{"id":"https://openalex.org/W2897870704","doi":"https://doi.org/10.1145/3240508.3240527","title":"Fast Parameter Adaptation for Few-shot Image Captioning and Visual Question Answering","display_name":"Fast Parameter Adaptation for Few-shot Image Captioning and Visual Question Answering","publication_year":2018,"publication_date":"2018-10-15","ids":{"openalex":"https://openalex.org/W2897870704","doi":"https://doi.org/10.1145/3240508.3240527","mag":"2897870704"},"language":"en","primary_location":{"id":"doi:10.1145/3240508.3240527","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3240508.3240527","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM international conference on Multimedia","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/A5069837273","display_name":"Xuanyi Dong","orcid":"https://orcid.org/0000-0001-9272-1590"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xuanyi Dong","raw_affiliation_strings":["Southern University of Science and Technology & University of Technology Sydney, Sydney, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology & University of Technology Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043617790","display_name":"Linchao Zhu","orcid":"https://orcid.org/0000-0002-4093-7557"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Linchao Zhu","raw_affiliation_strings":["Southern University of Science and Technology & University of Technology Sydney, Sydney, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology & University of Technology Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104028892","display_name":"De Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I2800372957","display_name":"China Electronics Technology Group Corporation","ror":"https://ror.org/0098hst83","country_code":"CN","type":"company","lineage":["https://openalex.org/I2800372957"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"De Zhang","raw_affiliation_strings":["China Electronics Technology Group Corporation, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Electronics Technology Group Corporation, Beijing, China","institution_ids":["https://openalex.org/I2800372957"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005421447","display_name":"Yi Yang","orcid":"https://orcid.org/0000-0002-0512-880X"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yi Yang","raw_affiliation_strings":["Southern University of Science and Technology & University of Technology Sydney, Sydney, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology & University of Technology Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004882141","display_name":"Fei Wu","orcid":"https://orcid.org/0000-0003-2139-8807"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Wu","raw_affiliation_strings":["Zhejiang University, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"54","last_page":"62"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9958999752998352,"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":0.9944999814033508,"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/closed-captioning","display_name":"Closed captioning","score":0.9548658132553101},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.8159372210502625},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7978399991989136},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.6989673376083374},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6551944613456726},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5927020311355591},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.541313648223877},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5334563255310059},{"id":"https://openalex.org/keywords/one-shot","display_name":"One shot","score":0.4586472809314728},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.445247083902359},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4365774691104889},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4135608673095703},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39697736501693726},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36952346563339233},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3374847173690796}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9548658132553101},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.8159372210502625},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7978399991989136},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6989673376083374},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6551944613456726},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5927020311355591},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.541313648223877},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5334563255310059},{"id":"https://openalex.org/C2992734406","wikidata":"https://www.wikidata.org/wiki/Q413267","display_name":"One shot","level":2,"score":0.4586472809314728},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.445247083902359},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4365774691104889},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4135608673095703},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39697736501693726},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36952346563339233},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3374847173690796},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"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},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3240508.3240527","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3240508.3240527","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM international conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:opus.lib.uts.edu.au:10453/131494","is_oa":false,"landing_page_url":"http://hdl.handle.net/10453/131494","pdf_url":null,"source":{"id":"https://openalex.org/S4306401357","display_name":"UTS ePRESS (University of Technology Sydney)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114017466","host_organization_name":"University of Technology Sydney","host_organization_lineage":["https://openalex.org/I114017466"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceeding"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W8316075","https://openalex.org/W1514535095","https://openalex.org/W1677182931","https://openalex.org/W1861492603","https://openalex.org/W1897761818","https://openalex.org/W1933349210","https://openalex.org/W1969616664","https://openalex.org/W1980287119","https://openalex.org/W2064675550","https://openalex.org/W2139380585","https://openalex.org/W2157331557","https://openalex.org/W2173180041","https://openalex.org/W2194775991","https://openalex.org/W2202226326","https://openalex.org/W2277195237","https://openalex.org/W2302086703","https://openalex.org/W2550143307","https://openalex.org/W2560730294","https://openalex.org/W2561272927","https://openalex.org/W2601450892","https://openalex.org/W2601529995","https://openalex.org/W2603777577","https://openalex.org/W2604998962","https://openalex.org/W2605963463","https://openalex.org/W2618530766","https://openalex.org/W2753160622","https://openalex.org/W2760103357","https://openalex.org/W2765569127","https://openalex.org/W2787119853","https://openalex.org/W2788159735","https://openalex.org/W2792764867","https://openalex.org/W2797733588","https://openalex.org/W2798730128","https://openalex.org/W2799185441","https://openalex.org/W2949218037","https://openalex.org/W2950170241","https://openalex.org/W2951775809","https://openalex.org/W2952342379","https://openalex.org/W2962749469","https://openalex.org/W2962779575","https://openalex.org/W2963010714","https://openalex.org/W2963175879","https://openalex.org/W2963191264","https://openalex.org/W2963224792","https://openalex.org/W2963289251","https://openalex.org/W2963341924","https://openalex.org/W2963446712","https://openalex.org/W2963954913","https://openalex.org/W2964121744","https://openalex.org/W2964138017","https://openalex.org/W3037856073","https://openalex.org/W3100115227"],"related_works":["https://openalex.org/W2497720472","https://openalex.org/W4292659306","https://openalex.org/W3044321615","https://openalex.org/W4294892107","https://openalex.org/W2806221744","https://openalex.org/W2326937258","https://openalex.org/W394267150","https://openalex.org/W2357748469","https://openalex.org/W2392917037","https://openalex.org/W2046675961"],"abstract_inverted_index":{"\u00a9":[0],"2018":[1],"Association":[2],"for":[3,48,104,137],"Computing":[4],"Machinery.":[5],"Given":[6],"only":[7,66,75],"a":[8,30,36,76,119,143,150,157,165],"few":[9,77,120,171],"image-text":[10,140],"pairs,":[11],"humans":[12],"can":[13,155],"learn":[14,111],"to":[15,34,40,52,55,110,163,170,199],"detect":[16],"semantic":[17],"concepts":[18],"and":[19,68,90,115,189,217,234],"describe":[20],"the":[21,42,49,56,61,96,138,176,191,201,205,215,220],"content.":[22],"For":[23],"machine":[24],"learning":[25,130],"algorithms,":[26],"they":[27],"usually":[28],"require":[29],"lot":[31],"of":[32,146,160,204],"data":[33,117,179],"train":[35],"deep":[37],"neural":[38],"network":[39],"solve":[41],"problem.":[43],"However,":[44],"it":[45],"is":[46],"challenging":[47],"existing":[50],"systems":[51],"generalize":[53],"well":[54],"few-shot":[57,97,174,231],"multi-modal":[58,85],"scenario,":[59],"because":[60],"learner":[62,141],"should":[63],"understand":[64],"not":[65],"images":[67],"texts":[69],"but":[70],"also":[71],"their":[72],"relationships":[73],"from":[74,142],"examples.":[78,121,172],"In":[79,122,173,209],"this":[80,210],"paper,":[81],"we":[82],"tackle":[83],"two":[84,126],"problems,":[86],"i.e.,":[87],"image":[88,114,232],"captioning":[89,233],"visual":[91],"question":[92],"answering":[93],"(VQA),":[94],"in":[95,184],"setting.":[98],"We":[99],"propose":[100],"Fast":[101,129],"Parameter":[102],"Adaptation":[103],"Image-Text":[105],"Modeling":[106],"(FPAIT)":[107],"that":[108],"learns":[109,133],"jointly":[112],"understanding":[113],"text":[116],"by":[118],"practice,":[123],"FPAIT":[124,132,154,194,212,225],"has":[125],"benefits.":[127],"(1)":[128],"ability.":[131],"proper":[134],"initial":[135],"parameters":[136],"joint":[139],"large":[144,182],"number":[145,159],"different":[147],"tasks.":[148],"When":[149],"new":[151],"task":[152],"comes,":[153],"use":[156],"small":[158,177,206],"gradient":[161],"steps":[162],"achieve":[164],"good":[166],"performance.":[167,193],"(2)":[168],"Robust":[169],"tasks,":[175],"training":[178,207],"will":[180],"introduce":[181],"biases":[183,221],"Convolutional":[185],"Neural":[186],"Networks":[187],"(CNN)":[188],"damage":[190],"learner's":[192],"leverages":[195],"dynamic":[196],"linear":[197],"transformations":[198],"alleviate":[200],"side":[202],"effects":[203],"set.":[208],"way,":[211],"flexibly":[213],"normalizes":[214],"features":[216],"thus":[218],"reduces":[219],"during":[222],"training.":[223],"Quantitatively,":[224],"achieves":[226],"superior":[227],"performance":[228],"on":[229],"both":[230],"VQA":[235],"benchmarks.":[236]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}