{"id":"https://openalex.org/W4383337770","doi":"https://doi.org/10.1109/tip.2023.3286259","title":"Joint Answering and Explanation for Visual Commonsense Reasoning","display_name":"Joint Answering and Explanation for Visual Commonsense Reasoning","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4383337770","doi":"https://doi.org/10.1109/tip.2023.3286259","pmid":"https://pubmed.ncbi.nlm.nih.gov/37410654"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2023.3286259","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2023.3286259","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5001893388","display_name":"Zhenyang Li","orcid":"https://orcid.org/0000-0002-4694-1231"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhenyang Li","raw_affiliation_strings":["School of Computer Science and Technology, Shandong University, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0002-4694-1231","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I80143920"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054313646","display_name":"Yangyang Guo","orcid":"https://orcid.org/0000-0001-8691-5372"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yangyang Guo","raw_affiliation_strings":["School of Computing, National University of Singapore, Queenstown, Singapore","National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-8691-5372","affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Queenstown, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053685797","display_name":"Kejie Wang","orcid":"https://orcid.org/0000-0003-0595-6856"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kejie Wang","raw_affiliation_strings":["School of Computer Science and Technology, Shandong University, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0003-0595-6856","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I80143920"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039731055","display_name":"Yinwei Wei","orcid":"https://orcid.org/0000-0003-1791-3159"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yinwei Wei","raw_affiliation_strings":["School of Computing, National University of Singapore, Queenstown, Singapore","National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-1791-3159","affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Queenstown, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038612499","display_name":"Liqiang Nie","orcid":"https://orcid.org/0000-0003-1476-0273"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liqiang Nie","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China","Harbin Institute of Technology, China"],"raw_orcid":"https://orcid.org/0000-0003-1476-0273","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016415049","display_name":"Mohan Kankanhalli","orcid":"https://orcid.org/0000-0002-4846-2015"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Mohan Kankanhalli","raw_affiliation_strings":["School of Computing, National University of Singapore, Queenstown, Singapore","National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-4846-2015","affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Queenstown, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5001893388"],"corresponding_institution_ids":["https://openalex.org/I80143920"],"apc_list":null,"apc_paid":null,"fwci":3.0614,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.93197776,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"32","issue":null,"first_page":"3836","last_page":"3846"},"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":0.9933000206947327,"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":0.9915000200271606,"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/question-answering","display_name":"Question answering","score":0.914082407951355},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7978577017784119},{"id":"https://openalex.org/keywords/commonsense-reasoning","display_name":"Commonsense reasoning","score":0.7933554649353027},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7634656429290771},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6327924132347107},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.48061317205429077},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4619908630847931},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.453841894865036},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4112801253795624},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38018617033958435},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33833009004592896}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.914082407951355},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7978577017784119},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.7933554649353027},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7634656429290771},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6327924132347107},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.48061317205429077},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4619908630847931},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