{"id":"https://openalex.org/W4416016984","doi":"https://doi.org/10.1145/3746252.3761265","title":"Retrieval-Augmented Image Captioning via Synthesized Entity-Aware Knowledge Representations","display_name":"Retrieval-Augmented Image Captioning via Synthesized Entity-Aware Knowledge Representations","publication_year":2025,"publication_date":"2025-11-07","ids":{"openalex":"https://openalex.org/W4416016984","doi":"https://doi.org/10.1145/3746252.3761265"},"language":null,"primary_location":{"id":"doi:10.1145/3746252.3761265","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746252.3761265","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 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746252.3761265","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112892087","display_name":"Lin Shen","orcid":"https://orcid.org/0009-0008-9570-767X"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Shen","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China, School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China, and State Key Laboratory of Cyberspace Security Defense, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-9570-767X","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China, School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China, and State Key Laboratory of Cyberspace Security Defense, Beijing, China","institution_ids":["https://openalex.org/I4210156404"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102632601","display_name":"Chenxu Cui","orcid":"https://orcid.org/0009-0007-5228-7989"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenxu Cui","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China, School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China, and State Key Laboratory of Cyberspace Security Defense, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-5228-7989","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China, School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China, and State Key Laboratory of Cyberspace Security Defense, Beijing, China","institution_ids":["https://openalex.org/I4210156404"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033921366","display_name":"Jinchao Zhang","orcid":"https://orcid.org/0009-0005-1835-1700"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinchao Zhang","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China and State Key Laboratory of Cyberspace Security Defense, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-1835-1700","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China and State Key Laboratory of Cyberspace Security Defense, Beijing, China","institution_ids":["https://openalex.org/I4210156404"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040867646","display_name":"Haihui Fan","orcid":"https://orcid.org/0000-0002-4366-9121"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haihui Fan","raw_affiliation_strings":["Instute of information engineering, chinese academy of Science, Beijing, China and State Key Laboratory of Cyberspace Security Defense, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4366-9121","affiliations":[{"raw_affiliation_string":"Instute of information engineering, chinese academy of Science, Beijing, China and State Key Laboratory of Cyberspace Security Defense, Beijing, China","institution_ids":["https://openalex.org/I4210156404"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Haotian Jin","orcid":"https://orcid.org/0009-0004-6482-8461"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haotian Jin","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China, School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China, and State Key Laboratory of Cyberspace Security Defense, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-6482-8461","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China, School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China, and State Key Laboratory of Cyberspace Security Defense, Beijing, China","institution_ids":["https://openalex.org/I4210156404"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100374360","display_name":"Bo Li","orcid":"https://orcid.org/0000-0001-6709-0942"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Li","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China and State Key Laboratory of Cyberspace Security Defense, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6709-0942","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China and State Key Laboratory of Cyberspace Security Defense, Beijing, China","institution_ids":["https://openalex.org/I4210156404"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210156404"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2566","last_page":"2576"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9915000200271606,"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":0.9915000200271606,"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":0.0020000000949949026,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.0010999999940395355,"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":0.9643999934196472},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5230000019073486},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.42989999055862427},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.3652999997138977},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.3610999882221222},{"id":"https://openalex.org/keywords/knowledge-based-systems","display_name":"Knowledge-based