{"id":"https://openalex.org/W4400230133","doi":"https://doi.org/10.1109/iscas58744.2024.10558240","title":"Enhancing Cross-Modal Understanding for Audio Visual Scene-Aware Dialog Through Contrastive Learning","display_name":"Enhancing Cross-Modal Understanding for Audio Visual Scene-Aware Dialog Through Contrastive Learning","publication_year":2024,"publication_date":"2024-05-19","ids":{"openalex":"https://openalex.org/W4400230133","doi":"https://doi.org/10.1109/iscas58744.2024.10558240"},"language":"en","primary_location":{"id":"doi:10.1109/iscas58744.2024.10558240","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iscas58744.2024.10558240","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Symposium on Circuits and Systems (ISCAS)","raw_type":"proceedings-article"},"type":"article","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/A5045082466","display_name":"Feifei Xu","orcid":"https://orcid.org/0000-0001-8044-5912"},"institutions":[{"id":"https://openalex.org/I23632641","display_name":"Shanghai University of Electric Power","ror":"https://ror.org/02w4tny03","country_code":"CN","type":"education","lineage":["https://openalex.org/I23632641"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Feifei Xu","raw_affiliation_strings":["Shanghai University of Electric Power,Shanghai,China,201306"],"affiliations":[{"raw_affiliation_string":"Shanghai University of Electric Power,Shanghai,China,201306","institution_ids":["https://openalex.org/I23632641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100420313","display_name":"Zhou Wang","orcid":"https://orcid.org/0000-0003-4413-4441"},"institutions":[{"id":"https://openalex.org/I23632641","display_name":"Shanghai University of Electric Power","ror":"https://ror.org/02w4tny03","country_code":"CN","type":"education","lineage":["https://openalex.org/I23632641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang Zhou","raw_affiliation_strings":["Shanghai University of Electric Power,Shanghai,China,201306"],"affiliations":[{"raw_affiliation_string":"Shanghai University of Electric Power,Shanghai,China,201306","institution_ids":["https://openalex.org/I23632641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042284446","display_name":"Guangzhen Li","orcid":"https://orcid.org/0000-0002-8812-5558"},"institutions":[{"id":"https://openalex.org/I23632641","display_name":"Shanghai University of Electric Power","ror":"https://ror.org/02w4tny03","country_code":"CN","type":"education","lineage":["https://openalex.org/I23632641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangzhen Li","raw_affiliation_strings":["Shanghai University of Electric Power,Shanghai,China,201306"],"affiliations":[{"raw_affiliation_string":"Shanghai University of Electric Power,Shanghai,China,201306","institution_ids":["https://openalex.org/I23632641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100664803","display_name":"Zheng Zhong","orcid":"https://orcid.org/0000-0002-1711-7315"},"institutions":[{"id":"https://openalex.org/I23632641","display_name":"Shanghai University of Electric Power","ror":"https://ror.org/02w4tny03","country_code":"CN","type":"education","lineage":["https://openalex.org/I23632641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Zhong","raw_affiliation_strings":["Shanghai University of Electric Power,Shanghai,China,201306"],"affiliations":[{"raw_affiliation_string":"Shanghai University of Electric Power,Shanghai,China,201306","institution_ids":["https://openalex.org/I23632641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113373757","display_name":"Yingchen Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I23632641","display_name":"Shanghai University of Electric Power","ror":"https://ror.org/02w4tny03","country_code":"CN","type":"education","lineage":["https://openalex.org/I23632641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingchen Zhou","raw_affiliation_strings":["Shanghai University of Electric Power,Shanghai,China,201306"],"affiliations":[{"raw_affiliation_string":"Shanghai University of Electric Power,Shanghai,China,201306","institution_ids":["https://openalex.org/I23632641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5045082466"],"corresponding_institution_ids":["https://openalex.org/I23632641"],"apc_list":null,"apc_paid":null,"fwci":0.2624,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.50290803,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"1","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9782000184059143,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9782000184059143,"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/T11309","display_name":"Music and Audio