{"id":"https://openalex.org/W4415540365","doi":"https://doi.org/10.1145/3746027.3754724","title":"Multi-Task Gaze Communication Understanding","display_name":"Multi-Task Gaze Communication Understanding","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540365","doi":"https://doi.org/10.1145/3746027.3754724"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754724","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3754724","pdf_url":null,"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 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3754724","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102762721","display_name":"Cheng Peng","orcid":"https://orcid.org/0000-0002-1778-1005"},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]},{"id":"https://openalex.org/I4210119896","display_name":"King's College School","ror":"https://ror.org/02bbqcn27","country_code":"GB","type":"education","lineage":["https://openalex.org/I4210119896"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Cheng Peng","raw_affiliation_strings":["Department of Engineering, King's College London, London, England, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-1778-1005","affiliations":[{"raw_affiliation_string":"Department of Engineering, King's College London, London, England, United Kingdom","institution_ids":["https://openalex.org/I183935753","https://openalex.org/I4210119896"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059459055","display_name":"Oya \u00c7eliktutan","orcid":"https://orcid.org/0000-0002-7213-6359"},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]},{"id":"https://openalex.org/I4210119896","display_name":"King's College School","ror":"https://ror.org/02bbqcn27","country_code":"GB","type":"education","lineage":["https://openalex.org/I4210119896"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Oya Celiktutan","raw_affiliation_strings":["Department of Engineering, King's College London, London, England, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-7213-6359","affiliations":[{"raw_affiliation_string":"Department of Engineering, King's College London, London, England, United Kingdom","institution_ids":["https://openalex.org/I183935753","https://openalex.org/I4210119896"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":"5471","last_page":"5479"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9998999834060669,"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":0.9998999834060669,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9980999827384949,"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/T13382","display_name":"Robotics and Automated Systems","score":0.9957000017166138,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/gaze","display_name":"Gaze","score":0.9490000009536743},{"id":"https://openalex.org/keywords/human-communication","display_name":"Human communication","score":0.46149998903274536},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4575999975204468},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.3456000089645386},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3086000084877014}],"concepts":[{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.9490000009536743},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6001999974250793},{"id":"https://openalex.org/C30539005","wikidata":"https://www.wikidata.org/wiki/Q1066689","display_name":"Human communication","level":2,"score":0.46149998903274536},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4575999975204468},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.41110000014305115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3955000042915344},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.3456000089645386},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3086000084877014},{"id":"https://openalex.org/C137878579","wikidata":"https://www.wikidata.org/wiki/Q9636076","display_name":"Joint attention","level":3,"score":0.28110000491142273},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.27799999713897705},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.2540999948978424}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754724","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3754724","pdf_url":null,"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 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3746027.3754724","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3754724","pdf_url":null,"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 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7612302558","display_name":null,"funder_award_id":"202208060296","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"}],"funders":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2027879843","https://openalex.org/W2617211984","https://openalex.org/W2776312359","https://openalex.org/W2798558457","https://openalex.org/W2883284130","https://openalex.org/W2963351448","https://openalex.org/W3035735638","https://openalex.org/W3174359952","https://openalex.org/W4312303088","https://openalex.org/W4312510569","https://openalex.org/W4312567381","https://openalex.org/W4377996674","https://openalex.org/W4386065554","https://openalex.org/W4386071798","https://openalex.org/W4386072441","https://openalex.org/W4386075882","https://openalex.org/W4390874324"],"related_works":[],"abstract_inverted_index":{"Human":[0],"gaze":[1,25,42,67,71,92,108,112,121],"communication":[2,26,93,109,122],"is":[3],"complex,":[4],"comprising":[5],"atomic-level":[6,64,89],"(e.g.":[7,13],"mutual,":[8],"share,":[9],"etc.)":[10,16],"and":[11,65,82,90,110,131,142],"event-level":[12,66,91],"follow,":[14],"aversion,":[15],"behaviours.":[17],"Various":[18],"methods":[19],"have":[20],"been":[21],"developed":[22],"to":[23,61,80],"analyse":[24],"in":[27,43,98],"images,":[28],"but":[29],"they":[30],"typically":[31],"fall":[32],"short":[33],"of":[34,39,107],"fully":[35,119],"understanding":[36],"the":[37,40,77,84,88],"complexities":[38],"human":[41],"videos.":[44],"In":[45],"this":[46,99],"paper,":[47],"we":[48,75,116],"present":[49,117],"a":[50,118],"multi-task,":[51],"multimodal":[52],"model":[53,79,128],"based":[54],"on":[55,129],"Contrastive":[56],"Language-Image":[57],"Pre-training":[58],"(CLIP),":[59],"designed":[60],"jointly":[62],"predict":[63],"communication,":[68],"along":[69],"with":[70],"target":[72,113],"estimation.":[73],"Specifically,":[74],"leverage":[76],"Vision-Language":[78],"capture":[81],"utilise":[83],"semantic":[85],"information":[86],"between":[87],"categories.":[94],"Additionally,":[95],"most":[96],"datasets":[97],"field":[100],"lack":[101],"comprehensive":[102],"annotations":[103],"for":[104],"both":[105],"levels":[106],"detailed":[111],"information.":[114],"Therefore,":[115],"annotated":[120],"dataset,":[123],"GP-Static++.":[124],"We":[125],"validate":[126],"our":[127],"GP-Static++":[130],"several":[132],"publicly":[133],"available":[134,145],"datasets,":[135],"demonstrating":[136],"its":[137],"state-of-the-art":[138],"performance.":[139],"The":[140],"dataset":[141],"code":[143],"are":[144],"at":[146],"https://pengc98.github.io/Multi-Task-Gaze-Communication-Understanding/.":[147]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}