{"id":"https://openalex.org/W4403791665","doi":"https://doi.org/10.1145/3664647.3680839","title":"MPT: Multi-grained Prompt Tuning for Text-Video Retrieval","display_name":"MPT: Multi-grained Prompt Tuning for Text-Video Retrieval","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791665","doi":"https://doi.org/10.1145/3664647.3680839"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680839","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680839","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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":["University of Electronic Science and Technology of China, Sichuan, China"],"raw_orcid":"https://orcid.org/0000-0003-1015-7338","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Sichuan, 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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pengpeng Zeng","raw_affiliation_strings":["Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen, 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, Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066645546","display_name":"Lianli Gao","orcid":"https://orcid.org/0000-0002-2522-6394"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lianli Gao","raw_affiliation_strings":["Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen, 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, Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036987388","display_name":"Jingkuan Song","orcid":"https://orcid.org/0000-0002-2549-8322"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingkuan Song","raw_affiliation_strings":["Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen, 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, Shenzhen, China","institution_ids":[]}]},{"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/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]},{"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":["University of Electronic Science and Technology of China & Tongji University, Sichuan, China"],"raw_orcid":"https://orcid.org/0000-0002-2999-2088","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China & Tongji University, Sichuan, China","institution_ids":["https://openalex.org/I116953780","https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1206","last_page":"1214"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9991000294685364,"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":0.996999979019165,"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":0.7566119432449341},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4838332235813141},{"id":"https://openalex.org/keywords/video-retrieval","display_name":"Video retrieval","score":0.41825318336486816},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3332226276397705}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7566119432449341},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4838332235813141},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.41825318336486816},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3332226276397705}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3680839","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680839","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2885775891","https://openalex.org/W2963017553","https://openalex.org/W2984008963","https://openalex.org/W3043840704","https://openalex.org/W3098071563","https://openalex.org/W3113151582","https://openalex.org/W3168640669","https://openalex.org/W3173223111","https://openalex.org/W3184735396","https://openalex.org/W3198377975","https://openalex.org/W3204588463","https://openalex.org/W3205021045","https://openalex.org/W4214931087","https://openalex.org/W4225323055","https://openalex.org/W4282005462","https://openalex.org/W4285191490","https://openalex.org/W4285606530","https://openalex.org/W4298083345","https://openalex.org/W4304099166","https://openalex.org/W4312614039","https://openalex.org/W4312651322","https://openalex.org/W4313011746","https://openalex.org/W4319299894","https://openalex.org/W4320086306","https://openalex.org/W4385767942","https://openalex.org/W4385804899","https://openalex.org/W4385895960","https://openalex.org/W4386076600","https://openalex.org/W4386523254","https://openalex.org/W4387967944","https://openalex.org/W4387967980","https://openalex.org/W4390871861","https://openalex.org/W4390873546","https://openalex.org/W4401307360","https://openalex.org/W4403792529"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2333966947","https://openalex.org/W2399947890"],"abstract_inverted_index":{"Recently,":[0],"significant":[1],"advancements":[2],"have":[3],"been":[4],"made":[5],"in":[6],"supporting":[7],"text-video":[8,68,108],"retrieval":[9,69],"by":[10,48],"transferring":[11],"large-scale":[12],"image-text":[13,149],"pre-training":[14],"models":[15],"through":[16,174],"model":[17,39,151],"adaptation,":[18],"i.e.,":[19,188],"full":[20,30],"fine-tuning,":[21],"or":[22],"prompt":[23,41,57],"tuning,":[24],"a":[25,51,102,112,131,161],"parameter-efficient":[26],"fine-tuning":[27,31],"strategy.":[28],"While":[29],"involves":[32],"high":[33],"computational":[34,205],"costs,":[35],"particularly":[36],"with":[37,125,203],"increasing":[38],"size,":[40],"tuning":[42,58],"offers":[43],"greater":[44],"flexibility":[45],"and":[46,64,92,139,179,192],"efficiency":[47],"adjusting":[49],"only":[50],"few":[52],"learnable":[53],"parameters.":[54],"However,":[55],"current":[56],"methods":[59,202],"rely":[60],"on":[61,184],"coarse":[62],"visual":[63],"textual":[65,172],"cues":[66],"for":[67,107],"task,":[70],"neglecting":[71],"the":[72,77,88,144,148,175],"domain-specific":[73],"features":[74],"when":[75],"performing":[76],"adaptation.":[78],"This":[79],"approach":[80],"may":[81],"lead":[82],"to":[83,87,117,142],"sub-optimal":[84],"performance":[85],"due":[86],"incorporation":[89],"of":[90,114,171,177],"irrelevant":[91],"indiscriminate":[93],"knowledge.":[94],"To":[95],"address":[96],"such":[97],"an":[98],"issue,":[99],"we":[100,129,159],"present":[101],"Multi-grained":[103],"Prompt":[104],"Tuning":[105],"(MPT)":[106],"retrieval,":[109],"that":[110,135,195],"designs":[111],"variety":[113],"specific":[115],"prompts":[116,141],"effectively":[118],"explore":[119],"semantic":[120],"interaction":[121],"across":[122],"different":[123],"modalities":[124],"diverse":[126],"granularity.":[127],"Specifically,":[128],"devise":[130],"multi-grained":[132,163],"video":[133],"encoder":[134,165],"employs":[136],"spatial,":[137],"temporal,":[138],"global":[140],"transfer":[143],"base-generic":[145],"knowledge":[146],"from":[147],"pre-trained":[150],"while":[152],"comprehensively":[153],"excavating":[154],"determinative":[155],"video-specific":[156],"characteristics.":[157],"Meanwhile,":[158],"introduce":[160],"novel":[162],"text":[164],"aimed":[166],"at":[167],"capturing":[168],"various":[169],"levels":[170],"clues":[173],"utilization":[176],"word":[178],"phrase":[180],"prompts.":[181],"Extensive":[182],"experiments":[183],"four":[185],"benchmark":[186],"datasets,":[187],"MSR-VTT,":[189],"ActivityNet,":[190],"DiDeMo,":[191],"LSMDC,":[193],"demonstrate":[194],"MPT":[196],"achieves":[197],"outstanding":[198],"performance,":[199],"surpassing":[200],"state-of-the-art":[201],"negligible":[204],"cost.":[206],"The":[207],"codebase":[208],"is":[209],"publicly":[210],"available":[211],"at:":[212],"https://github.com/zchoi/MPT.":[213]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":5}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}