{"id":"https://openalex.org/W4224003584","doi":"https://doi.org/10.1109/icassp43922.2022.9747769","title":"Improving Cross-Modal Understanding in Visual Dialog Via Contrastive Learning","display_name":"Improving Cross-Modal Understanding in Visual Dialog Via Contrastive Learning","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224003584","doi":"https://doi.org/10.1109/icassp43922.2022.9747769"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747769","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747769","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/A5101667541","display_name":"Feilong Chen","orcid":"https://orcid.org/0000-0002-4860-8483"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feilong Chen","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences,Beijing,China","Institute of Automation, Chinese Academy of Sciences, Beijing, China","School of Future Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]},{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]},{"raw_affiliation_string":"School of Future Technology, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009070585","display_name":"Xiuyi Chen","orcid":"https://orcid.org/0000-0002-9351-4160"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiuyi Chen","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences,Beijing,China","Institute of Automation, Chinese Academy of Sciences, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]},{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004363895","display_name":"Shuang Xu","orcid":"https://orcid.org/0000-0003-3576-6914"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuang Xu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences,Beijing,China","Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]},{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112315995","display_name":"Bo Xu","orcid":"https://orcid.org/0000-0002-2144-4271"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Xu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences,Beijing,China","Institute of Automation, Chinese Academy of Sciences, Beijing, China","School of Future Technology, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]},{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]},{"raw_affiliation_string":"School of Future Technology, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3869,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.87992448,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7937","last_page":"7941"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9929999709129333,"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":0.9821000099182129,"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/dialog-box","display_name":"Dialog box","score":0.954648494720459},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8142129778862},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6249730587005615},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6239442825317383},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.572708785533905},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5623630881309509},{"id":"https://openalex.org/keywords/dialog-system","display_name":"Dialog system","score":0.47421741485595703},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.47196802496910095},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.46387943625450134},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3931381404399872},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35769569873809814},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.1197793185710907},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09819814562797546},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.09246104955673218}],"concepts":[{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.954648494720459},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8142129778862},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6249730587005615},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6239442825317383},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.572708785533905},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5623630881309509},{"id":"https://openalex.org/C190954187","wikidata":"https://www.wikidata.org/wiki/Q5270587","display_name":"Dialog system","level":3,"score":0.47421741485595703},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.47196802496910095},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.46387943625450134},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3931381404399872},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35769569873809814},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.1197793185710907},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09819814562797546},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.09246104955673218},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"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/icassp43922.2022.9747769","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747769","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","score":0.47999998927116394,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1575833922","https://openalex.org/W2277195237","https://openalex.org/W2622980782","https://openalex.org/W2892245540","https://openalex.org/W2896457183","https://openalex.org/W2963287297","https://openalex.org/W2963623904","https://openalex.org/W2964218959","https://openalex.org/W2966158321","https://openalex.org/W2967045987","https://openalex.org/W2967674528","https://openalex.org/W2996781902","https://openalex.org/W2997547717","https://openalex.org/W3034291519","https://openalex.org/W3035052826","https://openalex.org/W3035103424","https://openalex.org/W3095309002","https://openalex.org/W3099143471","https://openalex.org/W3105966348","https://openalex.org/W3107092117","https://openalex.org/W3116651605","https://openalex.org/W3175076935","https://openalex.org/W3175445769","https://openalex.org/W4206715653","https://openalex.org/W4249013746","https://openalex.org/W4385245566","https://openalex.org/W6620707391","https://openalex.org/W6630875275","https://openalex.org/W6631190155","https://openalex.org/W6634232107","https://openalex.org/W6739177970","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6766849139","https://openalex.org/W6768086466","https://openalex.org/W6780226713"],"related_works":["https://openalex.org/W48079147","https://openalex.org/W2394821827","https://openalex.org/W2563921006","https://openalex.org/W1963944933","https://openalex.org/W2111550420","https://openalex.org/W1977846844","https://openalex.org/W2549666521","https://openalex.org/W3133893348","https://openalex.org/W2901575119","https://openalex.org/W3183295012"],"abstract_inverted_index":{"Visual":[0],"Dialog":[1],"is":[2],"a":[3,15,80,132],"challenging":[4],"vision-language":[5,74],"task":[6],"since":[7],"the":[8,23,36,65,73,85,117,124,139,143,154],"visual":[9,40,56,69,89,119,125,144],"dialog":[10,27,70,126,145],"agent":[11],"needs":[12],"to":[13,33,83,122,130,153],"answer":[14],"series":[16],"of":[17,55],"questions":[18,105],"after":[19],"reasoning":[20],"over":[21],"both":[22],"image":[24],"content":[25],"and":[26,57,78,149],"history.":[28],"Though":[29],"existing":[30],"methods":[31],"try":[32],"deal":[34],"with":[35],"cross-modal":[37,66,86,95,128,147],"understanding":[38,54,67,87,96,129,148],"in":[39,47,68],"dialog,":[41,90],"they":[42],"are":[43],"still":[44],"not":[45],"enough":[46],"ranking":[48],"candidate":[49],"answers":[50],"based":[51,71,108],"on":[52,72,109],"their":[53],"textual":[58],"contexts.":[59],"In":[60,113],"this":[61],"paper,":[62],"we":[63],"analyze":[64],"pre-training":[75],"model":[76],"VD-BERT":[77],"propose":[79],"novel":[81],"approach":[82,141],"improve":[84],"for":[88],"named":[91],"ICMU.":[92],"ICMU":[93,115],"enhances":[94],"by":[97],"distinguishing":[98],"different":[99],"pulled":[100,103],"inputs":[101],"(i.e.":[102],"images,":[104],"or":[106],"answers)":[107],"four-way":[110],"contrastive":[111],"learning.":[112],"addition,":[114],"exploits":[116],"single-turn":[118],"question":[120],"answering":[121],"enhance":[123],"model\u2019s":[127,146],"handle":[131],"multi-turn":[133],"visually-grounded":[134],"conversation.":[135],"Experiments":[136],"show":[137],"that":[138],"proposed":[140],"improves":[142],"brings":[150],"satisfactory":[151],"gain":[152],"Vis-Dial":[155],"dataset.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}