{"id":"https://openalex.org/W4402754015","doi":"https://doi.org/10.1109/cvpr52733.2024.01303","title":"Evcap: Retrieval-Augmented Image Captioning with External Visual-Name Memory for Open-World Comprehension","display_name":"Evcap: Retrieval-Augmented Image Captioning with External Visual-Name Memory for Open-World Comprehension","publication_year":2024,"publication_date":"2024-06-16","ids":{"openalex":"https://openalex.org/W4402754015","doi":"https://doi.org/10.1109/cvpr52733.2024.01303"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52733.2024.01303","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.01303","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5100333829","display_name":"Jiaxuan Li","orcid":"https://orcid.org/0000-0002-3104-8280"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jiaxuan Li","raw_affiliation_strings":["The University of Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043253670","display_name":"Duc Minh Vo","orcid":"https://orcid.org/0000-0003-4839-032X"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Duc Minh Vo","raw_affiliation_strings":["The University of Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101463320","display_name":"Akihiro Sugimoto","orcid":"https://orcid.org/0000-0001-9148-9822"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akihiro Sugimoto","raw_affiliation_strings":["National Institute of Informatics,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics,Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042739835","display_name":"Hideki Nakayama","orcid":"https://orcid.org/0000-0002-3244-0268"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hideki Nakayama","raw_affiliation_strings":["The University of Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.9518,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.98661851,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"13733","last_page":"13742"},"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":0.995199978351593,"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":0.9872000217437744,"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":0.9529479742050171},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7960195541381836},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.5387760996818542},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5289922952651978},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.5018103122711182},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47998949885368347},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.43593037128448486},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.43590012192726135},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38689103722572327},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3859894871711731},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08133816719055176}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9529479742050171},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7960195541381836},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.5387760996818542},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5289922952651978},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.5018103122711182},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47998949885368347},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43593037128448486},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.43590012192726135},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38689103722572327},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3859894871711731},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08133816719055176}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52733.2024.01303","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.01303","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G638349425","display_name":"Story Video Generation Based on Content Planning Using Knowledge Graphs","funder_award_id":"23K28139","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320335839","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W1773149199","https://openalex.org/W1905882502","https://openalex.org/W2173180041","https://openalex.org/W2187089797","https://openalex.org/W2745461083","https://openalex.org/W2795151422","https://openalex.org/W2904565150","https://openalex.org/W2948672349","https://openalex.org/W2952122856","https://openalex.org/W2963088515","https://openalex.org/W2998702515","https://openalex.org/W3104279398","https://openalex.org/W3173220247","https://openalex.org/W3176587734","https://openalex.org/W4225323055","https://openalex.org/W4288089799","https://openalex.org/W4292779060","https://openalex.org/W4307106676","https://openalex.org/W4312522167","https://openalex.org/W4322718191","https://openalex.org/W4366850747","https://openalex.org/W4376312115","https://openalex.org/W4378942562","https://openalex.org/W4386065803","https://openalex.org/W4386076004","https://openalex.org/W4386076522","https://openalex.org/W4386566587","https://openalex.org/W4388482029","https://openalex.org/W4389520529","https://openalex.org/W4390872382","https://openalex.org/W4390873015","https://openalex.org/W4390873635","https://openalex.org/W4390874161","https://openalex.org/W6755207826","https://openalex.org/W6769627184","https://openalex.org/W6775970589","https://openalex.org/W6778883912","https://openalex.org/W6791353385","https://openalex.org/W6803567076","https://openalex.org/W6810334672","https://openalex.org/W6810595431","https://openalex.org/W6811013733","https://openalex.org/W6842585177","https://openalex.org/W6847062943","https://openalex.org/W6849177959","https://openalex.org/W6850625674","https://openalex.org/W6851950068","https://openalex.org/W6853116092","https://openalex.org/W6853330684","https://openalex.org/W6858268588"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3217388757","https://openalex.org/W3122720459","https://openalex.org/W4298897568","https://openalex.org/W4289422896","https://openalex.org/W1938708284","https://openalex.org/W4380190185"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)-based":[3],"image":[4,53],"captioning":[5,54],"has":[6],"the":[7,24,84,113],"capability":[8],"of":[9,26,35,40],"describing":[10],"objects":[11,20],"not":[12],"explicitly":[13],"observed":[14],"in":[15],"training":[16],"data;":[17],"yet":[18],"novel":[19],"occur":[21],"frequently,":[22],"necessitating":[23],"requirement":[25],"sustaining":[27],"up-to-date":[28],"object":[29,60,71,97],"knowledge":[30,72],"for":[31],"open-world":[32],"comprehension.":[33],"Instead":[34],"relying":[36],"on":[37,112,129,151],"large":[38],"amounts":[39],"data":[41,134],"and/or":[42],"scaling":[43],"up":[44],"network":[45],"parameters,":[46,142],"we":[47],"introduce":[48],"a":[49,87,101],"highly":[50],"effective":[51],"retrieval-augmented":[52],"method":[55],"that":[56,136,163],"prompts":[57],"LLMs":[58,94],"with":[59,95,138],"names":[61,98],"retrieved":[62,96],"from":[63],"External":[64],"Visual-name":[65],"memory":[66,73,85],"(EVCAP).":[67],"We":[68],"build":[69],"ever-changing":[70],"using":[74],"objects'":[75],"visuals":[76],"and":[77,90,103,131],"names,":[78],"enabling":[79],"us":[80],"to":[81,118,147,160],"(i)":[82],"update":[83],"at":[86],"minimal":[88],"cost":[89],"(ii)":[91],"effort-lessly":[92],"augment":[93],"by":[99],"uti-lizing":[100],"lightweight":[102],"fast-to-train":[104],"model.":[105],"Our":[106,126],"model,":[107],"which":[108],"was":[109],"trained":[110],"only":[111,139],"COCO":[114],"dataset,":[115],"can":[116],"adapt":[117],"out-of-domain":[119],"without":[120],"requiring":[121],"additional":[122],"fine-tuning":[123],"or":[124],"retraining.":[125],"experiments":[127],"conducted":[128],"benchmarks":[130],"synthetic":[132],"commonsense-violating":[133],"show":[135],"EV-CAP,":[137],"3.97M":[140],"trainable":[141],"exhibits":[143],"superior":[144],"performance":[145,156],"compared":[146],"other":[148],"methods":[149],"based":[150],"frozen":[152],"pretrained":[153],"LLMs.":[154],"Its":[155],"is":[157],"also":[158],"competitive":[159],"specialist":[161],"SOTAs":[162],"require":[164],"extensive":[165],"training.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":13},{"year":2025,"cited_by_count":23},{"year":2024,"cited_by_count":5}],"updated_date":"2026-08-15T07:11:24.734988","created_date":"2025-10-10T00:00:00"}