{"id":"https://openalex.org/W3206300869","doi":"https://doi.org/10.1145/3462244.3481002","title":"Gaze-based Multimodal Meaning Recovery for Noisy\u00a0/\u00a0Complex Environments","display_name":"Gaze-based Multimodal Meaning Recovery for Noisy\u00a0/\u00a0Complex Environments","publication_year":2021,"publication_date":"2021-10-15","ids":{"openalex":"https://openalex.org/W3206300869","doi":"https://doi.org/10.1145/3462244.3481002","mag":"3206300869"},"language":"en","primary_location":{"id":"doi:10.1145/3462244.3481002","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3462244.3481002","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Multimodal Interaction","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014151067","display_name":"\u00d6zge Ala\u00e7am","orcid":null},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"\u00d6zge Ala\u00e7am","raw_affiliation_strings":["Language Technology, Universit\u00e4t Hamburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technology, Universit\u00e4t Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057318422","display_name":"Ganeshan Malhotra","orcid":null},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]},{"id":"https://openalex.org/I74796645","display_name":"Birla Institute of Technology and Science, Pilani","ror":"https://ror.org/001p3jz28","country_code":"IN","type":"education","lineage":["https://openalex.org/I74796645"]}],"countries":["DE","IN"],"is_corresponding":false,"raw_author_name":"Ganeshan Malhotra","raw_affiliation_strings":["BITS Pilani Goa, India and Language Technology, Universit\u00e4t Hamburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BITS Pilani Goa, India and Language Technology, Universit\u00e4t Hamburg, Germany","institution_ids":["https://openalex.org/I74796645","https://openalex.org/I159176309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018661511","display_name":"Eugen Ruppert","orcid":null},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Eugen Ruppert","raw_affiliation_strings":["Base.camp, Universit\u00e4t Hamburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Base.camp, Universit\u00e4t Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021287757","display_name":"Chris Biemann","orcid":"https://orcid.org/0000-0002-8449-9624"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Chris Biemann","raw_affiliation_strings":["Language Technology, Universit\u00e4t Hamburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technology, Universit\u00e4t Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"673","last_page":"681"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9962000250816345,"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/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9850000143051147,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7522883415222168},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6438453197479248},{"id":"https://openalex.org/keywords/gaze","display_name":"Gaze","score":0.6386371850967407},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.5923852324485779},{"id":"https://openalex.org/keywords/meaning","display_name":"Meaning (existential)","score":0.5866990685462952},{"id":"https://openalex.org/keywords/clutter","display_name":"Clutter","score":0.5337100625038147},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.520745038986206},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.49384433031082153},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4771706163883209},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.4523228406906128},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.44244664907455444},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.42912259697914124},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.39749112725257874},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3874775767326355},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.37808680534362793},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.17455366253852844},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.17401829361915588},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10134285688400269},{"id":"https://openalex.org/keywords/radar","display_name":"Radar","score":0.07758104801177979}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7522883415222168},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6438453197479248},{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.6386371850967407},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.5923852324485779},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.5866990685462952},{"id":"https://openalex.org/C132094186","wikidata":"https://www.wikidata.org/wiki/Q641585","display_name":"Clutter","level":3,"score":0.5337100625038147},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.520745038986206},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.49384433031082153},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4771706163883209},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4523228406906128},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.44244664907455444},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.42912259697914124},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.39749112725257874},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3874775767326355},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37808680534362793},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.17455366253852844},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.17401829361915588},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10134285688400269},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.07758104801177979},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3462244.3481002","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3462244.3481002","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Multimodal Interaction","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8299999833106995,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G2683928881","display_name":null,"funder_award_id":"SFB 169","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W82346763","https://openalex.org/W126238149","https://openalex.org/W1515760596","https://openalex.org/W1522146982","https://openalex.org/W2053315688","https://openalex.org/W2061346392","https://openalex.org/W2064675550","https://openalex.org/W2086458350","https://openalex.org/W2097041579","https://openalex.org/W2132684680","https://openalex.org/W2137974432","https://openalex.org/W2157191375","https://openalex.org/W2251943134","https://openalex.org/W2599276130","https://openalex.org/W2738132155","https://openalex.org/W2739890004","https://openalex.org/W2885048649","https://openalex.org/W2888656057","https://openalex.org/W2896457183","https://openalex.org/W2914304175","https://openalex.org/W2921304183","https://openalex.org/W2940674770","https://openalex.org/W2950133940","https://openalex.org/W2950577311","https://openalex.org/W2966765144","https://openalex.org/W2979352286","https://openalex.org/W2979826702","https://openalex.org/W2985540049","https://openalex.org/W2999734205","https://openalex.org/W3029726344","https://openalex.org/W3035390927","https://openalex.org/W4237795037"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W203959209","https://openalex.org/W2110287964","https://openalex.org/W2167701463","https://openalex.org/W4307407935"],"abstract_inverted_index":{"Reference":[0],"resolution":[1,56],"is":[2,26],"an":[3],"important":[4],"problem":[5],"that":[6,45,119],"has":[7],"enormous":[8],"practical":[9],"implications":[10],"in":[11,16,21,30,38,57,79,86,112,128],"daily":[12],"life,":[13],"for":[14,124],"example":[15],"recovering":[17],"the":[18,24,31,39,50,54,65,68,84,99,106,113,125,129],"intended":[19],"meaning":[20,85],"communication":[22,78,133],"when":[23,134],"environment":[25],"noisy":[27,87],"(acoustic":[28],"noise":[29,111],"spoken":[32],"channel,":[33],"or":[34],"clutter":[35],"/":[36],"occlusion":[37],"visual":[40,137],"world).":[41],"Recent":[42],"literature":[43],"indicates":[44],"cross-modal":[46],"processing":[47],"of":[48,67,76,105],"all":[49],"contributive":[51],"modalities":[52],"improves":[53],"reference":[55],"such":[58],"settings.":[59,88],"In":[60],"this":[61],"paper,":[62],"we":[63],"investigate":[64],"contribution":[66],"eye-tracking":[69],"methodology,":[70],"a":[71],"substantial":[72],"but":[73],"underrepresented":[74],"component":[75],"face-to-face":[77],"NLP":[80],"systems,":[81],"to":[82],"recover":[83],"We":[89],"integrate":[90],"gaze":[91],"features":[92],"into":[93],"state-of-the-art":[94],"language":[95,135],"models":[96],"and":[97,131,136],"test":[98],"model":[100],"on":[101],"data":[102],"where":[103],"parts":[104],"sentences":[107],"are":[108],"masked,":[109],"mimicking":[110],"acoustic":[114],"channel.":[115],"The":[116],"results":[117],"indicate":[118],"eye":[120],"movements":[121],"can":[122],"compensate":[123],"missing":[126],"information":[127],"situation":[130],"support":[132],"modality":[138],"fail.":[139]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
