{"id":"https://openalex.org/W4388650621","doi":"https://doi.org/10.48550/arxiv.2311.05669","title":"Multi-Modal Gaze Following in Conversational Scenarios","display_name":"Multi-Modal Gaze Following in Conversational Scenarios","publication_year":2023,"publication_date":"2023-11-09","ids":{"openalex":"https://openalex.org/W4388650621","doi":"https://doi.org/10.48550/arxiv.2311.05669"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2311.05669","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":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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","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/0009-0002-3086-8698"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hou, Yuqi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034357624","display_name":"Zhongqun Zhang","orcid":"https://orcid.org/0000-0003-0884-8711"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Zhongqun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005688747","display_name":"N\u00f3ra Hor\u00e1nyi","orcid":"https://orcid.org/0000-0002-7135-0222"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Horanyi, Nora","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066921632","display_name":"Jaewon Moon","orcid":"https://orcid.org/0000-0001-7451-6411"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Moon, Jaewon","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102735526","display_name":"Yihua Cheng","orcid":"https://orcid.org/0000-0003-1353-9817"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, Yihua","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5004895698","display_name":"Hyung Jin Chang","orcid":"https://orcid.org/0000-0001-7495-9677"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chang, Hyung Jin","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5081759736"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":0.995199978351593,"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":0.995199978351593,"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":0.9943000078201294,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9693999886512756,"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":0.9322080612182617},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7858494520187378},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6379531025886536},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6080673336982727},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5952118039131165},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5797587633132935},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5440577268600464},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.47069573402404785}],"concepts":[{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.9322080612182617},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7858494520187378},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6379531025886536},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6080673336982727},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5952118039131165},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5797587633132935},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5440577268600464},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.47069573402404785},{"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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2311.05669","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":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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/c48ee5e1-995a-4bb7-b0d4-9d7b468b307d","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,"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":"Hou, Y, Zhang, Z, Horanyi, N, Moon, J, Cheng, Y & Chang, H J 2024, Multi-Modal Gaze Following in Conversational Scenarios. in 2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). IEEE Workshop on Applications of Computer Vision (WACV), IEEE, pp. 1175-1184, 2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, Hawaii, United States, 3/01/24. https://doi.org/10.48550/arXiv.2311.05669, https://doi.org/10.1109/WACV57701.2024.00122","raw_type":"contributionToPeriodical"},{"id":"doi: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":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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2311.05669","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":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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"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/W4388650621.pdf","grobid_xml":"https://content.openalex.org/works/W4388650621.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1880689012","https://openalex.org/W3014378845","https://openalex.org/W4240909707","https://openalex.org/W2059546927","https://openalex.org/W3207760378","https://openalex.org/W4386072035","https://openalex.org/W2562758970","https://openalex.org/W1986970529","https://openalex.org/W1563178652","https://openalex.org/W2947492009"],"abstract_inverted_index":{"Gaze":[0],"following":[1,45,55,66,136,160,187,198],"estimates":[2,115],"gaze":[3,22,44,54,65,109,116,135,159,186,197],"targets":[4],"of":[5,182],"in-scene":[6],"person":[7],"by":[8],"understanding":[9],"human":[10,36],"behavior":[11],"and":[12,86,88,91,106,122,164],"scene":[13,19,104,120],"information.":[14],"Existing":[15,134],"methods":[16,171],"usually":[17],"analyze":[18],"images":[20,105,121,141,163],"for":[21,34],"following.":[23],"However,":[24],"compared":[25],"with":[26,129],"visual":[27,140],"images,":[28],"audio":[29,47,85,183],"also":[30,178],"provides":[31],"crucial":[32],"cues":[33,184],"determining":[35],"behavior.This":[37],"suggests":[38],"that":[39],"we":[40,52,123,148],"can":[41],"further":[42],"improve":[43],"considering":[46],"cues.":[48],"In":[49],"this":[50],"paper,":[51],"explore":[53],"tasks":[56],"in":[57,93,172,185,195],"conversational":[58,151],"scenarios.":[59],"We":[60,79,96],"propose":[61,107],"a":[62,94,108,150],"novel":[63],"multi-modal":[64,196],"framework":[67],"based":[68],"on":[69,76,139],"our":[70,146],"observation":[71],"``audiences":[72],"tend":[73],"to":[74,102,126],"focus":[75,138],"the":[77,82,99,157,180],"speaker''.":[78],"first":[80,158],"leverage":[81],"correlation":[83],"between":[84],"lips,":[87],"classify":[89],"speakers":[90],"listeners":[92],"scene.":[95],"then":[97],"use":[98,124],"identity":[100],"information":[101],"enhance":[103],"candidate":[110],"estimation":[111],"network.":[112],"The":[113,175],"network":[114],"candidates":[117,130],"from":[118],"enhanced":[119],"MLP":[125],"match":[127],"subjects":[128],"as":[131],"classification":[132],"tasks.":[133,188],"datasets":[137],"while":[142],"ignore":[143],"audios.To":[144],"evaluate":[145],"method,":[147],"collect":[149],"dataset,":[152],"VideoGazeSpeech":[153],"(VGS),":[154],"which":[155],"is":[156],"dataset":[161],"including":[162],"audio.":[165],"Our":[166,189],"method":[167],"significantly":[168],"outperforms":[169],"existing":[170],"VGS":[173],"datasets.":[174],"visualization":[176],"result":[177],"prove":[179],"advantage":[181],"work":[190],"will":[191],"inspire":[192],"more":[193],"researches":[194],"estimation.":[199]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}