{"id":"https://openalex.org/W7128597887","doi":"https://doi.org/10.1145/3797043","title":"Adaptive Co-Operative Prompting and Uncertainty-Aware Implicit Knowledge Enhancement for Cross-Modal Retrieval","display_name":"Adaptive Co-Operative Prompting and Uncertainty-Aware Implicit Knowledge Enhancement for Cross-Modal Retrieval","publication_year":2026,"publication_date":"2026-02-11","ids":{"openalex":"https://openalex.org/W7128597887","doi":"https://doi.org/10.1145/3797043"},"language":"en","primary_location":{"id":"doi:10.1145/3797043","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3797043","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","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/A5125599075","display_name":"Xin Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210110718","display_name":"Nanyang Normal University","ror":"https://ror.org/01f7yer47","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210110718"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Huang","raw_affiliation_strings":["School of Artificial Intelligence, Nanyang Normal University, Nanyang, China and Henan Digital Image Big Data Development Innovation Laboratory, Nanyang, China"],"raw_orcid":"https://orcid.org/0009-0006-3201-4978","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Nanyang Normal University, Nanyang, China and Henan Digital Image Big Data Development Innovation Laboratory, Nanyang, China","institution_ids":["https://openalex.org/I4210110718"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shilong Wang","orcid":"https://orcid.org/0009-0007-7340-6334"},"institutions":[{"id":"https://openalex.org/I4210110718","display_name":"Nanyang Normal University","ror":"https://ror.org/01f7yer47","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210110718"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shilong Wang","raw_affiliation_strings":["School of Artificial Intelligence, Nanyang Normal University, Nanyang, China and Henan Digital Image Big Data Development Innovation Laboratory, Nanyang, China"],"raw_orcid":"https://orcid.org/0009-0007-7340-6334","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Nanyang Normal University, Nanyang, China and Henan Digital Image Big Data Development Innovation Laboratory, Nanyang, China","institution_ids":["https://openalex.org/I4210110718"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069358025","display_name":"Tong Jia","orcid":"https://orcid.org/0000-0002-5946-9829"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong Jia","raw_affiliation_strings":["Institute for Artificial Intelligence, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5946-9829","affiliations":[{"raw_affiliation_string":"Institute for Artificial Intelligence, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570","https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125601438","display_name":"Zhimin Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210110718","display_name":"Nanyang Normal University","ror":"https://ror.org/01f7yer47","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210110718"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhimin Yuan","raw_affiliation_strings":["School of Artificial Intelligence, Nanyang Normal University, Nanyang, China and Henan Digital Image Big Data Development Innovation Laboratory, Nanyang, China"],"raw_orcid":"https://orcid.org/0000-0003-4587-8370","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Nanyang Normal University, Nanyang, China and Henan Digital Image Big Data Development Innovation Laboratory, Nanyang, China","institution_ids":["https://openalex.org/I4210110718"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073389089","display_name":"Runsheng Zhang","orcid":"https://orcid.org/0009-0008-0943-9008"},"institutions":[{"id":"https://openalex.org/I153473198","display_name":"North China Electric Power University","ror":"https://ror.org/04qr5t414","country_code":"CN","type":"education","lineage":["https://openalex.org/I153473198"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Runsheng Zhang","raw_affiliation_strings":["School of Energy, Power and Mechanical Engineering, North China Electric Power University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-0943-9008","affiliations":[{"raw_affiliation_string":"School of Energy, Power and Mechanical Engineering, North China Electric Power University, Beijing, China","institution_ids":["https://openalex.org/I153473198"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jingjing Li","orcid":"https://orcid.org/0009-0006-0714-3356"},"institutions":[{"id":"https://openalex.org/I4210110718","display_name":"Nanyang Normal University","ror":"https://ror.org/01f7yer47","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210110718"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingjing Li","raw_affiliation_strings":["School of Artificial Intelligence, Nanyang Normal University, Nanyang, China and Henan Digital Image Big Data Development Innovation Laboratory, Nanyang, China"],"raw_orcid":"https://orcid.org/0009-0006-0714-3356","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Nanyang Normal University, Nanyang, China and Henan Digital Image Big Data Development Innovation Laboratory, Nanyang, China","institution_ids":["https://openalex.org/I4210110718"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17092716,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"22","issue":"5","first_page":"1","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9108999967575073,"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":0.9108999967575073,"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":0.06759999692440033,"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/T11605","display_name":"Visual Attention and Saliency Detection","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/semantics","display_name":"Semantics (computer science)","score":0.4657999873161316},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.42500001192092896},{"id":"https://openalex.org/keywords/semantic-matching","display_name":"Semantic