{"id":"https://openalex.org/W4402352809","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650237","title":"Visual Dialog with Explicit Co-Reference Resolution and Personality Consistency","display_name":"Visual Dialog with Explicit Co-Reference Resolution and Personality Consistency","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402352809","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650237"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10650237","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10650237","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","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/A5100331862","display_name":"Yunpeng Li","orcid":"https://orcid.org/0000-0003-4798-541X"},"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/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunpeng Li","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107951196","display_name":"Yue Hu","orcid":null},"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/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Hu","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101877619","display_name":"Xu Bai","orcid":null},"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/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Bai","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"30","issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9998000264167786,"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/T11148","display_name":"Language, Metaphor, and Cognition","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9854999780654907,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.7962902784347534},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6820595860481262},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6214013695716858},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.5916688442230225},{"id":"https://openalex.org/keywords/personality","display_name":"Personality","score":0.5373451113700867},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4578711986541748},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.43798828125},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.4086286425590515},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3893411159515381},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38244953751564026},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.29958605766296387},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.17479470372200012},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.10934913158416748}],"concepts":[{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.7962902784347534},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6820595860481262},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6214013695716858},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.5916688442230225},{"id":"https://openalex.org/C187288502","wikidata":"https://www.wikidata.org/wiki/Q641118","display_name":"Personality","level":2,"score":0.5373451113700867},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4578711986541748},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.43798828125},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.4086286425590515},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3893411159515381},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38244953751564026},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.29958605766296387},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.17479470372200012},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.10934913158416748}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn60899.2024.10650237","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10650237","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2020240201","https://openalex.org/W2134051188","https://openalex.org/W2563399268","https://openalex.org/W2612690371","https://openalex.org/W2892245540","https://openalex.org/W2904910963","https://openalex.org/W2917061951","https://openalex.org/W2963191264","https://openalex.org/W2963623904","https://openalex.org/W2963625095","https://openalex.org/W2964218959","https://openalex.org/W2964352131","https://openalex.org/W2966158321","https://openalex.org/W2966683369","https://openalex.org/W2967045987","https://openalex.org/W2981902456","https://openalex.org/W2986536733","https://openalex.org/W2988023442","https://openalex.org/W2990095214","https://openalex.org/W2997547717","https://openalex.org/W3034291519","https://openalex.org/W3034578524","https://openalex.org/W3035103424","https://openalex.org/W3095309002","https://openalex.org/W3147630004","https://openalex.org/W4206625585","https://openalex.org/W4237040408","https://openalex.org/W4249013746","https://openalex.org/W6629633590","https://openalex.org/W6679436768","https://openalex.org/W6691553118","https://openalex.org/W6727884368","https://openalex.org/W6739177970","https://openalex.org/W6743696045","https://openalex.org/W6747998910","https://openalex.org/W6749996792","https://openalex.org/W6755207826","https://openalex.org/W6759446547","https://openalex.org/W6770005108","https://openalex.org/W6777153324","https://openalex.org/W6777875527"],"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":{"Visual":[0],"dialog":[1,38,71,125,138],"is":[2,11,40,47],"a":[3,8,92],"multi-turn":[4],"on-going":[5],"conversation,":[6],"where":[7],"critical":[9],"challenge":[10],"how":[12,129],"to":[13,98,117],"understand":[14],"questions":[15,134],"with":[16,21,28],"co-reference":[17,86],"ambiguities":[18],"and":[19,73,140,193],"reply":[20],"personality":[22,56],"consistency":[23],"through":[24],"dialog.":[25,61],"Previous":[26],"works":[27,50],"history":[29,39,72,102],"encoding":[30],"inevitably":[31],"introduce":[32],"unexpected":[33],"noise":[34],"since":[35],"the":[36,53,70,100,104,114,119,131,136,142,183,196],"whole":[37],"considered":[41],"via":[42],"implicit":[43],"attention.":[44],"Moreover,":[45],"there":[46],"still":[48],"no":[49],"focus":[51],"on":[52,181,190],"role":[54],"of":[55,69,128,153],"at":[57],"present":[58],"in":[59,79,123,126,135,163,172],"visual":[60,124],"In":[62,107],"this":[63],"paper,":[64],"we":[65,84,112,177],"conduct":[66],"in-depth":[67],"study":[68],"propose":[74],"two":[75,170],"novel":[76],"modules.":[77],"Specifically,":[78],"Explicit":[80],"Co-Reference":[81],"Resolution":[82],"module,":[83,111],"perform":[85],"resolution":[87],"by":[88],"modeling":[89],"it":[90],"as":[91,200],"sequence":[93],"tagging":[94],"task,":[95],"which":[96],"helps":[97],"locate":[99],"relevant":[101],"for":[103,146],"current":[105],"question.":[106],"User":[108],"Personality":[109],"Modeling":[110],"make":[113],"first":[115],"attempt":[116],"model":[118],"user\u2019s":[120],"interaction":[121],"style":[122],"terms":[127],"detailedly":[130],"user":[132,143],"answered":[133],"previous":[137],"rounds":[139],"generate":[141],"preference":[144],"score":[145],"each":[147],"answer":[148],"candidate.":[149],"Note":[150],"that":[151],"both":[152],"our":[154],"proposed":[155],"modules":[156,171],"are":[157,161],"model-agnostic":[158],"so":[159],"they":[160],"applicable":[162],"any":[164],"VisDial":[165,191],"model.":[166],"By":[167],"applying":[168],"these":[169],"several":[173],"representative":[174],"baseline":[175],"models,":[176],"show":[178],"significant":[179],"boosts":[180],"all":[182],"evaluation":[184],"metrics,":[185],"achieving":[186],"new":[187],"state-of-the-art":[188],"results":[189],"v1.0":[192],"even":[194],"outperforming":[195],"pre-training":[197],"models":[198],"such":[199],"VD-BERT":[201],"[1].":[202]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}