{"id":"https://openalex.org/W3205782068","doi":"https://doi.org/10.1109/icassp43922.2022.9746481","title":"Audio-Visual Scene-Aware Dialog and Reasoning Using Audio-Visual Transformers with Joint Student-Teacher Learning","display_name":"Audio-Visual Scene-Aware Dialog and Reasoning Using Audio-Visual Transformers with Joint Student-Teacher Learning","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3205782068","doi":"https://doi.org/10.1109/icassp43922.2022.9746481","mag":"3205782068"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746481","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746481","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5029694255","display_name":"Ankit Shah","orcid":"https://orcid.org/0000-0001-6818-0827"},"institutions":[{"id":"https://openalex.org/I4210133125","display_name":"Mitsubishi Electric (Japan)","ror":"https://ror.org/033y26782","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["JP","US"],"is_corresponding":false,"raw_author_name":"Ankit Shah","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL)","Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL)","institution_ids":["https://openalex.org/I4210133125"]},{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080973846","display_name":"Shijie Geng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096112","display_name":"Rutgers Sexual and Reproductive Health and Rights","ror":"https://ror.org/00rcvgx40","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210096112"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Shijie Geng","raw_affiliation_strings":["Rutgers University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers University","institution_ids":["https://openalex.org/I4210096112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106667221","display_name":"Peng Gao","orcid":"https://orcid.org/0009-0005-7881-712X"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Peng Gao","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024613828","display_name":"Anoop Cherian","orcid":"https://orcid.org/0000-0002-5566-0351"},"institutions":[{"id":"https://openalex.org/I4210133125","display_name":"Mitsubishi Electric (Japan)","ror":"https://ror.org/033y26782","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Anoop Cherian","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL)","institution_ids":["https://openalex.org/I4210133125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087554069","display_name":"Takaaki Hori","orcid":"https://orcid.org/0000-0003-4560-8039"},"institutions":[{"id":"https://openalex.org/I4210133125","display_name":"Mitsubishi Electric (Japan)","ror":"https://ror.org/033y26782","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takaaki Hori","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL)","institution_ids":["https://openalex.org/I4210133125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008369672","display_name":"Tim K. Marks","orcid":null},"institutions":[{"id":"https://openalex.org/I4210133125","display_name":"Mitsubishi Electric (Japan)","ror":"https://ror.org/033y26782","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tim K. Marks","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL)","institution_ids":["https://openalex.org/I4210133125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076453358","display_name":"Jonathan Le Roux","orcid":"https://orcid.org/0000-0002-3451-171X"},"institutions":[{"id":"https://openalex.org/I4210133125","display_name":"Mitsubishi Electric (Japan)","ror":"https://ror.org/033y26782","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jonathan Le Roux","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL)","institution_ids":["https://openalex.org/I4210133125"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001601327","display_name":"Chiori Hori","orcid":"https://orcid.org/0000-0002-4201-7578"},"institutions":[{"id":"https://openalex.org/I4210133125","display_name":"Mitsubishi Electric (Japan)","ror":"https://ror.org/033y26782","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Chiori Hori","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL)","institution_ids":["https://openalex.org/I4210133125"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7732","last_page":"7736"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9951000213623047,"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/T10812","display_name":"Human Pose and Action Recognition","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7831451892852783},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.7815054059028625},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5809581279754639},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5762825608253479},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5343493819236755},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5213752388954163},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4818207323551178},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4739282727241516},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.430441677570343},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.42659100890159607},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33527475595474243},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.32380491495132446},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3046896457672119},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.13509