalex.org/W3081857844","https://openalex.org/W3092462694","https://openalex.org/W3126337491","https://openalex.org/W3135367836","https://openalex.org/W3136078915","https://openalex.org/W3150780326","https://openalex.org/W3163269234","https://openalex.org/W3174359952","https://openalex.org/W3202228467","https://openalex.org/W4220793198","https://openalex.org/W4312461822","https://openalex.org/W4312510569","https://openalex.org/W4312996499","https://openalex.org/W4377014017","https://openalex.org/W4385804754","https://openalex.org/W4390872741","https://openalex.org/W4395470955","https://openalex.org/W6784333009"],"related_works":["https://openalex.org/W4408611587","https://openalex.org/W4409346461","https://openalex.org/W4308238077","https://openalex.org/W4387089887","https://openalex.org/W3008756694","https://openalex.org/W7110586803","https://openalex.org/W4415065150","https://openalex.org/W3097805300","https://openalex.org/W7155045972","https://openalex.org/W2019989248"],"abstract_inverted_index":{"Gaze":[0],"following":[1,46,56,67,137,162,189,200],"estimates":[2,116],"gaze":[3,22,45,55,66,110,117,136,161,188,199],"targets":[4],"of":[5,184],"in-scene":[6],"person":[7],"by":[8],"understanding":[9],"human":[10,36],"behavior":[11],"and":[12,87,89,92,107,123,166],"scene":[13,19,105,121],"information.":[14],"Existing":[15,135],"methods":[16,173],"usually":[17],"analyze":[18],"images":[20,106,122,142,165],"for":[21,34],"following.":[23],"However,":[24],"compared":[25],"with":[26,130],"visual":[27,141],"images,":[28],"audio":[29,48,86,185],"also":[30,180],"provides":[31],"crucial":[32],"cues":[33,186],"determining":[35],"behavior.":[37],"This":[38],"suggests":[39],"that":[40],"we":[41,53,124,150],"can":[42],"further":[43],"improve":[44],"considering":[47],"cues.":[49],"In":[50],"this":[51],"paper,":[52],"explore":[54],"tasks":[57],"in":[58,94,174,187,197],"conversational":[59,153],"scenarios.":[60],"We":[61,80,97],"propose":[62,108],"a":[63,95,109,152],"novel":[64],"multimodal":[65],"framework":[68],"based":[69],"on":[70,77,140],"our":[71,148],"observation":[72],"\"audiences":[73],"tend":[74],"to":[75,103,127],"focus":[76,139],"the":[78,83,100,159,182],"speaker\".":[79],"first":[81,160],"leverage":[82],"correlation":[84],"between":[85],"lips,":[88],"classify":[90],"speakers":[91],"listeners":[93],"scene.":[96],"then":[98],"use":[99,125],"identity":[101],"information":[102],"enhance":[104],"candidate":[111],"estimation":[112],"network.":[113],"The":[114,177],"network":[115],"candidates":[118,131],"from":[119],"enhanced":[120],"MLP":[126],"match":[128],"subjects":[129],"as":[132],"classification":[133],"tasks.":[134,190],"datasets":[138],"while":[143],"ignore":[144],"audios.":[145],"To":[146],"evaluate":[147],"method,":[149],"collect":[151],"dataset,":[154],"VideoGazeSpeech":[155],"(VGS),":[156],"which":[157],"is":[158],"dataset":[163],"including":[164],"audio.":[167],"Our":[168,191],"method":[169],"significantly":[170],"outperforms":[171],"existing":[172],"VGS":[175],"datasets.":[176],"visualization":[178],"result":[179],"prove":[181],"advantage":[183],"work":[192],"will":[193],"inspire":[194],"more":[195],"researches":[196],"multi-modal":[198],"estimation.":[201]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2024-04-10T00:00:00"}