systems","score":0.28200000524520874}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9643999934196472},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8097000122070312},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5723000168800354},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5230000019073486},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48919999599456787},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.42989999055862427},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.3652999997138977},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.3610999882221222},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3165000081062317},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2784999907016754},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27160000801086426},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.25380000472068787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746252.3761265","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746252.3761265","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 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3746252.3761265","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746252.3761265","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 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G201311321","display_name":null,"funder_award_id":"ZTZB-23-990-024","funder_id":"https://openalex.org/F4320323970","funder_display_name":"Ministry of Industry and Information Technology of the People's Republic of China"},{"id":"https://openalex.org/G3252164262","display_name":null,"funder_award_id":"62172404","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323970","display_name":"Ministry of Industry and Information Technology of the People's Republic of China","ror":"https://ror.org/0385nmy68"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2506483933","https://openalex.org/W2904565150","https://openalex.org/W2950339735","https://openalex.org/W2998702515","https://openalex.org/W3091588028","https://openalex.org/W3200808010","https://openalex.org/W4312522167","https://openalex.org/W4322718191","https://openalex.org/W4372337842","https://openalex.org/W4385569985","https://openalex.org/W4386076004","https://openalex.org/W4386270350","https://openalex.org/W4386566587","https://openalex.org/W4387968461","https://openalex.org/W4388185726","https://openalex.org/W4390872382","https://openalex.org/W4390873015","https://openalex.org/W4402671679","https://openalex.org/W4402671983","https://openalex.org/W4402703029","https://openalex.org/W4402754015","https://openalex.org/W4403792088","https://openalex.org/W4409347288","https://openalex.org/W4409363063","https://openalex.org/W4409368286","https://openalex.org/W4412376913"],"related_works":[],"abstract_inverted_index":{"Retrieval-Augmented":[0],"Image":[1],"Captioning":[2],"enhances":[3],"the":[4,25,36,40,47,60,119,131,136,141,154,178],"model's":[5],"understanding":[6],"of":[7,55,180],"real-world":[8],"images":[9,87,98,101],"by":[10,134],"retrieving":[11],"external":[12,75],"knowledge.":[13],"Existing":[14],"methods":[15,34,191],"mainly":[16],"use":[17],"original":[18],"captions":[19,164],"or":[20,43,57],"isolated":[21],"entities":[22],"related":[23],"to":[24,28,45,80,111,129,140,156],"query":[26,142],"image":[27],"help":[29],"generate":[30],"captions.":[31,62,122],"However,":[32],"these":[33,65,146],"make":[35],"model":[37,110,155],"either":[38],"imitate":[39],"caption":[41],"style":[42],"fail":[44],"capture":[46],"relationship":[48],"between":[49],"entities,":[50],"resulting":[51],"in":[52,59,148],"a":[53,70,108,126],"lack":[54],"diversity":[56],"inaccuracy":[58],"generated":[61],"To":[63],"address":[64],"issues,":[66],"we":[67,124],"propose":[68],"SEAR,":[69],"novel":[71],"framework":[72],"that":[73],"utilizes":[74,107],"Synthesized":[76],"Entity-Aware":[77],"knowledge":[78,116,132],"Representations":[79],"improve":[81],"captioning":[82],"performance.":[83],"Specifically,":[84],"SEAR":[85,152],"clusters":[86],"based":[88],"on":[89,172],"scene-level":[90],"and":[91,94,105,113,159,165,175,185,192],"entity-level":[92],"features,":[93],"synthesizes":[95],"each":[96],"clustered":[97],"into":[99],"representative":[100],"as":[102],"retrieval":[103],"indexes,":[104],"simultaneously":[106],"large":[109],"extract":[112],"supplement":[114],"structured":[115,160],"graphs":[117],"from":[118],"corresponding":[120],"cluster":[121],"Furthermore,":[123],"design":[125],"knowledge-graph":[127],"pruner":[128],"prune":[130],"graph":[133],"retaining":[135],"most":[137],"relevant":[138],"subgraphs":[139],"image.":[143],"By":[144],"undertaking":[145],"steps":[147],"an":[149],"integrated":[150],"manner,":[151],"enables":[153],"acquire":[157],"non-redundant":[158],"information":[161],"for":[162],"generating":[163],"avoid":[166],"data-related":[167],"privacy":[168],"issues.":[169],"Extensive":[170],"experiments":[171],"MSCOCO,":[173],"Flickr30k,":[174],"NoCaps":[176],"demonstrate":[177],"effectiveness":[179],"our":[181],"method":[182],"both":[183],"in-domain":[184],"out-of-domain,":[186],"outperforming":[187],"existing":[188],"lightweight":[189],"RAIC":[190],"remaining":[193],"competitive":[194],"with":[195],"heavyweight":[196],"models.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2025-11-08T00:00:00"}
