{"id":"https://openalex.org/W4400679250","doi":"https://doi.org/10.1109/tcsvt.2024.3429192","title":"Ump: Unified Modality-Aware Prompt Tuning for Text-Video Retrieval","display_name":"Ump: Unified Modality-Aware Prompt Tuning for Text-Video Retrieval","publication_year":2024,"publication_date":"2024-07-16","ids":{"openalex":"https://openalex.org/W4400679250","doi":"https://doi.org/10.1109/tcsvt.2024.3429192"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2024.3429192","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3429192","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","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/A5084439574","display_name":"Haonan Zhang","orcid":"https://orcid.org/0000-0003-1015-7338"},"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":"Haonan Zhang","raw_affiliation_strings":["Center for Future Media and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0003-1015-7338","affiliations":[{"raw_affiliation_string":"Center for Future Media and the 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/A5087623065","display_name":"Pengpeng Zeng","orcid":"https://orcid.org/0000-0002-0672-3790"},"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":"Pengpeng Zeng","raw_affiliation_strings":["Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-0672-3790","affiliations":[{"raw_affiliation_string":"Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066645546","display_name":"Lianli Gao","orcid":"https://orcid.org/0000-0002-2522-6394"},"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":"Lianli Gao","raw_affiliation_strings":["Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-2522-6394","affiliations":[{"raw_affiliation_string":"Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036987388","display_name":"Jingkuan Song","orcid":"https://orcid.org/0000-0002-2549-8322"},"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":"Jingkuan Song","raw_affiliation_strings":["Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-2549-8322","affiliations":[{"raw_affiliation_string":"Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052993469","display_name":"Heng Tao Shen","orcid":"https://orcid.org/0000-0002-2999-2088"},"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":"Heng Tao Shen","raw_affiliation_strings":["Center for Future Media and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-2999-2088","affiliations":[{"raw_affiliation_string":"Center for Future Media and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":1.656,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.84324581,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"34","issue":"11","first_page":"11954","last_page":"11964"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9983999729156494,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9983999729156494,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9983000159263611,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9975000023841858,"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":0.7379649877548218},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.7082557082176208},{"id":"https://openalex.org/keywords/video-retrieval","display_name":"Video retrieval","score":0.5006346702575684},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4733835756778717},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3987799882888794},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3417716920375824},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3266845941543579}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7379649877548218},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.7082557082176208},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.5006346702575684},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4733835756778717},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3987799882888794},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3417716920375824},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3266845941543579}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2024.3429192","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3429192","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G2546663186","display_name":null,"funder_award_id":"62020106008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G259376912","display_name":null,"funder_award_id":"YYJC012022019","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5422811002","display_name":null,"funder_award_id":"U23A20315","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6864684409","display_name":null,"funder_award_id":"62122018","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":74,"referenced_works":["https://openalex.org/W1893116441","https://openalex.org/W1927052826","https://openalex.org/W1969198793","https://openalex.org/W1981723314","https://openalex.org/W2425121537","https://openalex.org/W2753311918","https://openalex.org/W2786672974","https://openalex.org/W2808399042","https://openalex.org/W2885775891","https://openalex.org/W2908510526","https://openalex.org/W2956018683","https://openalex.org/W2963017553","https://openalex.org/W2964214371","https://openalex.org/W2965458216","https://openalex.org/W2984008963","https://openalex.org/