.453841894865036},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4112801253795624},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38018617033958435},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33833009004592896},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2023.3286259","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2023.3286259","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},{"id":"pmid:37410654","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37410654","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7231895066","display_name":null,"funder_award_id":"U1936203","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2142192571","https://openalex.org/W2471094925","https://openalex.org/W2561715562","https://openalex.org/W2739879705","https://openalex.org/W2745461083","https://openalex.org/W2886641317","https://openalex.org/W2914699769","https://openalex.org/W2947312908","https://openalex.org/W2962749469","https://openalex.org/W2962858109","https://openalex.org/W2962884579","https://openalex.org/W2963115613","https://openalex.org/W2963150697","https://openalex.org/W2963397674","https://openalex.org/W2963609017","https://openalex.org/W2963717374","https://openalex.org/W2963991868","https://openalex.org/W2964118342","https://openalex.org/W2964138343","https://openalex.org/W2964303913","https://openalex.org/W2973009097","https://openalex.org/W2981819252","https://openalex.org/W2983256121","https://openalex.org/W2998014937","https://openalex.org/W3000346474","https://openalex.org/W3034727271","https://openalex.org/W3090449556","https://openalex.org/W3091093673","https://openalex.org/W3160447289","https://openalex.org/W3173909648","https://openalex.org/W3176896951","https://openalex.org/W3185066916","https://openalex.org/W3192587235","https://openalex.org/W3197813359","https://openalex.org/W3206218097","https://openalex.org/W3216470601","https://openalex.org/W4200475325","https://openalex.org/W4312864639","https://openalex.org/W6637551013","https://openalex.org/W6638523607","https://openalex.org/W6679909955","https://openalex.org/W6728881024","https://openalex.org/W6730179637","https://openalex.org/W6766904570","https://openalex.org/W6767194493","https://openalex.org/W6767211374","https://openalex.org/W6767362881","https://openalex.org/W6769264886"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W4313191056","https://openalex.org/W4383337770","https://openalex.org/W4225546813","https://openalex.org/W4320086306"],"abstract_inverted_index":{"Visual":[0,10],"Commonsense":[1],"Reasoning":[2],"(VCR),":[3],"deemed":[4],"as":[5,155],"one":[6],"challenging":[7],"extension":[8],"of":[9,43,56,113,149,209],"Question":[11],"Answering":[12],"(VQA),":[13],"endeavors":[14],"to":[15,97,133,158,172],"pursue":[16],"a":[17,29,41,66,79,127,150,156],"higher-level":[18],"visual":[19,98],"comprehension.":[20],"VCR":[21,44,72],"includes":[22],"two":[23,63,74,161],"complementary":[24],"processes:":[25],"question":[26,85,136],"answering":[27,36,86,137],"over":[28],"given":[30],"image":[31],"and":[32,69,87,117,138,177,201],"rationale":[33,88,139],"inference":[34,89,140],"for":[35],"explanation.":[37],"Over":[38],"the":[39,51,62,81,135,147,160,173,182,188,207],"years,":[40],"variety":[42],"methods":[45],"have":[46],"pushed":[47],"more":[48],"advancements":[49],"on":[50,121,181],"benchmark":[52,183],"dataset.":[53,184],"Despite":[54],"significance":[55],"these":[57,196],"methods,":[58],"they":[59],"often":[60],"treat":[61],"processes":[64,210],"in":[65,111,146,187],"separate":[67],"manner":[68],"hence":[70],"decompose":[71],"into":[73],"irrelevant":[75],"VQA":[76],"instances.":[77],"As":[78,185],"result,":[80],"pivotal":[82],"connection":[83],"between":[84],"is":[90,167],"broken,":[91],"rendering":[92],"existing":[93,174],"efforts":[94],"less":[95],"faithful":[96],"reasoning.":[99],"To":[100],"empirically":[101],"study":[102],"this":[103],"issue,":[104],"we":[105,124,169],"perform":[106],"some":[107],"in-depth":[108],"empirical":[109],"explorations":[110],"terms":[112],"both":[114],"language":[115],"shortcuts":[116],"generalization":[118],"capability.":[119],"Based":[120],"our":[122,165,194],"findings,":[123],"then":[125],"propose":[126],"plug-and-play":[128],"knowledge":[129],"distillation":[130],"enhanced":[131],"framework":[132,166],"couple":[134],"processes.":[141,162],"The":[142],"key":[143],"contribution":[144],"lies":[145],"introduction":[148],"new":[151],"branch,":[152],"which":[153],"serves":[154],"relay":[157],"bridge":[159],"Given":[163],"that":[164],"model-agnostic,":[168],"apply":[170],"it":[171],"popular":[175],"baselines":[176,197],"validate":[178],"its":[179],"effectiveness":[180],"demonstrated":[186],"experimental":[189],"results,":[190],"when":[191],"equipped":[192],"with":[193],"method,":[195],"all":[198],"achieve":[199],"consistent":[200],"significant":[202],"performance":[203],"improvements,":[204],"evidently":[205],"verifying":[206],"viability":[208],"coupling.":[211]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}