{"id":"https://openalex.org/W4379983266","doi":"https://doi.org/10.1109/tmm.2023.3284594","title":"Counterfactual Visual Dialog: Robust Commonsense Knowledge Learning From Unbiased Training","display_name":"Counterfactual Visual Dialog: Robust Commonsense Knowledge Learning From Unbiased Training","publication_year":2023,"publication_date":"2023-06-09","ids":{"openalex":"https://openalex.org/W4379983266","doi":"https://doi.org/10.1109/tmm.2023.3284594"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2023.3284594","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3284594","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5081485810","display_name":"An-An Liu","orcid":"https://orcid.org/0000-0001-5755-9145"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"An-An Liu","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China","Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-5755-9145","affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009018575","display_name":"Chenxi Huang","orcid":"https://orcid.org/0000-0002-2100-0259"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenxi Huang","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054900679","display_name":"Ning Xu","orcid":"https://orcid.org/0000-0002-7526-4356"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ning Xu","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-7526-4356","affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019994406","display_name":"Hongshuo Tian","orcid":"https://orcid.org/0000-0001-7635-0961"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongshuo Tian","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0001-7635-0961","affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100375136","display_name":"Jing Liu","orcid":"https://orcid.org/0000-0003-4690-1886"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Liu","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0003-4690-1886","affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046305086","display_name":"Yongdong Zhang","orcid":"https://orcid.org/0000-0002-1151-1792"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongdong Zhang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-1151-1792","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0638,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.75413546,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"26","issue":null,"first_page":"1639","last_page":"1651"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9965999722480774,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9751999974250793,"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":0.8200291991233826},{"id":"https://openalex.org/keywords/commonsense-knowledge","display_name":"Commonsense knowledge","score":0.6839258074760437},{"id":"https://openalex.org/keywords/notation","display_name":"Notation","score":0.5929941534996033},{"id":"https://openalex.org/keywords/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.5642427206039429},{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.563077449798584},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5519171357154846},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4776562452316284},{"id":"https://openalex.org/keywords/marginalia","display_name":"Marginalia","score":0.41142377257347107},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.3417777419090271},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2855061888694763},{"id":"https://openalex.org/keywords/epistemology","display_name":"Epistemology","score":0.26084446907043457},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.19818800687789917},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.18420934677124023},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.13029956817626953},{"id":"https://openalex.org/keywords/theology","display_name":"Theology","score":0.1236640214920044},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.1143556535243988},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.11396867036819458}],"concepts":[{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.8200291991233826},{"id":"https://openalex.org/C30542707","wikidata":"https://www.wikidata.org/wiki/Q1603203","display_name":"Commonsense knowledge","level":3,"score":0.6839258074760437},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.5929941534996033},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.5642427206039429},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.563077449798584},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5519171357154846},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4776562452316284},{"id":"https://openalex.org/C2777940294","wikidata":"https://www.wikidata.org/wiki/Q1572441","display_name":"Marginalia","level":2,"score":0.41142377257347107},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.3417777419090271},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2855061888694763},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.26084446907043457},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.19818800687789917},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.18420934677124023},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.13029956817626953},{"id":"https://openalex.org/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","level":1,"score":0.1236640214920044},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.1143556535243988},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.11396867036819458}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2023.3284594","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3284594","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G173205433","display_name":null,"funder_award_id":"U21B2024","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7474616114