{"id":"https://openalex.org/W4400074770","doi":"https://doi.org/10.1145/3673902","title":"HCCL: Hierarchical Counterfactual Contrastive Learning for Robust Visual Question Answering","display_name":"HCCL: Hierarchical Counterfactual Contrastive Learning for Robust Visual Question Answering","publication_year":2024,"publication_date":"2024-06-27","ids":{"openalex":"https://openalex.org/W4400074770","doi":"https://doi.org/10.1145/3673902"},"language":"en","primary_location":{"id":"doi:10.1145/3673902","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1145/3673902","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","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/A5019338727","display_name":"Dongze Hao","orcid":"https://orcid.org/0000-0001-5504-1799"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"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":"Dongze Hao","raw_affiliation_strings":["Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, China and School of Artificial Intelligence, University of Chinese Academy of Sciences, China"],"raw_orcid":"https://orcid.org/0000-0001-5504-1799","affiliations":[{"raw_affiliation_string":"Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, China and School of Artificial Intelligence, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043193778","display_name":"Qunbo Wang","orcid":"https://orcid.org/0000-0002-5607-7854"},"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/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qunbo Wang","raw_affiliation_strings":["Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, China"],"raw_orcid":"https://orcid.org/0000-0002-5607-7854","affiliations":[{"raw_affiliation_string":"Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103047969","display_name":"Xinxin Zhu","orcid":"https://orcid.org/0000-0002-2142-5580"},"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/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinxin Zhu","raw_affiliation_strings":["Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, China"],"raw_orcid":"https://orcid.org/0000-0002-2142-5580","affiliations":[{"raw_affiliation_string":"Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108392430","display_name":"Jing Liu","orcid":"https://orcid.org/0000-0003-0903-9131"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"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":"Jing Liu","raw_affiliation_strings":["Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, China and School of Artificial Intelligence, University of Chinese Academy of Sciences, China"],"raw_orcid":"https://orcid.org/0000-0003-0903-9131","affiliations":[{"raw_affiliation_string":"Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, China and School of Artificial Intelligence, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210112150","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":0.4935,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.59296659,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"20","issue":"10","first_page":"1","last_page":"21"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9988999962806702,"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":0.9925000071525574,"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/group-b","display_name":"Group B","score":0.3657466769218445},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.2095930576324463},{"id":"https://openalex.org/keywords/internal-medicine","display_name":"Internal medicine","score":0.09734505414962769}],"concepts":[{"id":"https://openalex.org/C2777785397","wikidata":"https://www.wikidata.org/wiki/Q492194","display_name":"Group B","level":2,"score":0.3657466769218445},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.2095930576324463},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.09734505414962769}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3673902","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1145/3673902","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8636683191","display_name":null,"funder_award_id":"62206279 and