848713874817}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7831451892852783},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.7815054059028625},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5809581279754639},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5762825608253479},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5343493819236755},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5213752388954163},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4818207323551178},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4739282727241516},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.430441677570343},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.42659100890159607},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33527475595474243},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32380491495132446},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3046896457672119},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.13509848713874817},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746481","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746481","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4000000059604645}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W854541894","https://openalex.org/W1933349210","https://openalex.org/W2133564696","https://openalex.org/W2250539671","https://openalex.org/W2337252826","https://openalex.org/W2526050071","https://openalex.org/W2560730294","https://openalex.org/W2584992898","https://openalex.org/W2603266952","https://openalex.org/W2613718673","https://openalex.org/W2768661419","https://openalex.org/W2810643877","https://openalex.org/W2911400095","https://openalex.org/W2952686080","https://openalex.org/W2952728748","https://openalex.org/W2963403868","https://openalex.org/W2963524571","https://openalex.org/W2963890019","https://openalex.org/W2963890755","https://openalex.org/W2964213933","https://openalex.org/W2972745026","https://openalex.org/W3000366420","https://openalex.org/W3004165599","https://openalex.org/W3012039651","https://openalex.org/W3099388488","https://openalex.org/W3126942607","https://openalex.org/W3128093669","https://openalex.org/W3134294468","https://openalex.org/W3137384391","https://openalex.org/W3162479984","https://openalex.org/W3177418244","https://openalex.org/W4287777632","https://openalex.org/W4385245566","https://openalex.org/W6620707391","https://openalex.org/W6623517193","https://openalex.org/W6679434410","https://openalex.org/W6739901393","https://openalex.org/W6745764446","https://openalex.org/W6777481484","https://openalex.org/W6780226713"],"related_works":["https://openalex.org/W2098987383","https://openalex.org/W2417260800","https://openalex.org/W1596203174","https://openalex.org/W2117933979","https://openalex.org/W2283130723","https://openalex.org/W103938586","https://openalex.org/W2104718772","https://openalex.org/W4233992201","https://openalex.org/W1977846844","https://openalex.org/W2999894541"],"abstract_inverted_index":{"In":[0,37],"previous":[1],"work,":[2],"we":[3,72,131,148],"have":[4],"proposed":[5,73],"the":[6,27,40,49,56,84,103,112,124,152,183],"Audio-Visual":[7],"Scene-Aware":[8],"Dialog":[9,31],"(AVSD)":[10],"task,":[11],"collected":[12,132],"an":[13,21,145],"AVSD":[14,17,22,76,125,184],"dataset,":[15],"developed":[16],"technologies,":[18],"and":[19,29,92,119,175,189,202],"hosted":[20],"challenge":[23],"track":[24],"at":[25,78,89],"both":[26],"7th":[28],"8th":[30],"System":[32],"Technology":[33],"Challenges":[34],"(DSTC7,":[35],"DSTC8).":[36],"these":[38],"challenges,":[39],"best-performing":[41],"systems":[42,94],"relied":[43],"heavily":[44],"on":[45,182,205],"human-generated":[46,133],"descriptions":[47],"of":[48,123],"video":[50,104],"content,":[51],"which":[52,130,147],"were":[53],"available":[54],"in":[55,62],"datasets":[57,185],"but":[58],"would":[59],"be":[60],"unavailable":[61,88],"real-world":[63,70],"applications.":[64],"To":[65],"promote":[66],"further":[67],"advancements":[68],"for":[69,127,129,186,198],"applications,":[71],"a":[74,140,159,206],"third":[75],"challenge,":[77],"DSTC10,":[79,128],"with":[80,151,167],"two":[81,194],"modifications:":[82],"1)":[83],"human-created":[85],"description":[86],"is":[87],"inference":[90],"time,":[91],"2)":[93],"must":[95],"demonstrate":[96],"temporal":[97,117,134,195],"reasoning":[98,118,135,196],"by":[99],"finding":[100],"evidence":[101],"from":[102],"to":[105],"support":[106],"each":[107],"answer.":[108],"This":[109],"paper":[110,157],"introduces":[111,158],"new":[113,121,153,160],"task":[114],"that":[115,162],"includes":[116],"our":[120,164],"extension":[122],"dataset":[126],"data.":[136],"We":[137,191],"also":[138,192],"introduce":[139],"baseline":[141,165],"system":[142,161,166],"built":[143],"using":[144],"AV-transformer,":[146],"released":[149],"along":[150],"dataset.":[154],"Finally,":[155],"this":[156],"extends":[163],"attentional":[168],"multimodal":[169],"fusion,":[170],"joint":[171],"student-teacher":[172],"learning":[173],"(JSTL),":[174],"model":[176],"combination":[177],"techniques,":[178],"achieving":[179],"state-of-the-art":[180],"performances":[181],"DSTC7,":[187],"DSTC8,":[188],"DSTC10.":[190],"propose":[193],"methods":[197],"AVSD:":[199],"one":[200,203],"attention-based,":[201],"based":[204],"time-domain":[207],"region":[208],"proposal":[209],"network.":[210]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}