{"id":"https://openalex.org/W4403780659","doi":"https://doi.org/10.1145/3664647.3681597","title":"Few-Shot Multimodal Explanation for Visual Question Answering","display_name":"Few-Shot Multimodal Explanation for Visual Question Answering","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403780659","doi":"https://doi.org/10.1145/3664647.3681597"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681597","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3681597","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3664647.3681597","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068536664","display_name":"Dizhan Xue","orcid":"https://orcid.org/0000-0002-0173-1556"},"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":true,"raw_author_name":"Dizhan Xue","raw_affiliation_strings":["MAIS, Institute of Automation, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"MAIS, Institute of Automation, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073601707","display_name":"Shengsheng Qian","orcid":"https://orcid.org/0000-0001-9488-2208"},"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":"Shengsheng Qian","raw_affiliation_strings":["MAIS, Institute of Automation, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"MAIS, Institute of Automation, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022636178","display_name":"Changsheng Xu","orcid":"https://orcid.org/0000-0001-8343-9665"},"institutions":[{"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"]},{"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":"Changsheng Xu","raw_affiliation_strings":["MAIS, Institute of Automation, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"MAIS, Institute of Automation, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5068536664"],"corresponding_institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.2616,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55399704,"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":"1875","last_page":"1884"},"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":0.9975000023841858,"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":0.9927999973297119,"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/question-answering","display_name":"Question answering","score":0.7608634233474731},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7289043664932251},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5771090388298035},{"id":"https://openalex.org/keywords/one-shot","display_name":"One shot","score":0.5479079484939575},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4607348144054413},{"id":"https://openalex.org/keywords/multimodal-interaction","display_name":"Multimodal interaction","score":0.4165692627429962},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3759196996688843},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07264453172683716},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.0467873215675354}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7608634233474731},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7289043664932251},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5771090388298035},{"id":"https://openalex.org/C2992734406","wikidata":"https://www.wikidata.org/wiki/Q413267","display_name":"One shot","level":2,"score":0.5479079484939575},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4607348144054413},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.4165692627429962},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3759196996688843},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07264453172683716},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0467873215675354},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"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:10.1145/3664647.3681597","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3681597","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3664647.3681597","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3681597","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1593271688","https://openalex.org/W1933349210","https://openalex.org/W1956340063","https://openalex.org/W1972945478","https://openalex.org/W2277195237","https://openalex.org/W2600463316","https://openalex.org/W2745461083","https://openalex.org/W2766605158","https://openalex.org/W2913550731","https://openalex.org/W2913668833","https://openalex.org/W2958089299","https://openalex.org/W2962884579","https://openalex.org/W2963115613","https://openalex.org/W2963518342","https://openalex.org/W2963609017","https://openalex.org/W2963991868","https://openalex.org/W2964061310","https://openalex.org/W2964303913","https://openalex.org/W2970231061","https://openalex.org/W2973009097","https://openalex.org/W3021007069","https://openalex.org/W3176349206","https://openalex.org/W3176709420","https://openalex.org/W3187176672","https://openalex.org/W3205249428","https://openalex.org/W4212774754","https://openalex.org/W4237040408","https://openalex.org/W4245255589","https://openalex.org/W4283837671","https://openalex.org/W4294559022","https://openalex.org/W4296605665","https://openalex.org/W4304092489","https://openalex.org/W4312695920","https://openalex.org/W4313026212","https://openalex.org/W4319163914","https://openalex.org/W4367047111","https://openalex.org/W4386065691","https://openalex.org/W4389518632","https://openalex.org/W4390872352","https://openalex.org/W4390872747","https://openalex.org/W4390874280","https://openalex.org/W4391216149","https://openalex.org/W4393156804","https://openalex.org/W4396753382","https://openalex.org/W4400530983"],"related_works":["https://openalex.org/W2497720472","https://openalex.org/W4292659306","https://openalex.org/W3044321615","https://openalex.org/W2806221744","https://openalex.org/W2035104213","https://openalex.org/W2326937258","https://openalex.org/W394267150","https://openalex.org/W2773965352","https://openalex.org/W4294892107","https://openalex.org/W2357748469"],"abstract_inverted_index":{"A":[0],"key":[1],"object":[2],"in":[3,115],"eXplainable":[4],"Artificial":[5],"Intelligence":[6],"(XAI)":[7],"is":[8,128],"to":[9,20,36,47,79,165,190],"create":[10],"intelligent":[11],"systems":[12],"capable":[13],"of":[14,30,84,104,124,218],"reasoning":[15,87],"and":[16,33,54,67,108,119,141,168,186,207,225],"explaining":[17],"real-world":[18],"data":[19,53,226],"facilitate":[21,37,113],"reliable":[22],"decision-making.":[23],"Recent":[24],"studies":[25],"have":[26],"acknowledged":[27],"the":[28,81,85,122,129,216],"importance":[29],"providing":[31],"user-friendly":[32],"verifiable":[34],"explanations":[35,136,171],"trustworthy":[38],"Visual":[39],"Question":[40],"Answering":[41],"(VQA)":[42],"systems.":[43],"This":[44],"paper":[45],"aims":[46,78],"promote":[48],"explainable":[49],"VQA":[50,74],"from":[51,181],"both":[52,116],"method":[55,155,220],"perspectives.":[56],"First,":[57],"we":[58,147],"propose":[59,148],"a":[60,68,149],"new":[61,69],"Standard":[62],"Multimodal":[63,71,151],"Explanation":[64,72],"(SME)":[65],"dataset":[66,99,132,214],"Few-Shot":[70],"for":[73,89,172,221],"(FS-MEVQA)":[75],"task,":[76],"which":[77,111],"generate":[80,169],"multimodal":[82,109,162,170,179],"explanation":[83,180],"underlying":[86],"process":[88],"solving":[90],"visual":[91,143,173,204,208],"questions":[92],"with":[93,133,161],"few":[94],"training":[95,184],"samples.":[96,195],"Our":[97,175,223],"SME":[98,213],"includes":[100],"1,028,230":[101],"samples":[102,185],"composed":[103],"questions,":[105],"images,":[106],"answers,":[107],"explanations,":[110],"can":[112,177],"research":[114],"traditional":[117],"MEVQA":[118],"FS-MEVQA.":[120,222],"To":[121],"best":[123],"our":[125,212,219],"knowledge,":[126],"this":[127],"first":[130],"large-scale":[131],"joint":[134],"language-vision":[135],"based":[137,156],"on":[138,157,193,211],"standard":[139],"English":[140],"additional":[142],"grounding":[144],"tokens.":[145],"Second,":[146],"training-free":[150],"Explaining":[152],"Agent":[153],"(MEAgent)":[154],"an":[158],"LLM":[159],"agent":[160],"open-world":[163,188],"tools":[164],"infer":[166],"answers":[167],"questions.":[174],"MEAgent":[176],"learn":[178],"merely":[182],"N(=16)":[183],"leverage":[187],"abilities":[189],"perform":[191],"FS-MEVQA":[192],"test":[194],"Comprehensive":[196],"experimental":[197],"results":[198],"evaluated":[199],"by":[200],"language":[201],"quality":[202],"metrics,":[203],"detection":[205],"metric,":[206],"attribution":[209],"metrics":[210],"indicate":[215],"superiority":[217],"code":[224],"are":[227],"available":[228],"at":[229],"https://github.com/LivXue/FS-MEVQA.":[230]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-02-27T16:54:17.756197","created_date":"2025-10-10T00:00:00"}