{"id":"https://openalex.org/W3216470601","doi":"https://doi.org/10.1109/tip.2021.3128322","title":"Loss Re-Scaling VQA: Revisiting the Language Prior Problem From a Class-Imbalance View","display_name":"Loss Re-Scaling VQA: Revisiting the Language Prior Problem From a Class-Imbalance View","publication_year":2021,"publication_date":"2021-11-30","ids":{"openalex":"https://openalex.org/W3216470601","doi":"https://doi.org/10.1109/tip.2021.3128322","mag":"3216470601","pmid":"https://pubmed.ncbi.nlm.nih.gov/34847029"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2021.3128322","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2021.3128322","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":null,"display_name":"Yangyang Guo","orcid":"https://orcid.org/0000-0001-8691-5372"},"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":"Yangyang Guo","raw_affiliation_strings":["School of Computer Science and Technology, Shandong University, Qingdao, China"],"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":null,"display_name":"Liqiang Nie","orcid":"https://orcid.org/0000-0003-1476-0273"},"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":"Liqiang Nie","raw_affiliation_strings":["School of Computer Science and Technology, Shandong University, Qingdao, China"],"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":null,"display_name":"Zhiyong Cheng","orcid":"https://orcid.org/0000-0003-1109-5028"},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]},{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Cheng","raw_affiliation_strings":["Shandong Artificial Intelligence Institute, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China"],"affiliations":[{"raw_affiliation_string":"Shandong Artificial Intelligence Institute, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China","institution_ids":["https://openalex.org/I4210142748","https://openalex.org/I152269853"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qi Tian","orcid":"https://orcid.org/0000-0002-7252-5047"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Tian","raw_affiliation_strings":["Huawei Cloud & AI, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Huawei Cloud & AI, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":null,"display_name":"Min Zhang","orcid":"https://orcid.org/0000-0002-3895-5510"},"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":"Min Zhang","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I80143920"],"apc_list":null,"apc_paid":null,"fwci":4.5637,"has_fulltext":false,"cited_by_count":64,"citation_normalized_percentile":{"value":0.95925028,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"31","issue":null,"first_page":"227","last_page":"238"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9854999780654907,"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":0.9854999780654907,"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":0.006300000008195639,"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/T10028","display_name":"Topic Modeling","score":0.0012000000569969416,"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/perplexity","display_name":"Perplexity","score":0.8948000073432922},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6879000067710876},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6136999726295471},{"id":"https://openalex.org/keywords/interpretation","display_name":"Interpretation (philosophy)","score":0.6118999719619751},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.602400004863739},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5658000111579895},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5437999963760376},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.539900004863739},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.498199999332428}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.8948000073432922},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7534000277519226},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6879000067710876},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6496999859809875},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6136999726295471},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.6118999719619751},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.602400004863739},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5658000111579895},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5454999804496765},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5437999963760376},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.539900004863739},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.498199999332428},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4465000033378601},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4156999886035919},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4018999934196472},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.37130001187324524},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.36980000138282776},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.32820001244544983},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.3224000036716461},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.31450000405311584},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.29490000009536743},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.29260000586509705},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2531000077724457},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.2529999911785126},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2021.3128322