{"id":"https://openalex.org/W4303444943","doi":"https://doi.org/10.1145/3549555.3549585","title":"Retrieval-Augmented Transformer for Image Captioning","display_name":"Retrieval-Augmented Transformer for Image Captioning","publication_year":2022,"publication_date":"2022-09-14","ids":{"openalex":"https://openalex.org/W4303444943","doi":"https://doi.org/10.1145/3549555.3549585"},"language":"en","primary_location":{"id":"doi:10.1145/3549555.3549585","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3549555.3549585","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3549555.3549585","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Conference on Content-based Multimedia Indexing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3549555.3549585","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033144993","display_name":"Sara Sarto","orcid":"https://orcid.org/0000-0003-1057-3374"},"institutions":[{"id":"https://openalex.org/I122346577","display_name":"University of Modena and Reggio Emilia","ror":"https://ror.org/02d4c4y02","country_code":"IT","type":"education","lineage":["https://openalex.org/I122346577"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Sara Sarto","raw_affiliation_strings":["Department of Engineering, University of Modena and Reggio Emilia, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Engineering, University of Modena and Reggio Emilia, Italy","institution_ids":["https://openalex.org/I122346577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066519737","display_name":"Marcella Cornia","orcid":"https://orcid.org/0000-0001-9640-9385"},"institutions":[{"id":"https://openalex.org/I122346577","display_name":"University of Modena and Reggio Emilia","ror":"https://ror.org/02d4c4y02","country_code":"IT","type":"education","lineage":["https://openalex.org/I122346577"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marcella Cornia","raw_affiliation_strings":["Department of Education and Humanities, University of Modena and Reggio Emilia, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Education and Humanities, University of Modena and Reggio Emilia, Italy","institution_ids":["https://openalex.org/I122346577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048928616","display_name":"Lorenzo Baraldi","orcid":"https://orcid.org/0000-0001-5125-4957"},"institutions":[{"id":"https://openalex.org/I122346577","display_name":"University of Modena and Reggio Emilia","ror":"https://ror.org/02d4c4y02","country_code":"IT","type":"education","lineage":["https://openalex.org/I122346577"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Lorenzo Baraldi","raw_affiliation_strings":["Department of Engineering, University of Modena and Reggio Emilia, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Engineering, University of Modena and Reggio Emilia, Italy","institution_ids":["https://openalex.org/I122346577"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030948871","display_name":"Rita Cucchiara","orcid":"https://orcid.org/0000-0002-2239-283X"},"institutions":[{"id":"https://openalex.org/I122346577","display_name":"University of Modena and Reggio Emilia","ror":"https://ror.org/02d4c4y02","country_code":"IT","type":"education","lineage":["https://openalex.org/I122346577"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Rita Cucchiara","raw_affiliation_strings":["Department of Engineering, University of Modena and Reggio Emilia, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Engineering, University of Modena and Reggio Emilia, Italy","institution_ids":["https://openalex.org/I122346577"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5033144993"],"corresponding_institution_ids":["https://openalex.org/I122346577"],"apc_list":null,"apc_paid":null,"fwci":4.6904,"has_fulltext":false,"cited_by_count":47,"citation_normalized_percentile":{"value":0.96154551,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"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":0.9972000122070312,"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":0.9898999929428101,"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":0.9536938667297363},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8546568751335144},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5974257588386536},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5956471562385559},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5373818278312683},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5067885518074036},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.496615469455719},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.41148820519447327},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.32430773973464966}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9536938667297363},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8546568751335144},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5974257588386536},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5956471562385559},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5373818278312683},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5067885518074036},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.496615469455719},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.41148820519447327},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.32430773973464966},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3549555.3549585","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3549555.3549585","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3549555.3549585","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Conference on Content-based Multimedia Indexing","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.unimore.it:11380/1281718","is_oa":true,"landing_page_url":"https://hdl.handle.net/11380/1281718","pdf_url":null,"source":{"id":"https://openalex.org/S4306400718","display_name":"IRIS UNIMORE (University of Modena and Reggio Emilia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I122346577","host_organization_name":"University of Modena and Reggio Emilia","host_organization_lineage":["https://openalex.org/I122346577"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.1145/3549555.3549585","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3549555.3549585","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3549555.3549585","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Conference on Content-based Multimedia Indexing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7699999809265137,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4303444943.pdf","grobid_xml":"https://content.openalex.org/works/W4303444943.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2745461083","https://openalex.org/W2890531016","https://openalex.org/W2962784628","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2963686907","https://openalex.org/W2986670728","https://openalex.org/W2990069284","https://openalex.org/W2997591391","https://openalex.org/W2998702515","https://openalex.org/W3016923549","https://openalex.org/W3034655362","https://openalex.org/W3034733309","https://openalex.org/W3043343140","https://openalex.org/W3043501111","https://openalex.org/W3088493063","https://openalex.org/W3112689365","https://openalex.org/W3129831491","https://openalex.org/W3156789018","https://openalex.org/W3157700644","https://openalex.org/W3167939936","https://openalex.org/W3174380564","https://openalex.org/W3198206641","https://openalex.org/W3203778378","https://openalex.org/W4299301436","https://openalex.org/W4312712450"],"related_works":["https://openalex.org/W4310447809","https://openalex.org/W4200243030","https://openalex.org/W2800782462","https://openalex.org/W4323777661","https://openalex.org/W4388184981","https://openalex.org/W3209117276","https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3122720459"],"abstract_inverted_index":{"Image":[0],"captioning":[1,53,140],"models":[2,30,141],"aim":[3],"at":[4,142],"connecting":[5],"Vision":[6],"and":[7,31,87,100,127],"Language":[8],"by":[9,27,38],"providing":[10],"natural":[11],"language":[12],"descriptions":[13],"of":[14,50],"input":[15],"images.":[16],"In":[17,43],"the":[18,22,48,71,97,105,112,124],"past":[19,98],"few":[20],"years,":[21],"task":[23],"has":[24],"been":[25],"tackled":[26],"learning":[28],"parametric":[29],"proposing":[32],"visual":[33,82],"feature":[34],"extraction":[35],"advancements":[36],"or":[37],"modeling":[39],"better":[40],"multi-modal":[41],"connections.":[42],"this":[44],"paper,":[45],"we":[46],"investigate":[47],"development":[49],"an":[51,66,118],"image":[52,139],"approach":[54],"with":[55,59],"a":[56,77,84,88],"kNN":[57],"memory,":[58],"which":[60],"knowledge":[61,78],"can":[62,122],"be":[63],"retrieved":[64,103],"from":[65,104],"external":[67,106,120],"corpus":[68],"to":[69,92],"aid":[70,123],"generation":[72,125],"process.":[73],"Our":[74,131],"architecture":[75],"combines":[76],"retriever":[79],"based":[80,95],"on":[81,96,101,111],"similarities,":[83],"differentiable":[85],"encoder,":[86],"kNN-augmented":[89],"attention":[90],"layer":[91],"predict":[93],"tokens":[94],"context":[99],"text":[102],"memory.":[107],"Experimental":[108],"results,":[109],"conducted":[110],"COCO":[113],"dataset,":[114],"demonstrate":[115],"that":[116],"employing":[117],"explicit":[119],"memory":[121],"process":[126],"increase":[128],"caption":[129],"quality.":[130],"work":[132],"opens":[133],"up":[134],"new":[135],"avenues":[136],"for":[137],"improving":[138],"larger":[143],"scale.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":17}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