","display_name":null,"funder_award_id":"62002257","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"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":66,"referenced_works":["https://openalex.org/W284239745","https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W2064675550","https://openalex.org/W2125204570","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2561529111","https://openalex.org/W2892245540","https://openalex.org/W2917061951","https://openalex.org/W2955124656","https://openalex.org/W2963287297","https://openalex.org/W2963609017","https://openalex.org/W2963623904","https://openalex.org/W2964218959","https://openalex.org/W2966158321","https://openalex.org/W2966817867","https://openalex.org/W2967045987","https://openalex.org/W2970019270","https://openalex.org/W2970355596","https://openalex.org/W2981902456","https://openalex.org/W2983256121","https://openalex.org/W2987123286","https://openalex.org/W2988023442","https://openalex.org/W2996984511","https://openalex.org/W3015686016","https://openalex.org/W3027560576","https://openalex.org/W3035017890","https://openalex.org/W3035103424","https://openalex.org/W3035517717","https://openalex.org/W3037466839","https://openalex.org/W3038528491","https://openalex.org/W3043515420","https://openalex.org/W3095309002","https://openalex.org/W3096612875","https://openalex.org/W3101767943","https://openalex.org/W3107092117","https://openalex.org/W3108230874","https://openalex.org/W3126665002","https://openalex.org/W3139224848","https://openalex.org/W3139565899","https://openalex.org/W3154360660","https://openalex.org/W3165695488","https://openalex.org/W3173972567","https://openalex.org/W3177101259","https://openalex.org/W3177934633","https://openalex.org/W3181758331","https://openalex.org/W3203596689","https://openalex.org/W3206022579","https://openalex.org/W4211071949","https://openalex.org/W4221155360","https://openalex.org/W4223451840","https://openalex.org/W4249013746","https://openalex.org/W4285725668","https://openalex.org/W4288055726","https://openalex.org/W4288062562","https://openalex.org/W4293519344","https://openalex.org/W4296079526","https://openalex.org/W4312457137","https://openalex.org/W4312695920","https://openalex.org/W4385573551","https://openalex.org/W6631190155","https://openalex.org/W6631501603","https://openalex.org/W6739177970","https://openalex.org/W6743696045","https://openalex.org/W7064929991"],"related_works":["https://openalex.org/W3201448254","https://openalex.org/W4286970243","https://openalex.org/W1985363335","https://openalex.org/W2066431708","https://openalex.org/W4391028641","https://openalex.org/W1977858819","https://openalex.org/W3136477027","https://openalex.org/W3025615835","https://openalex.org/W4384133558","https://openalex.org/W4284706735"],"abstract_inverted_index":{"Visual":[0,147],"Dialog":[1,148],"(VD)":[2],"requires":[3],"an":[4,20,192],"agent":[5],"to":[6,19,29,34,51,96,107,122,171,201,209],"answer":[7,89,206],"the":[8,23,37,44,61,78,82,87,109,117,126,146,154,180,196,205,211,214,220,230,238,248,254],"current":[9],"question":[10,79],"by":[11,58,234],"engaging":[12],"in":[13,195],"a":[14,74,139],"conversation":[15],"with":[16,153],"humans":[17],"referring":[18],"image.":[21,178],"Despite":[22],"recent":[24],"progress,":[25],"it":[26,190,218,236],"is":[27,81,184],"beneficial":[28],"introduce":[30],"external":[31],"commonsense":[32,98,114,130,165,197,225],"knowledge":[33,115,182],"fully":[35],"understand":[36],"given":[38],"image":[39],"and":[40,86,119,124,167,177,186,228,258],"dialog":[41],"history.":[42],"However,":[43],"existing":[45,158],"knowledge-based":[46],"VD":[47,159],"models":[48],"are":[49,93],"inclined":[50],"rely":[52],"on":[53,132,226,253],"severe":[54],"learning":[55,99,143],"bias":[56,131],"brought":[57],"commonsense,":[59],"e.g.,":[60],"retrieved$<":[62],"{\\mathtt{{bus}}},":[63,66,70],"{\\mathtt{capable\\;of}},":[64],"{\\mathtt{transport\\;people}}>$,$<":[65],"{\\mathtt{is\\;a}},":[67,71],"{\\mathtt{public\\;transport}}>$,":[68],"and$<":[69],"{\\mathtt{car}}>$can":[72],"induce":[73],"spurious":[75,103,202],"correlation":[76],"between":[77],"\u201cWhat":[80],"bus":[83],"used":[84],"for?\u201d":[85],"false":[88],"\u201cCity":[90],"bus\u201d.":[91],"There":[92],"two":[94],"challenges":[95],"make":[97],"more":[100],"robust":[101],"against":[102],"correlations:":[104],"1)":[105],"how":[106,121],"disentangle":[108],"true":[110],"effect":[111,127,212,223,233,241],"of":[112,128,157,213,224,250],"\u201cgood\u201d":[113],"from":[116,174,237],"whole,":[118],"2)":[120],"estimate":[123],"remove":[125,210,229],"\u201cbad\u201d":[129],"answers.":[133],"In":[134],"this":[135],"article,":[136],"we":[137,161,188,216],"propose":[138],"novel":[140],"CounterFactual":[141],"Commonsense":[142],"scheme":[144],"for":[145,204],"task":[149],"(CFC-VD).":[150],"First,":[151],"comparing":[152],"causal":[155,222,240],"graph":[156],"models,":[160],"add":[162],"one":[163,168],"new":[164,169],"node":[166],"link":[170],"multi-modal":[172],"information":[173],"history,":[175],"question,":[176],"Since":[179],"retrieved":[181],"prior":[183],"subtle":[185],"uncontrollable,":[187],"consider":[189],"as":[191,219],"unobserved":[193],"confounder":[194],"node,":[198],"which":[199],"leads":[200],"correlations":[203],"inference.":[207],"Then,":[208],"confounder,":[215],"formulate":[217],"direct":[221,231],"answers":[227],"language":[232],"subtracting":[235],"total":[239],"via":[242],"counterfactual":[243],"reasoning.":[244],"Experimental":[245],"results":[246],"certify":[247],"effectiveness":[249],"our":[251],"method":[252],"prevailing":[255],"Visdial":[256,259],"v0.9":[257],"v1.0":[260],"datasets.":[261]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3}],"updated_date":"2026-08-03T07:22:36.454288","created_date":"2025-10-10T00:00:00"}