W3035635319","https://openalex.org/W3043840704","https://openalex.org/W3047922786","https://openalex.org/W3102887392","https://openalex.org/W3173223111","https://openalex.org/W3174873881","https://openalex.org/W3176799298","https://openalex.org/W3185341429","https://openalex.org/W3198377975","https://openalex.org/W3200114289","https://openalex.org/W3204588463","https://openalex.org/W4210900713","https://openalex.org/W4211053420","https://openalex.org/W4212819272","https://openalex.org/W4224545477","https://openalex.org/W4229453513","https://openalex.org/W4285606530","https://openalex.org/W4296437558","https://openalex.org/W4306313147","https://openalex.org/W4312299780","https://openalex.org/W4312372711","https://openalex.org/W4312383773","https://openalex.org/W4312480274","https://openalex.org/W4312651322","https://openalex.org/W4312884055","https://openalex.org/W4313055276","https://openalex.org/W4313887138","https://openalex.org/W4384161812","https://openalex.org/W4385767942","https://openalex.org/W4385895960","https://openalex.org/W4386076265","https://openalex.org/W4386076600","https://openalex.org/W4386790226","https://openalex.org/W4387967944","https://openalex.org/W4390075233","https://openalex.org/W4390874542","https://openalex.org/W4398230671","https://openalex.org/W4402703062","https://openalex.org/W4402727025","https://openalex.org/W4402754025","https://openalex.org/W6726497184","https://openalex.org/W6748816842","https://openalex.org/W6757817989","https://openalex.org/W6759579507","https://openalex.org/W6766582784","https://openalex.org/W6778883912","https://openalex.org/W6785440099","https://openalex.org/W6790019176","https://openalex.org/W6791353385","https://openalex.org/W6797148833","https://openalex.org/W6801567822","https://openalex.org/W6802744804","https://openalex.org/W6809591836","https://openalex.org/W6810452849","https://openalex.org/W6838701581","https://openalex.org/W6846004651","https://openalex.org/W6846822233","https://openalex.org/W6868225046","https://openalex.org/W6872269894"],"related_works":["https://openalex.org/W2385859805","https://openalex.org/W2530972254","https://openalex.org/W2374013449","https://openalex.org/W73545470","https://openalex.org/W2364381299","https://openalex.org/W2374430585","https://openalex.org/W2399947890","https://openalex.org/W655728004","https://openalex.org/W2046272293","https://openalex.org/W2310544549"],"abstract_inverted_index":{"Prompt":[0,90,102],"tuning,":[1],"an":[2],"emerging":[3],"parameter-efficient":[4],"strategy,":[5],"leverages":[6],"the":[7,72,113,137,169],"powerful":[8],"knowledge":[9],"of":[10,74,115],"large-scale":[11],"pre-trained":[12,68],"image-text":[13],"models":[14],"(e.g.,":[15],"CLIP)":[16],"to":[17,20,29,43,52,106,156,188],"swiftly":[18],"adapt":[19],"downstream":[21],"tasks.":[22],"Despite":[23],"its":[24],"effectiveness,":[25],"adapting":[26],"prompt":[27,41,44,110,126,166],"tuning":[28],"text-video":[30,94],"retrieval":[31],"encounters":[32],"two":[33,39,45,132,141],"limitations:":[34],"i)":[35],"existing":[36,189],"methods":[37,191],"adopt":[38],"isolated":[40],"tokens":[42,127,164,167],"modal":[46],"branches":[47,133],"separately,":[48],"making":[49],"it":[50],"challenging":[51],"learn":[53],"a":[54,66,82,100,144,150],"well-aligned":[55],"unified":[56],"representation,":[57],"i.e.,":[58],"modality":[59],"gap;":[60],"ii)":[61],"video":[62,121,163],"encoders":[63],"typically":[64],"utilize":[65],"fixed":[67],"visual":[69],"backbone,":[70],"neglecting":[71],"incorporation":[73],"spatial-temporal":[75,170],"information.":[76],"To":[77],"this":[78],"end,":[79],"we":[80,97,148],"propose":[81],"simple":[83],"yet":[84],"effective":[85],"method,":[86],"named":[87],"Unified":[88,101],"Modality-aware":[89],"Tuning":[91],"(UMP),":[92],"for":[93],"retrieval.":[95],"Concretely,":[96],"first":[98],"introduce":[99],"Generation":[103],"(UPG)":[104],"module":[105,155],"dynamically":[107],"produce":[108],"modality-aware":[109],"tokens,":[111],"enabling":[112],"perception":[114],"prior":[116],"semantic":[117],"information":[118],"on":[119,175],"both":[120,158],"and":[122,160,165],"text":[123],"inputs.":[124],"These":[125],"are":[128],"simultaneously":[129],"injected":[130],"into":[131],"that":[134,181],"can":[135],"bridge":[136],"semantics":[138],"gap":[139],"between":[140],"modalities":[142],"in":[143,168],"unified-adjusting":[145],"manner.":[146],"Then,":[147],"design":[149],"parameter-free":[151],"Spatial-Temporal":[152],"Shift":[153],"(STS)":[154],"facilitate":[157],"intra-":[159],"inter-communication":[161],"among":[162],"dimension.":[171],"Notably,":[172],"extensive":[173],"experiments":[174],"four":[176],"widely":[177],"used":[178],"benchmarks":[179],"show":[180],"UMP":[182],"achieves":[183],"new":[184],"state-of-the-art":[185],"performance":[186],"compared":[187],"prompt-tuning":[190],"without":[192],"bringing":[193],"excessive":[194],"parameters.":[195],"Code":[196],"is":[197],"available":[198],"at:":[199],"<uri":[200],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[201],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/zchoi/UMP_TVR</uri>.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7}],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2025-10-10T00:00:00"}