{"id":"https://openalex.org/W3090765191","doi":"https://doi.org/10.1145/3395035.3425202","title":"Training Strategies to Handle Missing Modalities for Audio-Visual Expression Recognition","display_name":"Training Strategies to Handle Missing Modalities for Audio-Visual Expression Recognition","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3090765191","doi":"https://doi.org/10.1145/3395035.3425202","mag":"3090765191"},"language":"en","primary_location":{"id":"doi:10.1145/3395035.3425202","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3395035.3425202","pdf_url":null,"source":{"id":"https://openalex.org/S4306506653","display_name":"Companion Publication of the 2020 International Conference on Multimodal Interaction","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"Companion Publication of the 2020 International Conference on Multimodal Interaction","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2010.00734","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103091951","display_name":"Srinivas Parthasarathy","orcid":"https://orcid.org/0000-0001-8928-9821"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Srinivas Parthasarathy","raw_affiliation_strings":["Amazon, Sunnyvale, CA, USA","[Amazon, Sunnyvale, CA, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"[Amazon, Sunnyvale, CA, USA]","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113697636","display_name":"Shiva Sundaram","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shiva Sundaram","raw_affiliation_strings":["Amazon, Sunnyvale, CA, USA","[Amazon, Sunnyvale, CA, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"[Amazon, Sunnyvale, CA, USA]","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1311688040"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.10718581,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"400","last_page":"404"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.8328558206558228},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.7386974096298218},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.7168847322463989},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.698795735836029},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5112230777740479},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5040613412857056},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4027068018913269},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.2412206530570984}],"concepts":[{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.8328558206558228},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.7386974096298218},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.7168847322463989},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.698795735836029},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5112230777740479},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5040613412857056},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4027068018913269},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2412206530570984},{"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3395035.3425202","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3395035.3425202","pdf_url":null,"source":{"id":"https://openalex.org/S4306506653","display_name":"Companion Publication of the 2020 International Conference on Multimodal Interaction","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"Companion Publication of the 2020 International Conference on Multimodal Interaction","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2010.00734","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.00734","pdf_url":"https://arxiv.org/pdf/2010.00734","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,"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":"mag:3090765191","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2010.00734.pdf","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,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2010.00734","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2010.00734","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,"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":"pmh:oai:arXiv.org:2010.00734","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.00734","pdf_url":"https://arxiv.org/pdf/2010.00734","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,"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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3090765191.pdf","grobid_xml":"https://content.openalex.org/works/W3090765191.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W257874415","https://openalex.org/W1842328245","https://openalex.org/W2003502731","https://openalex.org/W2015433306","https://openalex.org/W2144005487","https://openalex.org/W2158705122","https://openalex.org/W2325939864","https://openalex.org/W2547190339","https://openalex.org/W2551572271","https://openalex.org/W2767618761","https://openalex.org/W2884739346","https://openalex.org/W2886300652","https://openalex.org/W2899500748","https://openalex.org/W2901836079","https://openalex.org/W2936900244","https://openalex.org/W2952746495","https://openalex.org/W2962749013","https://openalex.org/W2963130397","https://openalex.org/W2963252191","https://openalex.org/W2963403868","https://openalex.org/W2972602947","https://openalex.org/W2980182114","https://openalex.org/W3034266838","https://openalex.org/W3035299099","https://openalex.org/W3106250896","https://openalex.org/W3128420506"],"related_works":["https://openalex.org/W3114214226","https://openalex.org/W2944644860","https://openalex.org/W2072280422","https://openalex.org/W2064376699","https://openalex.org/W2796389856","https://openalex.org/W1493921411","https://openalex.org/W2608909763","https://openalex.org/W3048437343","https://openalex.org/W2790619349","https://openalex.org/W2743620379","https://openalex.org/W228268266","https://openalex.org/W2762989847","https://openalex.org/W1978247574","https://openalex.org/W2765407918","https://openalex.org/W2588045789","https://openalex.org/W2951582018","https://openalex.org/W3129885336","https://openalex.org/W2897688721","https://openalex.org/W3092154597","https://openalex.org/W2953001380"],"abstract_inverted_index":{"Automatic":[0],"audio-visual":[1,22,36],"expression":[2,23,37],"recognition":[3,24,38],"can":[4],"play":[5],"an":[6],"important":[7],"role":[8],"in":[9,41,47,101,138],"communication":[10],"services":[11],"such":[12,67],"as":[13,68],"tele-health,":[14],"VOIP":[15],"calls":[16],"and":[17],"human-machine":[18],"interaction.":[19],"Accuracy":[20],"of":[21,65,81,88,104,164],"could":[25,58],"benefit":[26],"from":[27],"the":[28,31,53,79,89,99,102,120,162],"interplay":[29],"between":[30],"two":[32],"modalities.":[33,166],"However,":[34],"most":[35],"systems,":[39],"trained":[40,141],"ideal":[42],"conditions,":[43],"fail":[44],"to":[45,62,97,112,125,148],"generalize":[46],"real":[48,127],"world":[49,128],"scenarios":[50],"where":[51],"either":[52,105],"audio":[54],"or":[55,122],"visual":[56,115],"modality":[57],"be":[59],"missing":[60,143],"due":[61],"a":[63,82,110],"number":[64],"reasons":[66],"limited":[69],"bandwidth,":[70],"interactors'":[71],"orientation,":[72],"caller":[73],"initiated":[74],"muting.":[75],"This":[76],"paper":[77],"studies":[78,96],"performance":[80],"state-of-the":[83],"art":[84],"transformer":[85],"when":[86],"one":[87],"modalities":[90],"is":[91],"missing.":[92],"We":[93],"conduct":[94],"ablation":[95],"evaluate":[98],"model":[100],"absence":[103],"modality.":[106],"Further,":[107],"we":[108],"propose":[109],"strategy":[111],"randomly":[113],"ablate":[114],"inputs":[116],"during":[117],"training":[118,157],"at":[119],"clip":[121],"frame":[123,151],"level":[124,152],"mimic":[126],"scenarios.":[129],"Results":[130],"conducted":[131],"on":[132,142],"in-the-wild":[133],"data,":[134],"indicate":[135],"significant":[136],"generalization":[137],"proposed":[139],"models":[140],"cues,":[144],"with":[145,161],"gains":[146],"up":[147],"17%":[149],"for":[150],"ablations,":[153],"showing":[154],"that":[155],"these":[156],"strategies":[158],"cope":[159],"better":[160],"loss":[163],"input":[165]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}