{"id":"https://openalex.org/W3206968814","doi":"https://doi.org/10.1145/3474085.3475360","title":"Exploring Contextual-Aware Representation and Linguistic-Diverse Expression for Visual Dialog","display_name":"Exploring Contextual-Aware Representation and Linguistic-Diverse Expression for Visual Dialog","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3206968814","doi":"https://doi.org/10.1145/3474085.3475360","mag":"3206968814"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475360","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475360","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","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/A5101598763","display_name":"Xiangpeng Li","orcid":"https://orcid.org/0000-0001-5350-5780"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangpeng Li","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066645546","display_name":"Lianli Gao","orcid":"https://orcid.org/0000-0002-2522-6394"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lianli Gao","raw_affiliation_strings":["University of Electronic Science and\u00a0Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and\u00a0Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101749819","display_name":"Lei Zhao","orcid":"https://orcid.org/0000-0002-8838-164X"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Zhao","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036987388","display_name":"Jingkuan Song","orcid":"https://orcid.org/0000-0002-2549-8322"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingkuan Song","raw_affiliation_strings":["University of Electronic Science and Technology of China, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Shenzhen, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4911","last_page":"4919"},"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/T10028","display_name":"Topic Modeling","score":0.9890000224113464,"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"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9853000044822693,"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":0.789177417755127},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5888002514839172},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.5743463039398193},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.523515522480011},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4989452362060547},{"id":"https://openalex.org/keywords/meaning","display_name":"Meaning (existential)","score":0.4869312047958374},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.48306113481521606},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4657258689403534},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.45058342814445496},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.43518853187561035},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.42965418100357056},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.41391226649284363},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1199679970741272},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11853161454200745},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.09327024221420288}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.789177417755127},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5888002514839172},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.5743463039398193},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.523515522480011},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4989452362060547},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.4869312047958374},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.48306113481521606},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4657258689403534},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45058342814445496},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.43518853187561035},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.42965418100357056},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.41391226649284363},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1199679970741272},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11853161454200745},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.09327024221420288},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3474085.3475360","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475360","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8500000238418579,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2296073425","https://openalex.org/W2625940279","https://openalex.org/W2786585376","https://openalex.org/W2808064329","https://openalex.org/W2892245540","https://openalex.org/W2895902247","https://openalex.org/W2917061951","https://openalex.org/W2923622379","https://openalex.org/W2930957955","https://openalex.org/W2963403868","https://openalex.org/W2963705779","https://openalex.org/W2964218959","https://openalex.org/W2966158321","https://openalex.org/W2967045987","https://openalex.org/W2970355596","https://openalex.org/W2981582341","https://openalex.org/W2981902456","https://openalex.org/W2997035654","https://openalex.org/W2997547717","https://openalex.org/W3027560576","https://openalex.org/W3034291519","https://openalex.org/W3034938700","https://openalex.org/W3035052826","https://openalex.org/W3035497460","https://openalex.org/W3037773948","https://openalex.org/W3093426013","https://openalex.org/W3095309002","https://openalex.org/W3099677434","https://openalex.org/W3116651605","https://openalex.org/W3147630004","https://openalex.org/W4249013746"],"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/W2368721880"],"abstract_inverted_index":{"Visual":[0],"dialog":[1],"is":[2,29,178],"a":[3,12,99,143,158,175,209],"fundamental":[4],"vision-language":[5],"task":[6,24],"where":[7,60],"an":[8],"AI":[9],"agent":[10],"holds":[11],"meaningful":[13],"dialogue":[14],"about":[15],"visual":[16,37,49,132],"content":[17],"with":[18,103,131,160,169,190],"humans":[19,155],"in":[20,41,186],"nature.":[21],"However,":[22],"this":[23,89],"remains":[25],"challenging,":[26],"since":[27],"there":[28],"still":[30],"no":[31],"consensus":[32],"way":[33],"to":[34,111,125,134,149,180],"capture":[35],"rich":[36],"contextual":[38],"information":[39,130],"contained":[40],"the":[42,56,69,73,113,118,127,136,151,165,183,188,206],"environment":[43],"rather":[44],"than":[45],"only":[46,62],"focusing":[47],"on":[48,197,212],"objects.":[50],"Furthermore,":[51],"conventional":[52],"methods":[53],"suffer":[54],"from":[55],"single-answer":[57],"learning":[58,110,146,152],"strategy,":[59],"it":[61],"accepts":[63],"one":[64,76],"correct":[65,162,191],"answer":[66,137],"without":[67],"considering":[68],"diverse":[70,170],"expressions":[71,81],"of":[72,154],"language":[74],"(i.e.,":[75],"identical":[77],"meaning":[78,167],"but":[79,168],"multiple":[80,161],"via":[82],"rephrasing":[83],"or":[84],"adopting":[85],"synonyms":[86],"etc).":[87],"In":[88,139],"paper,":[90],"we":[91,141],"introduce":[92],"Contextual-Aware":[93],"Representation":[94],"and":[95,107,201,217],"linguistic-diverse":[96],"Expression":[97],"(CARE),":[98],"novel":[100],"plug-and-play":[101],"framework":[102],"contextual-based":[104,119],"graph":[105,120],"embedding":[106,121],"curriculum":[108,144],"contrastive":[109,145],"solve":[112],"above":[114],"two":[115,198],"issues.":[116],"Specifically,":[117],"(CGE)":[122],"module":[123],"aims":[124],"integrate":[126],"environmental":[128],"context":[129],"objects":[133],"improve":[135],"quality.":[138],"addition,":[140],"propose":[142],"(CCL)":[147],"paradigm":[148],"imitate":[150],"habits":[153],"when":[156],"facing":[157],"question":[159],"answers":[163,189],"sharing":[164],"same":[166],"expressions.":[171],"To":[172],"support":[173],"CCL,":[174],"CCL":[176],"loss":[177],"designed":[179],"progressively":[181],"strengthen":[182],"model's":[184],"ability":[185],"identifying":[187],"semantics.":[192],"Extensive":[193],"experiments":[194],"are":[195],"conducted":[196],"benchmark":[199],"datasets,":[200],"our":[202],"proposed":[203],"method":[204],"outperforms":[205],"state-of-the-arts":[207],"by":[208],"considerable":[210],"margin":[211],"VisDial":[213,218],"V1.0":[214],"(4.63%":[215],"NDCG)":[216],"V0.9":[219],"(1.27%":[220],"MRR,":[221],"1.74%":[222],"[email":[223,226,229],"protected],":[224,227,230],"0.87%":[225],"1.28%":[228],"0.26":[231],"Mean.":[232]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}