{"id":"https://openalex.org/W4416078533","doi":"https://doi.org/10.1145/3746252.3760826","title":"Multimodal RAG Enhanced Visual Description","display_name":"Multimodal RAG Enhanced Visual Description","publication_year":2025,"publication_date":"2025-11-10","ids":{"openalex":"https://openalex.org/W4416078533","doi":"https://doi.org/10.1145/3746252.3760826"},"language":null,"primary_location":{"id":"doi:10.1145/3746252.3760826","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746252.3760826","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3746252.3760826","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://dl.acm.org/doi/pdf/10.1145/3746252.3760826","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050410519","display_name":"Amit Kumar Jaiswal","orcid":"https://orcid.org/0000-0001-8848-7041"},"institutions":[{"id":"https://openalex.org/I56404289","display_name":"Indian Institute of Technology BHU","ror":"https://ror.org/01kh5gc44","country_code":"IN","type":"education","lineage":["https://openalex.org/I56404289","https://openalex.org/I91357014"]},{"id":"https://openalex.org/I91357014","display_name":"Banaras Hindu University","ror":"https://ror.org/04cdn2797","country_code":"IN","type":"education","lineage":["https://openalex.org/I91357014"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Amit Kumar Jaiswal","raw_affiliation_strings":["Indian Institute of Technology (BHU), Varanasi, India"],"raw_orcid":"https://orcid.org/0000-0001-8848-7041","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology (BHU), Varanasi, India","institution_ids":["https://openalex.org/I56404289","https://openalex.org/I91357014"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034400349","display_name":"Haiming Liu","orcid":"https://orcid.org/0000-0002-0390-3657"},"institutions":[{"id":"https://openalex.org/I43439940","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543","country_code":"GB","type":"education","lineage":["https://openalex.org/I43439940"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Haiming Liu","raw_affiliation_strings":["University of Southampton, Southampton, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-0390-3657","affiliations":[{"raw_affiliation_string":"University of Southampton, Southampton, United Kingdom","institution_ids":["https://openalex.org/I43439940"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090419459","display_name":"Ingo Frommholz","orcid":"https://orcid.org/0000-0002-5622-5132"},"institutions":[{"id":"https://openalex.org/I150545927","display_name":"MODUL University Vienna","ror":"https://ror.org/04v2brz27","country_code":"AT","type":"education","lineage":["https://openalex.org/I150545927"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Ingo Frommholz","raw_affiliation_strings":["Modul University Vienna, Vienna, Austria"],"raw_orcid":"https://orcid.org/0000-0002-5622-5132","affiliations":[{"raw_affiliation_string":"Modul University Vienna, Vienna, Austria","institution_ids":["https://openalex.org/I150545927"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4827","last_page":"4831"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9750999808311462,"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":0.9750999808311462,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.004600000102072954,"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":0.00419999985024333,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7210000157356262},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6341000199317932},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6107000112533569},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4903999865055084},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.43630000948905945},{"id":"https://openalex.org/keywords/conjunction","display_name":"Conjunction (astronomy)","score":0.42559999227523804},{"id":"https://openalex.org/keywords/structured-prediction","display_name":"Structured prediction","score":0.32350000739097595},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.3073999881744385}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8281999826431274},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7210000157356262},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6341000199317932},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6107000112533569},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5636000037193298},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4903999865055084},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4489000141620636},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.43630000948905945},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.42559999227523804},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.32350000739097595},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3073999881744385},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30720001459121704},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.30090001225471497},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2962999939918518},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.28839999437332153},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746252.3760826","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746252.3760826","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3746252.3760826","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:10.1145/3746252.3760826","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746252.3760826","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3746252.3760826","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":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416078533.pdf"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2185175083","https://openalex.org/W2561995736","https://openalex.org/W2970231061","https://openalex.org/W2998702515","https://openalex.org/W3106859150","https://openalex.org/W3153469116","https://openalex.org/W3173220247","https://openalex.org/W4283803815","https://openalex.org/W4385768038","https://openalex.org/W4386076004","https://openalex.org/W4388193026","https://openalex.org/W4389520529"],"related_works":[],"abstract_inverted_index":{"Textual":[0],"descriptions":[1,135,176],"for":[2,78,153,169,183],"multimodal":[3,40,194],"inputs":[4],"entail":[5],"recurrent":[6],"refinement":[7],"of":[8,132],"queries":[9],"to":[10,17,75,96,124,157],"produce":[11],"relevant":[12],"output":[13],"images.":[14],"Despite":[15],"efforts":[16],"address":[18],"challenges":[19],"such":[20],"as":[21,149],"scaling":[22],"model":[23,156,180],"size":[24],"and":[25,33,53,72],"data":[26],"volume,":[27],"the":[28,76,99,137,154,171,178],"cost":[29],"associated":[30],"with":[31,145],"pre-training":[32],"fine-tuning":[34,62],"remains":[35],"substantial.":[36],"However,":[37],"pre-trained":[38],"large":[39],"models":[41],"(LMMs)":[42],"encounter":[43],"a":[44,49,57,88,102],"modality":[45,100],"gap,":[46,67],"characterised":[47],"by":[48,127,173],"misalignment":[50],"between":[51],"textual":[52,134,141,160],"visual":[54],"representations":[55],"within":[56],"common":[58],"embedding":[59],"space.":[60],"Although":[61],"can":[63,106,113],"potentially":[64],"mitigate":[65],"this":[66,84,120],"it":[68],"is":[69,122],"typically":[70],"expensive":[71],"impractical":[73],"due":[74],"requirement":[77],"extensive":[79],"domain-driven":[80],"data.":[81],"To":[82],"overcome":[83],"challenge,":[85],"we":[86,164],"propose":[87],"lightweight":[89],"training-free":[90],"approach":[91],"utilising":[92],"Retrieval-Augmented":[93],"Generation":[94],"(RAG)":[95],"extend":[97],"across":[98],"using":[101],"linear":[103],"mapping,":[104],"which":[105],"be":[107,114],"computed":[108],"efficiently.":[109],"Our":[110],"reproducible":[111],"code":[112],"found":[115],"in":[116,143],"https://github.com/amitkumarj441/mRAG-gim.":[117],"During":[118],"inference,":[119],"mapping":[121,172],"applied":[123],"images":[125],"embedded":[126],"an":[128,146,150,166],"LMM":[129],"enabling":[130],"retrieval":[131],"closest":[133],"from":[136],"training":[138],"set.":[139],"These":[140],"descriptions,":[142],"conjunction":[144],"instruction,":[147],"cater":[148],"input":[151],"prompt":[152],"language":[155,179],"generate":[158],"new":[159],"descriptions.":[161],"In":[162],"addition,":[163],"introduce":[165],"iterative":[167],"technique":[168],"distilling":[170],"generating":[174],"synthetic":[175],"via":[177],"facilitating":[181],"optimisation":[182],"standard":[184],"utilised":[185],"image":[186],"description":[187],"measures.":[188],"Experimental":[189],"results":[190],"on":[191],"two":[192],"benchmark":[193],"datasets":[195],"demonstrate":[196],"significant":[197],"improvements.":[198]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-10T00:00:00"}