{"id":"https://openalex.org/W4413469181","doi":"https://doi.org/10.1109/tmm.2025.3599070","title":"RA-BLIP: Multimodal Adaptive Retrieval-Augmented Bootstrapping Language-Image Pre-Training","display_name":"RA-BLIP: Multimodal Adaptive Retrieval-Augmented Bootstrapping Language-Image Pre-Training","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4413469181","doi":"https://doi.org/10.1109/tmm.2025.3599070"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2025.3599070","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3599070","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5011235816","display_name":"Mengmeng Ding","orcid":"https://orcid.org/0000-0001-9009-3615"},"institutions":[{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]},{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Muhe Ding","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China","School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I158809036","https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101875456","display_name":"Yang Ma","orcid":"https://orcid.org/0000-0003-3719-3195"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yang Ma","raw_affiliation_strings":["School of Computer Science, University of Sydney, Sydney, NSW, Australia"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034095320","display_name":"Pengda Qin","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengda Qin","raw_affiliation_strings":["Security Department, Alibaba Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Security Department, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101848141","display_name":"Jianlong Wu","orcid":"https://orcid.org/0000-0002-4619-0693"},"institutions":[{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]},{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianlong Wu","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China","School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I158809036","https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100341177","display_name":"Yuhong Li","orcid":"https://orcid.org/0009-0009-9185-7133"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhong Li","raw_affiliation_strings":["Security Department, Alibaba Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Security Department, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085804436","display_name":"Liqiang Nie","orcid":null},"institutions":[{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]},{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liqiang Nie","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China","School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I158809036","https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5011235816"],"corresponding_institution_ids":["https://openalex.org/I158809036","https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":9.4273,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.97689699,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"27","issue":null,"first_page":"7522","last_page":"7532"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9912999868392944,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9912999868392944,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9757000207901001,"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"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9544000029563904,"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/computer-science","display_name":"Computer science","score":0.8507159948348999},{"id":"https://openalex.org/keywords/bootstrapping","display_name":"Bootstrapping (finance)","score":0.6849023699760437},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5387680530548096},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.4904763400554657},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45528802275657654},{"id":"https://openalex.org/keywords/automatic-image-annotation","display_name":"Automatic image annotation","score":0.4190182089805603},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35673987865448},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.34602057933807373},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3431345224380493},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3393917381763458}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8507159948348999},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.6849023699760437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5387680530548096},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.4904763400554657},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45528802275657654},{"id":"https://openalex.org/C199579030","wikidata":"https://www.wikidata.org/wiki/Q2851778","display_name":"Automatic image annotation","level":4,"score":0.4190182089805603},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35673987865448},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.34602057933807373},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3431345224380493},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3393917381763458},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C106159729","wikidata":"https://www.wikidata.org/wiki/Q2294553","display_name":"Financial economics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2025.3599070","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3599070","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5954055007","display_name":null,"funder_award_id":"62376069","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G873523568","display_name":null,"funder_award_id":"2024A1515012027","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2560730294","https://openalex.org/W2896457183","https://openalex.org/W2951434086","https://openalex.org/W2963563735","https://openalex.org/W2970231061","https://openalex.org/W2970959783","https://openalex.org/W2997591391","https://openalex.org/W2998536339","https://openalex.org/W3005881764","https://openalex.org/W3034654340","https://openalex.org/W3087975588","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3156789018","https://openalex.org/W3173220247","https://openalex.org/W3177155667","https://openalex.org/W3210877910","https://openalex.org/W3212100893","https://openalex.org/W3213454282","https://openalex.org/W4253028564","https://openalex.org/W4281254837","https://openalex.org/W4285249364","https://openalex.org/W4290927857","https://openalex.org/W4312643954","https://openalex.org/W4313318649","https://openalex.org/W4321471832","https://openalex.org/W4367189320","https://openalex.org/W4378697123","https://openalex.org/W4382119268","https://openalex.org/W4382999123","https://openalex.org/W4385245566","https://openalex.org/W4385571810","https://openalex.org/W4385573236","https://openalex.org/W4385682832","https://openalex.org/W4386065803","https://openalex.org/W4386076522","https://openalex.org/W4387969587"],"related_works":["https://openalex.org/W3177930984","https://openalex.org/W2052697133","https://openalex.org/W2076896210","https://openalex.org/W2384288472","https://openalex.org/W1539573266","https://openalex.org/W2093596879","https://openalex.org/W2376984068","https://openalex.org/W2201969175","https://openalex.org/W2017257332","https://openalex.org/W2747088704"],"abstract_inverted_index":{"Multimodal":[0],"Large":[1],"Language":[2],"Models":[3],"(MLLMs)":[4],"have":[5,54],"recently":[6],"received":[7],"substantial":[8],"interest,":[9],"which":[10,43,167],"shows":[11],"their":[12,28],"emerging":[13],"potential":[14],"as":[15],"general-purpose":[16],"models":[17,38],"for":[18,60,83],"various":[19,84],"vision-language":[20],"tasks.":[21],"MLLMs":[22],"involve":[23],"significant":[24,183],"external":[25],"knowledge":[26,133],"within":[27],"parameters;":[29],"however,":[30],"it":[31],"is":[32],"challenging":[33],"to":[34,56,91,124,155,159],"continually":[35],"update":[36],"these":[37],"with":[39,100],"the":[40,89,93,157,162,187],"latest":[41],"knowledge,":[42,166],"involves":[44],"huge":[45],"computational":[46],"costs":[47],"and":[48,63,109,113,129,137,185],"poor":[49],"interpretability.":[50],"Retrieval":[51],"augmentation":[52],"techniques":[53],"proven":[55],"be":[57],"effective":[58],"plugins":[59],"both":[61],"LLMs":[62],"MLLMs.":[64,85],"In":[65],"this":[66],"study,":[67],"we":[68,116,146],"propose":[69],"multimodal":[70,120,132,176],"adaptive":[71,121],"Retrieval-Augmented":[72],"Bootstrapping":[73],"Language-Image":[74],"Pre-training":[75],"(<bold":[76],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[77],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">RA-BLIP</b>),":[78],"a":[79,118,141],"novel":[80],"retrieval-augmented":[81,189],"framework":[82],"We":[86],"first":[87],"leverage":[88],"question":[90,126],"instruct":[92],"extraction":[94],"of":[95,103,131,164],"visual":[96,136],"information":[97],"through":[98],"interactions":[99],"one":[101],"set":[102],"learnable":[104],"queries,":[105],"minimizing":[106],"irrelevant":[107],"interference":[108],"redundancy":[110],"during":[111],"retrieval":[112,128],"generation.":[114],"Besides,":[115],"introduce":[117],"pre-trained":[119],"fusion":[122],"module":[123],"achieve":[125],"text-to-multimodal":[127],"integration":[130],"by":[134],"projecting":[135],"language":[138],"modalities":[139],"into":[140],"unified":[142],"semantic":[143],"space.":[144],"Furthermore,":[145],"present":[147],"an":[148],"Adaptive":[149],"Selection":[150],"Knowledge":[151],"Generation":[152],"(ASKG)":[153],"strategy":[154],"train":[156],"generator":[158],"autonomously":[160],"discern":[161],"relevance":[163],"retrieved":[165],"realizes":[168],"excellent":[169],"denoising":[170],"performance.":[171],"Extensive":[172],"experiments":[173],"on":[174],"open":[175],"question-answering":[177],"datasets":[178],"demonstrate":[179],"that":[180],"RA-BLIP":[181],"achieves":[182],"performance":[184],"surpasses":[186],"state-of-the-art":[188],"models.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":4}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}