matching","score":0.4244000017642975},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.42419999837875366},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.3889000117778778},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.34380000829696655},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.3433000147342682}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9003999829292297},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5266000032424927},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4657999873161316},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.42500001192092896},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.4244000017642975},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.42419999837875366},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3889000117778778},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3716999888420105},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3610999882221222},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.34380000829696655},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3433000147342682},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.34119999408721924},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.3296999931335449},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.30570000410079956},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.30489999055862427},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2847000062465668},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.2809999883174896},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.272599995136261}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3797043","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3797043","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3378916720","display_name":null,"funder_award_id":"24YJCZH135","funder_id":"https://openalex.org/F4320336573","funder_display_name":"Humanities and Social Sciences Youth Foundation, Ministry of Education of the People's Republic of China"},{"id":"https://openalex.org/G3889249711","display_name":null,"funder_award_id":"62502243 and 52306082","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/F4320336573","display_name":"Humanities and Social Sciences Youth Foundation, Ministry of Education of the People's Republic of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2100560442","https://openalex.org/W2185175083","https://openalex.org/W2606965845","https://openalex.org/W3198377975","https://openalex.org/W3213100861","https://openalex.org/W4213303451","https://openalex.org/W4214819138","https://openalex.org/W4249992252","https://openalex.org/W4285606530","https://openalex.org/W4317436342","https://openalex.org/W4379409095","https://openalex.org/W4382999123","https://openalex.org/W4385571188","https://openalex.org/W4387951800","https://openalex.org/W4389675233","https://openalex.org/W4395056490","https://openalex.org/W4405778998"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,16,75,93,106,202],"rapid":[2],"growth":[3],"of":[4,22,78,204],"Internet":[5],"multimedia":[6],"data,":[7],"cross-modal":[8,23,32,40,63],"retrieval":[9,84],"techniques":[10],"have":[11],"garnered":[12],"significant":[13],"attention.":[14],"Given":[15],"inherent":[17],"complexity":[18],"and":[19,47,61,111,139,147,163,186,199],"non-intuitive":[20],"nature":[21],"relationships,":[24],"tuning":[25],"pre-trained":[26],"Large":[27],"Multimodal":[28],"Models":[29],"(LMMs)":[30],"with":[31,52],"data":[33,41],"has":[34],"become":[35],"a":[36,153],"mainstream":[37],"approach.":[38],"However,":[39],"commonly":[42],"exhibit":[43],"inter-modal":[44],"information":[45,149],"asymmetry":[46],"intra-modal":[48,183],"distribution":[49,184],"diversity.":[50],"Faced":[51],"these":[53,88],"challenges,":[54,89],"existing":[55],"paradigms":[56],"tend":[57],"to":[58,74,121,134,170],"learn":[59],"ambiguous":[60],"asymmetric":[62],"associations,":[64],"which":[65,104,168],"introduce":[66],"semantic":[67,127,137,176],"noise.":[68],"In":[69],"addition,":[70],"their":[71,136],"limited":[72],"adaptability":[73],"high":[76],"diversity":[77,185],"real-world":[79],"content":[80],"further":[81],"hinders":[82],"optimal":[83],"performance.":[85],"To":[86],"address":[87],"this":[90],"article":[91],"proposes":[92],"A":[94],"daptive":[95],"C":[96],"o-operative":[97],"K":[98],"nowledge":[99],"E":[100],"nhancement":[101],"(ACKE)":[102],"method,":[103],"comprises":[105],"Uncertainty-Aware":[107],"Inspire":[108],"Potential":[109],"(UAIP)":[110],"Adaptive":[112],"Co-Operative":[113],"Prompt":[114],"(ACP)":[115],"strategies.":[116],"UAIP":[117],"utilizes":[118],"generative":[119],"LMMs":[120],"generate":[122],"multi-perspective":[123],"descriptions":[124],"that":[125],"enrich":[126],"information,":[128],"while":[129],"employing":[130],"Dempster-Shafer":[131],"Theory":[132],"(DST)":[133],"quantify":[135],"uncertainty":[138],"adjust":[140],"contribution":[141],"weights,":[142],"reducing":[143],"inaccurate":[144],"relational":[145],"mappings":[146],"balancing":[148],"asymmetry.":[150],"ACP":[151],"constructs":[152],"prompt":[154],"pool":[155],"where":[156],"instance-specific":[157],"visual":[158],"prompts":[159],"are":[160,191],"dynamically":[161],"selected":[162],"projected":[164],"into":[165],"text":[166],"prompts,":[167],"collaborate":[169],"guide":[171],"modal":[172],"encoders":[173],"toward":[174],"deep":[175],"consensus,":[177],"thus":[178],"mitigating":[179],"alignment":[180],"bias":[181],"from":[182],"improving":[187],"accuracy.":[188],"Extensive":[189],"experiments":[190],"conducted":[192],"on":[193],"two":[194],"widely":[195],"used":[196],"datasets,":[197],"Flickr30K":[198],"MS-COCO,":[200],"demonstrating":[201],"effectiveness":[203],"our":[205],"proposed":[206],"method.":[207],"The":[208],"code":[209],"is":[210],"available":[211],"at":[212],"https://github.com/nynu-BDAI/ACKE":[213],".":[214]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-02-11T00:00:00"}