{"id":"https://openalex.org/W4402979950","doi":"https://doi.org/10.1109/icme57554.2024.10688129","title":"Overcoming Language Priors for Visual Question Answering Based on Knowledge Distillation","display_name":"Overcoming Language Priors for Visual Question Answering Based on Knowledge Distillation","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402979950","doi":"https://doi.org/10.1109/icme57554.2024.10688129"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10688129","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10688129","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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/A5066682332","display_name":"Daowan Peng","orcid":"https://orcid.org/0000-0001-5208-3811"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daowan Peng","raw_affiliation_strings":["Huazhong University of Science and Technology,CCIIP Lab, School of Computer Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,CCIIP Lab, School of Computer Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100323773","display_name":"Wei Wei","orcid":"https://orcid.org/0000-0002-8751-9205"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Wei","raw_affiliation_strings":["Huazhong University of Science and Technology,CCIIP Lab, School of Computer Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,CCIIP Lab, School of Computer Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":0.2629,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55005586,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9965000152587891,"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":0.9965000152587891,"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/T12031","display_name":"Speech and dialogue systems","score":0.9592999815940857,"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/T13382","display_name":"Robotics and Automated Systems","score":0.9114000201225281,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.8535082340240479},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6887387633323669},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.6881770491600037},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5242912173271179},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5053659081459045},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49173977971076965},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.12764963507652283}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.8535082340240479},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6887387633323669},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.6881770491600037},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5242912173271179},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5053659081459045},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49173977971076965},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.12764963507652283},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10688129","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10688129","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5}],"awards":[],"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":35,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2560730294","https://openalex.org/W2745461083","https://openalex.org/W2963644680","https://openalex.org/W2963954913","https://openalex.org/W2970019270","https://openalex.org/W2970231061","https://openalex.org/W2983256121","https://openalex.org/W2997072136","https://openalex.org/W3034287395","https://openalex.org/W3034756453","https://openalex.org/W3035517717","https://openalex.org/W3099884329","https://openalex.org/W3104788521","https://openalex.org/W3170243808","https://openalex.org/W3172438304","https://openalex.org/W3177934633","https://openalex.org/W3192587235","https://openalex.org/W3199231060","https://openalex.org/W3202778561","https://openalex.org/W3204222276","https://openalex.org/W3204924011","https://openalex.org/W3216470601","https://openalex.org/W4283258232","https://openalex.org/W4285414077","https://openalex.org/W4285605365","https://openalex.org/W4312457137","https://openalex.org/W4320003009","https://openalex.org/W4385571516","https://openalex.org/W4385571918","https://openalex.org/W4385768191","https://openalex.org/W4386065611","https://openalex.org/W4386066382","https://openalex.org/W4386160115","https://openalex.org/W4393160564"],"related_works":["https://openalex.org/W2580650124","https://openalex.org/W4386190339","https://openalex.org/W2968424575","https://openalex.org/W3142333283","https://openalex.org/W3122088529","https://openalex.org/W2384605597","https://openalex.org/W3041320102","https://openalex.org/W2111669074","https://openalex.org/W2085259108","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Previous":[0],"studies":[1],"have":[2],"pointed":[3],"out":[4],"that":[5,99,130],"visual":[6],"question":[7],"answering":[8],"(VQA)":[9],"models":[10],"are":[11],"prone":[12],"to":[13,56,79,82,115],"relying":[14],"on":[15,27,146],"language":[16],"priors":[17],"for":[18],"answer":[19],"predictions.":[20],"In":[21,43],"this":[22,44],"context,":[23],"predictions":[24],"often":[25],"depend":[26],"linguistic":[28],"shortcuts":[29],"rather":[30],"than":[31],"a":[32,48,74,92],"comprehensive":[33],"grasp":[34],"of":[35,103,124],"multimodal":[36],"knowledge,":[37],"which":[38,90],"diminishes":[39],"their":[40],"generalization":[41],"ability.":[42],"paper,":[45],"we":[46,107],"propose":[47],"novel":[49],"method,":[50],"namely,":[51],"KDAR,":[52],"leveraging":[53],"knowledge":[54],"distillation":[55],"address":[57],"the":[58,62,66,83,101,122,147],"prior-dependency":[59],"dilemmas":[60],"within":[61],"VQA":[63],"task.":[64],"Specifically,":[65],"regularization":[67,93],"effect":[68],"facilitated":[69],"by":[70,119],"soft":[71,88],"labels":[72],"from":[73],"well-trained":[75],"teacher":[76],"is":[77],"employed":[78],"penalize":[80],"overfitting":[81],"most":[84],"common":[85],"answers.":[86,105],"The":[87],"labels,":[89],"serve":[91],"role,":[94],"also":[95],"provide":[96],"semantic":[97],"guidance":[98],"narrows":[100],"range":[102],"candidate":[104],"Additionally,":[106],"design":[108],"an":[109],"adaptive":[110],"samplewise":[111],"reweighting":[112],"learning":[113],"strategy":[114],"further":[116],"mitigate":[117],"bias":[118],"dynamically":[120],"adjusting":[121],"importance":[123],"each":[125],"sample.":[126],"Experimental":[127],"results":[128],"demonstrate":[129],"our":[131],"method":[132,142],"enhances":[133],"performance":[134,145],"in":[135],"both":[136],"OOD":[137],"and":[138],"IID":[139],"settings.":[140],"Our":[141],"achieves":[143],"state-of-the-art":[144,155],"VQA-CPv2":[148],"out-of-distribution":[149],"(OOD)":[150],"benchmark,":[151],"significantly":[152],"outperforming":[153],"previous":[154],"approaches.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}