{"id":"https://openalex.org/W4416251377","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227734","title":"Beyond Similarity: Aligning Retrieval with Generation for Enhanced Image Captioning","display_name":"Beyond Similarity: Aligning Retrieval with Generation for Enhanced Image Captioning","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416251377","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227734"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11227734","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227734","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","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/A5018655903","display_name":"Guilin Yang","orcid":"https://orcid.org/0000-0001-6144-3401"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"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":true,"raw_author_name":"Gengqi Yang","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002436544","display_name":"Dayan Wu","orcid":"https://orcid.org/0000-0002-8604-7226"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"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":"Dayan Wu","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100595021","display_name":"Jinyang An","orcid":"https://orcid.org/0009-0009-0327-3809"},"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"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinyang An","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103121628","display_name":"Shupei Xiao","orcid":"https://orcid.org/0009-0003-2625-2185"},"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"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shupei Xiao","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013535291","display_name":"Zheng Lin","orcid":"https://orcid.org/0000-0001-7948-5001"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"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":"Zheng Lin","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5018655903"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34480657,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.987500011920929,"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":0.987500011920929,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.002899999963119626,"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/T10028","display_name":"Topic Modeling","score":0.00139999995008111,"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":0.9890000224113464},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5060999989509583},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.45809999108314514},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.4578000009059906},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4000999927520752},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3991999924182892},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.34689998626708984}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9890000224113464},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8122000098228455},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5774999856948853},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5060999989509583},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.45809999108314514},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.4578000009059906},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43369999527931213},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4000999927520752},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3991999924182892},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3978999853134155},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.34689998626708984},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.3278000056743622},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.32510000467300415},{"id":"https://openalex.org/C143271835","wikidata":"https://www.wikidata.org/wiki/Q254515","display_name":"Similitude","level":2,"score":0.31200000643730164},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2766999900341034},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2703000009059906},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.2531000077724457},{"id":"https://openalex.org/C199579030","wikidata":"https://www.wikidata.org/wiki/Q2851778","display_name":"Automatic image annotation","level":4,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11227734","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227734","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2133459682","https://openalex.org/W2185175083","https://openalex.org/W2506483933","https://openalex.org/W2886641317","https://openalex.org/W2904565150","https://openalex.org/W2998702515","https://openalex.org/W3091588028","https://openalex.org/W3110019360","https://openalex.org/W3176641147","https://openalex.org/W3216130706","https://openalex.org/W4292828275","https://openalex.org/W4312922092","https://openalex.org/W4385245566","https://openalex.org/W4386076004","https://openalex.org/W4386566587","https://openalex.org/W4388778348","https://openalex.org/W4390873015","https://openalex.org/W4396612944","https://openalex.org/W4401042773","https://openalex.org/W4402671679","https://openalex.org/W4402671977","https://openalex.org/W4402727516","https://openalex.org/W4402754015"],"related_works":[],"abstract_inverted_index":{"Image":[0],"captioning":[1,33,104,145,220,234],"is":[2,138,175],"a":[3,79,100,149],"crucial":[4],"task":[5],"that":[6,67,127,185,214],"bridges":[7],"computer":[8],"vision":[9],"and":[10,39,83,116,207,229],"natural":[11],"language":[12,195],"processing,":[13],"with":[14,142,159,180],"applications":[15],"ranging":[16],"from":[17],"assistive":[18],"technologies":[19],"to":[20,31,49,59,140,154],"content":[21],"creation.":[22],"Recently,":[23],"retrieval-augmented":[24],"generation":[25,62,76,84,133],"(RAG)":[26],"methods":[27],"have":[28],"been":[29],"introduced":[30],"enhance":[32,74],"models":[34],"by":[35,193],"incorporating":[36],"external":[37],"knowledge":[38],"enabling":[40],"training-free":[41],"domain":[42],"transfer.":[43],"These":[44],"approaches":[45],"utilize":[46],"pre-trained":[47,199],"retrievers":[48],"fetch":[50],"relevant":[51,190],"information":[52],"for":[53,96],"input":[54,114],"images,":[55],"providing":[56],"additional":[57],"context":[58],"the":[60,75,110,113,117,131,136,143,156,160,165,186,194,225],"caption":[61],"process.":[63],"However,":[64],"we":[65,92],"observe":[66],"high-similarity":[68],"retrieved":[69,118],"results":[70,126,191],"do":[71],"not":[72],"always":[73],"process,":[77],"revealing":[78],"misalignment":[80],"between":[81,112,227],"retrieval":[82,228],"in":[85],"existing":[86],"methods.":[87,221],"To":[88],"address":[89],"this":[90,169],"issue,":[91],"propose":[93],"Retrieval":[94],"Alignment":[95],"Caption":[97],"Enhancement":[98],"(RACE),":[99],"novel":[101],"RAG-based":[102,218],"image":[103,115,144,219],"method.":[105],"Instead":[106],"of":[107,164],"merely":[108],"enhancing":[109],"similarity":[111,151],"results,":[119],"our":[120],"RACE":[121,215,231],"method":[122],"focuses":[123],"on":[124,177,203],"retrieving":[125],"more":[128,189],"effectively":[129,223],"benefit":[130],"final":[132],"outcomes.":[134],"Specifically,":[135],"retriever":[137,187],"optimized":[139],"align":[141,155],"model.":[146],"We":[147],"introduce":[148],"generation-oriented":[150],"correction":[152],"loss":[153,171],"similarity-based":[157],"distribution":[158,163],"CIDEr-based":[161],"evaluation":[162],"generated":[166],"captions.":[167],"In":[168],"proposed":[170],"function,":[172],"greater":[173],"emphasis":[174],"placed":[176],"training":[178],"samples":[179],"higher":[181],"divergence.":[182],"This":[183],"ensures":[184],"retrieves":[188],"preferred":[192],"decoder,":[196],"while":[197],"preserving":[198],"knowledge.":[200],"Extensive":[201],"experiments":[202],"both":[204],"in-domain":[205],"(COCO)":[206],"out-of-domain":[208],"(NoCaps,":[209],"Flickr30k,":[210],"VizWiz)":[211],"benchmarks":[212],"demonstrate":[213],"outperforms":[216],"other":[217],"By":[222],"bridging":[224],"gap":[226],"generation,":[230],"enhances":[232],"overall":[233],"quality.":[235]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-14T00:00:00"}