{"id":"https://openalex.org/W7131841032","doi":"https://doi.org/10.1109/tmm.2026.3668503","title":"Beyond Mere Tuning: Harnessing the Full Potential of Prompts for Text-Video Retrieval","display_name":"Beyond Mere Tuning: Harnessing the Full Potential of Prompts for Text-Video Retrieval","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7131841032","doi":"https://doi.org/10.1109/tmm.2026.3668503"},"language":null,"primary_location":{"id":"doi:10.1109/tmm.2026.3668503","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3668503","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/A5101658131","display_name":"Donglin Zhang","orcid":"https://orcid.org/0000-0002-0716-0918"},"institutions":[{"id":"https://openalex.org/I111599522","display_name":"Jiangnan University","ror":"https://ror.org/04mkzax54","country_code":"CN","type":"education","lineage":["https://openalex.org/I111599522"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Donglin Zhang","raw_affiliation_strings":["School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China"],"raw_orcid":"https://orcid.org/0000-0002-0716-0918","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China","institution_ids":["https://openalex.org/I111599522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084816002","display_name":"Zhiwen Wang","orcid":"https://orcid.org/0000-0002-2648-5769"},"institutions":[{"id":"https://openalex.org/I111599522","display_name":"Jiangnan University","ror":"https://ror.org/04mkzax54","country_code":"CN","type":"education","lineage":["https://openalex.org/I111599522"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiwen Wang","raw_affiliation_strings":["School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China","institution_ids":["https://openalex.org/I111599522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009074046","display_name":"Xing Xu","orcid":"https://orcid.org/0000-0001-5685-3123"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Xu","raw_affiliation_strings":["Centre for Future Media, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0001-5685-3123","affiliations":[{"raw_affiliation_string":"Centre for Future Media, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127394712","display_name":"Xiao-Jun Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I111599522","display_name":"Jiangnan University","ror":"https://ror.org/04mkzax54","country_code":"CN","type":"education","lineage":["https://openalex.org/I111599522"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao-Jun Wu","raw_affiliation_strings":["School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China"],"raw_orcid":"https://orcid.org/0000-0002-0310-5778","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China","institution_ids":["https://openalex.org/I111599522"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5127393878","display_name":"Josef Kittler","orcid":null},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Josef Kittler","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Guildford, U.K"],"raw_orcid":"https://orcid.org/0000-0002-8110-9205","affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Guildford, U.K","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.8119,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.94963496,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"28","issue":null,"first_page":"5748","last_page":"5757"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.18639999628067017,"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":0.18639999628067017,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.15330000221729279,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.11140000075101852,"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/scope","display_name":"Scope (computer science)","score":0.710099995136261},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.650600016117096},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6026999950408936},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.4625000059604645},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.43709999322891235},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.41510000824928284},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4000000059604645},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.39809998869895935}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9081000089645386},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.710099995136261},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.650600016117096},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6026999950408936},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5059000253677368},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.4625000059604645},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.43709999322891235},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.41510000824928284},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4000000059604645},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.39809998869895935},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.36660000681877136},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3610999882221222},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.359499990940094},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.35850000381469727},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3278000056743622},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.3276999890804291},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C197914299","wikidata":"https://www.wikidata.org/wiki/Q18650","display_name":"Semantic memory","level":3,"score":0.29789999127388},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.29670000076293945},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2563999891281128},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2026.3668503","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3668503","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/G4692016002","display_name":null,"funder_award_id":"62202204","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G75458426","display_name":null,"funder_award_id":"JUSRP123032","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Text-video":[0],"retrieval":[1,90,134],"has":[2,18],"advanced":[3],"significantly":[4],"by":[5,185],"thanks":[6],"to":[7,24,40,54,67,124,131,139,189],"the":[8,26,47,65,72,77,102,126,145,180,191],"merits":[9],"of":[10,49,74,80,105,128],"large-scale":[11],"contrastive":[12],"languageimage":[13],"pre-training.":[14],"Recently,":[15],"prompt":[16,57,154,187],"tuning":[17,42,58],"emerged":[19],"as":[20],"a":[21,97,153,174],"parameter-efficient":[22],"strategy":[23,177],"solve":[25],"substantial":[27],"training":[28,165],"costs":[29],"associated":[30],"with":[31,76],"these":[32],"models.":[33],"However,":[34],"existing":[35],"studies":[36],"are":[37],"generally":[38],"confined":[39],"simple":[41],"strategies,":[43],"without":[44,162],"fully":[45],"exploring":[46],"potential":[48,104],"prompts.":[50],"Unlike":[51],"its":[52],"application":[53],"singlemodal":[55],"tasks,":[56],"in":[59,107,114],"cross-modal":[60],"learning":[61],"involves":[62],"not":[63],"only":[64],"adaptation":[66],"specific":[68],"tasks":[69],"but":[70],"also":[71],"challenge":[73],"dealing":[75],"intricate":[78],"interaction":[79],"semantic":[81,182],"information.":[82],"These":[83],"aspects":[84],"remain":[85],"insufficiently":[86],"explored,":[87],"thereby":[88],"limiting":[89],"performance.":[91,214],"To":[92],"this":[93],"end,":[94],"we":[95,111,120,151],"introduce":[96,173],"comprehensive":[98],"framework":[99],"for":[100],"harnessing":[101],"full":[103],"prompts":[106,113,123],"textvideo":[108],"retrieval.":[109],"Specifically,":[110],"explore":[112],"three":[115],"respects:":[116],"i)":[117],"Task":[118],"adaptation:":[119],"design":[121],"appropriate":[122],"guide":[125],"fine-tuning":[127],"pre-trained":[129],"models":[130],"perform":[132],"text-video":[133],"tasks.":[135],"ii)":[136],"Temporal":[137],"modelling:":[138],"enable":[140],"temporal":[141,160],"modelling,":[142],"while":[143],"protecting":[144],"original":[146],"knowledge":[147],"from":[148],"being":[149],"corrupted,":[150],"propose":[152],"rolling":[155],"module":[156],"that":[157,178,209],"enables":[158],"effective":[159],"processing":[161],"adding":[163],"extra":[164],"parameters.":[166],"iii)":[167],"The":[168],"sampling":[169,192],"scope":[170,193],"prediction:":[171],"We":[172],"query":[175],"expansion":[176],"exploits":[179],"rich":[181],"information":[183],"conveyed":[184],"multimodal":[186],"features":[188],"define":[190],"more":[194],"precisely.":[195],"Extensive":[196],"experiments":[197],"on":[198],"four":[199],"mainstream":[200],"datasets,":[201],"i.e.,":[202],"MSR-VTT,":[203],"ActivityNet,":[204],"DiDeMo,":[205],"and":[206],"LSMDC,":[207],"demonstrate":[208],"our":[210],"method":[211],"achieves":[212],"state-of-the-art":[213]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2026-02-28T00:00:00"}