Processing","score":0.95169997215271,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9516000151634216,"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":0.799221396446228},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.7398862838745117},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6720683574676514},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.55897456407547},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4903850555419922},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3907518982887268},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3825497627258301},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.379415899515152},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32988232374191284},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.2924806475639343},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.0739208459854126}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.799221396446228},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.7398862838745117},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6720683574676514},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.55897456407547},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4903850555419922},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3907518982887268},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3825497627258301},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.379415899515152},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32988232374191284},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2924806475639343},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0739208459854126},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscas58744.2024.10558240","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iscas58744.2024.10558240","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Symposium on Circuits and Systems (ISCAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W2070150502","https://openalex.org/W2101105183","https://openalex.org/W2154652894","https://openalex.org/W2337252826","https://openalex.org/W2525778437","https://openalex.org/W2905141912","https://openalex.org/W2952728748","https://openalex.org/W2964213933","https://openalex.org/W3000477803","https://openalex.org/W3035314827","https://openalex.org/W3099388488","https://openalex.org/W3123802026","https://openalex.org/W3137384391","https://openalex.org/W3162479984","https://openalex.org/W3205782068","https://openalex.org/W4221141684","https://openalex.org/W4224003584","https://openalex.org/W4287887552","https://openalex.org/W6682631176","https://openalex.org/W6727690538","https://openalex.org/W6757670774","https://openalex.org/W6773596017","https://openalex.org/W6789358351","https://openalex.org/W6810164656"],"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/W2292950558","https://openalex.org/W337810568"],"abstract_inverted_index":{"Audio":[0],"Visual":[1],"Scene-Aware":[2],"Dialog":[3],"is":[4,133],"a":[5,8,48,102,115,118,129],"task":[6],"where":[7],"robot":[9],"answers":[10,200],"questions":[11],"based":[12],"on":[13,101,211],"short":[14],"video":[15,204],"and":[16,35,61,105,137,141,184,213,222],"audio":[17,34],"content":[18],"as":[19,21],"well":[20],"dialog":[22,36],"history.":[23],"Although":[24],"previous":[25],"studies":[26],"try":[27],"to":[28,52,85,135,166,173,177,189,203],"improve":[29,106],"cross-modal":[30,54,224],"understanding":[31],"among":[32,143],"video,":[33,170],"history,":[37],"the":[38,72,80,98,107,121,139,154,169,175,191,199,208],"results":[39,210],"are":[40],"still":[41],"unsatisfactory.":[42],"In":[43],"this":[44],"paper,":[45],"we":[46,159],"propose":[47],"novel":[49],"contrastive":[50],"learning":[51],"enhance":[53,153],"understanding,":[55],"including":[56],"Masked":[57],"Contrastive":[58,63],"Learning":[59,64],"(CL-M)":[60,69],"Replaced":[62],"(CL-R).":[65],"The":[66,110],"first":[67],"strategy":[68,112],"involves":[70],"masking":[71,162],"entire":[73],"information":[74],"of":[75,207],"one":[76],"modality":[77,104,116,123],"while":[78],"keeping":[79],"other":[81],"three":[82],"modalities":[83,144],"unchanged":[84],"construct":[86],"negative":[87,130],"samples,":[88],"which":[89,151],"can":[90,152],"keep":[91],"awareness":[92],"towards":[93],"each":[94],"single":[95,103],"modality,":[96],"reduce":[97,190],"excessive":[99],"dependence":[100],"model\u2019s":[108,155],"robustness.":[109],"second":[111],"(CL-R)":[113],"replaces":[114],"in":[117,168,195],"sample":[119],"with":[120,147],"same":[122],"from":[124],"another":[125],"sample,":[126],"thereby":[127],"constructing":[128],"sample.":[131],"CL-R":[132],"designed":[134],"distinguish":[136],"comprehend":[138],"differences":[140],"relationships":[142],"when":[145],"faced":[146],"new":[148],"data":[149],"integration,":[150],"generalization":[156],"ability.":[157],"Additionally,":[158],"further":[160],"advance":[161],"entity":[163],"nouns":[164],"corresponding":[165],"objects":[167],"not":[171],"only":[172],"compel":[174],"model":[176],"draw":[178],"stronger":[179],"associations":[180],"between":[181],"textual":[182,196],"cues":[183],"visual":[185],"representations,":[186],"but":[187],"also":[188],"hallucination":[192],"often":[193],"existed":[194],"outputs,":[197],"generating":[198],"closely":[201],"related":[202],"contents.":[205],"Both":[206],"experimental":[209],"AVSD@DSTC7":[212],"AVSD@DSTC8":[214],"datasets":[215],"demonstrate":[216],"that":[217],"our":[218],"approach":[219],"shows":[220],"effectiveness":[221],"improves":[223],"understanding.":[225]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}