U21B2043","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":48,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W1933349210","https://openalex.org/W2250539671","https://openalex.org/W2277195237","https://openalex.org/W2560730294","https://openalex.org/W2597425697","https://openalex.org/W2745461083","https://openalex.org/W2747623286","https://openalex.org/W2913954081","https://openalex.org/W2914304175","https://openalex.org/W2916723116","https://openalex.org/W2955124656","https://openalex.org/W2962858109","https://openalex.org/W2962884579","https://openalex.org/W2963140463","https://openalex.org/W2963383024","https://openalex.org/W2963518342","https://openalex.org/W2963609017","https://openalex.org/W2963644680","https://openalex.org/W2963954913","https://openalex.org/W2964072591","https://openalex.org/W2964118342","https://openalex.org/W2970231061","https://openalex.org/W2983256121","https://openalex.org/W3026376263","https://openalex.org/W3035145964","https://openalex.org/W3035512383","https://openalex.org/W3035517717","https://openalex.org/W3035524453","https://openalex.org/W3035561630","https://openalex.org/W3080952252","https://openalex.org/W3094342158","https://openalex.org/W3099884329","https://openalex.org/W3103542727","https://openalex.org/W3104788521","https://openalex.org/W3106544837","https://openalex.org/W3110575265","https://openalex.org/W3174366544","https://openalex.org/W3177934633","https://openalex.org/W3202778561","https://openalex.org/W3204924011","https://openalex.org/W4213057961","https://openalex.org/W4214825151","https://openalex.org/W4297808394","https://openalex.org/W4312457137","https://openalex.org/W4385571516","https://openalex.org/W4385571918","https://openalex.org/W4386065611"],"related_works":["https://openalex.org/W1536372821","https://openalex.org/W2558446188","https://openalex.org/W2121556643","https://openalex.org/W4200103860","https://openalex.org/W2579083402","https://openalex.org/W2066096579","https://openalex.org/W1890492875","https://openalex.org/W2318761088","https://openalex.org/W2070137188","https://openalex.org/W2400914179"],"abstract_inverted_index":{"Despite":[0],"most":[1],"state-of-the-art":[2],"models":[3],"having":[4],"achieved":[5],"amazing":[6],"performance":[7],"in":[8,87,115,148,157,193,213,217],"Visual":[9],"Question":[10],"Answering":[11],"(VQA)":[12],",":[13],"they":[14],"usually":[15],"utilize":[16],"biases":[17,86,216],"to":[18,29,33,55,59,76,83,101,118,139,145,183],"answer":[19,161],"the":[20,31,35,56,61,64,70,78,85,112,141,149,166,171,185,197,215,221,224],"question.":[21],"Recently,":[22],"some":[23],"studies":[24],"synthesize":[25],"counterfactual":[26],"training":[27,57],"samples":[28,40,54,75,121,147,156],"help":[30],"model":[32,62,168],"mitigate":[34,77,84],"biases.":[36,79],"However,":[37],"these":[38,49],"synthetic":[39,53,74],"need":[41],"extra":[42,106],"annotations":[43],"and":[44,105,122,135,160,175,180,196,204],"often":[45],"contain":[46],"noises.":[47],"Moreover,":[48],"methods":[50],"simply":[51],"add":[52],"data":[58],"train":[60],"with":[63],"cross-entropy":[65],"loss,":[66],"which":[67,219],"cannot":[68],"make":[69,140],"best":[71],"use":[72],"of":[73,223],"In":[80,163],"this":[81,164],"article,":[82],"VQA":[88,167,201,225],"more":[89],"effectively,":[90],"we":[91],"propose":[92],"a":[93],"Hierarchical":[94],"Counterfactual":[95],"Contrastive":[96],"Learning":[97],"(HCCL)":[98],"method.":[99],"Firstly,":[100],"avoid":[102],"introducing":[103],"noises":[104],"annotations,":[107],"our":[108,131,209],"method":[109,132,189,210],"automatically":[110],"masks":[111],"unimportant":[113],"features":[114,174],"original":[116,142],"pairs":[117,126],"obtain":[119],"positive":[120,146],"create":[123],"mismatched":[124],"question-image":[125],"as":[127],"negative":[128,155],"samples.":[129],"Then":[130],"uses":[133],"feature-level":[134],"answer-level":[136],"contrastive":[137],"learning":[138],"sample":[143],"close":[144],"feature":[150,159],"space,":[151],"while":[152],"away":[153],"from":[154],"both":[158,178],"spaces.":[162],"way,":[165],"can":[169,190],"learn":[170],"robust":[172],"multimodal":[173],"focus":[176],"on":[177,200],"visual":[179],"language":[181],"information":[182],"produce":[184],"answer.":[186],"Our":[187],"HCCL":[188],"be":[191],"adopted":[192],"different":[194],"baselines,":[195],"experimental":[198],"results":[199],"v2,":[202],"VQA-CP,":[203],"GQA-OOD":[205],"datasets":[206],"show":[207],"that":[208],"is":[211],"effective":[212],"mitigating":[214],"VQA,":[218],"improves":[220],"robustness":[222],"model.":[226]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}