","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2021.3128322","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:34847029","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34847029","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/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6058138561","display_name":null,"funder_award_id":", No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"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":52,"referenced_works":["https://openalex.org/W102708294","https://openalex.org/W1933349210","https://openalex.org/W2016089260","https://openalex.org/W2142192571","https://openalex.org/W2148143831","https://openalex.org/W2157331557","https://openalex.org/W2194775991","https://openalex.org/W2560730294","https://openalex.org/W2561715562","https://openalex.org/W2735159761","https://openalex.org/W2741903908","https://openalex.org/W2745461083","https://openalex.org/W2884326683","https://openalex.org/W2885380450","https://openalex.org/W2897905870","https://openalex.org/W2918888132","https://openalex.org/W2944668088","https://openalex.org/W2957105406","https://openalex.org/W2962858109","https://openalex.org/W2962895364","https://openalex.org/W2962933664","https://openalex.org/W2963150162","https://openalex.org/W2963351448","https://openalex.org/W2963383024","https://openalex.org/W2963398599","https://openalex.org/W2963541336","https://openalex.org/W2963890019","https://openalex.org/W2963954913","https://openalex.org/W2964118342","https://openalex.org/W2964138343","https://openalex.org/W2964303913","https://openalex.org/W2970231061","https://openalex.org/W2983256121","https://openalex.org/W2997072136","https://openalex.org/W3033514332","https://openalex.org/W3034287395","https://openalex.org/W3035517717","https://openalex.org/W3037773948","https://openalex.org/W3039115681","https://openalex.org/W3039204154","https://openalex.org/W3041062282","https://openalex.org/W3196196682","https://openalex.org/W6620707391","https://openalex.org/W6680202767","https://openalex.org/W6719057275","https://openalex.org/W6726946684","https://openalex.org/W6736769356","https://openalex.org/W6754733129","https://openalex.org/W6763000187","https://openalex.org/W6764756247","https://openalex.org/W6768920361","https://openalex.org/W6774460212"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"studies":[1],"have":[2,69],"pointed":[3],"out":[4],"that":[5],"many":[6],"well-developed":[7],"Visual":[8],"Question":[9],"Answering":[10],"(VQA)":[11],"models":[12],"are":[13],"heavily":[14],"affected":[15],"by":[16],"the":[17,28,52,89,116,134,143,151,159,181,205,211,223,240,243],"language":[18,117],"prior":[19,118],"problem.":[20,108],"It":[21,82,155],"refers":[22],"to":[23,57,72,92,114,163,171,196,200,204],"making":[24],"predictions":[25],"based":[26],"on":[27,50,63,226,248],"co-occurrence":[29],"pattern":[30],"between":[31],"textual":[32],"questions":[33],"and":[34,77,139,222,257],"answers":[35,141],"instead":[36],"of":[37,136,242],"reasoning":[38],"upon":[39,185],"visual":[40,53],"contents.":[41],"To":[42],"tackle":[43],"this":[44,59,106,110,186],"problem,":[45],"most":[46],"existing":[47],"methods":[48],"focus":[49],"strengthening":[51],"feature":[54],"learning":[55],"capability":[56],"reduce":[58],"text":[60],"shortcut":[61],"influence":[62],"model":[64,101,161],"decisions.":[65],"However,":[66],"few":[67],"efforts":[68],"been":[70],"devoted":[71],"analyzing":[73],"its":[74,233],"inherent":[75],"cause":[76],"providing":[78],"an":[79],"explicit":[80],"interpretation.":[81],"thus":[83],"lacks":[84],"a":[85,96,123,129,165,172,191],"good":[86],"guidance":[87],"for":[88,209],"research":[90],"community":[91],"move":[93],"forward":[94],"in":[95,100,120,180],"purposeful":[97],"way,":[98],"resulting":[99],"construction":[102],"perplexity":[103],"towards":[104],"overcoming":[105],"non-trivial":[107],"In":[109,235],"paper,":[111],"we":[112,127,188,237],"propose":[113,190],"interpret":[115],"problem":[119],"VQA":[121,160],"from":[122,142],"class-imbalance":[124],"view.":[125],"Concretely,":[126],"design":[128],"novel":[130,192],"interpretation":[131,246],"scheme":[132,247],"whereby":[133],"loss":[135,193],"mis-predicted":[137],"frequent":[138,166],"sparse":[140,179],"same":[144],"question":[145,174],"type":[146],"is":[147,178],"distinctly":[148],"exhibited":[149],"during":[150],"late":[152],"training":[153,182,206],"phase.":[154],"explicitly":[156],"reveals":[157],"why":[158],"tends":[162],"produce":[164],"yet":[167],"obviously":[168],"wrong":[169],"answer,":[170],"given":[173],"whose":[175],"right":[176],"answer":[177,202],"set.":[183],"Based":[184],"observation,":[187],"further":[189],"re-scaling":[194],"approach":[195,217],"assign":[197],"different":[198],"weights":[199],"each":[201],"according":[203],"data":[207],"statistics":[208],"estimating":[210],"final":[212],"loss.":[213],"We":[214],"apply":[215],"our":[216],"into":[218],"six":[219],"strong":[220],"baselines":[221],"experimental":[224],"results":[225],"two":[227],"VQA-CP":[228],"benchmark":[229],"datasets":[230],"evidently":[231],"demonstrate":[232],"effectiveness.":[234],"addition,":[236],"also":[238],"justify":[239],"validity":[241],"class":[244],"imbalance":[245],"other":[249],"computer":[250],"vision":[251],"tasks,":[252],"such":[253],"as":[254],"face":[255],"recognition":[256],"image":[258],"classification.":[259]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":20},{"year":2023,"cited_by_count":22},{"year":2022,"cited_by_count":5}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2021-12-06T00:00:00"}