{"id":"https://openalex.org/W4399418385","doi":"https://doi.org/10.1145/3652583.3658049","title":"Progressive Multi-modal Conditional Prompt Tuning","display_name":"Progressive Multi-modal Conditional Prompt Tuning","publication_year":2024,"publication_date":"2024-05-30","ids":{"openalex":"https://openalex.org/W4399418385","doi":"https://doi.org/10.1145/3652583.3658049"},"language":"en","primary_location":{"id":"doi:10.1145/3652583.3658049","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658049","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658049","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658049","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5099043531","display_name":"Xiaoyu Qiu","orcid":"https://orcid.org/0000-0002-0966-2006"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaoyu Qiu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0002-0966-2006","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068201443","display_name":"Hao Feng","orcid":"https://orcid.org/0000-0001-8127-6639"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Feng","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0001-8127-6639","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049116027","display_name":"Yuechen Wang","orcid":"https://orcid.org/0000-0003-0965-584X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuechen Wang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0003-0965-584X","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046805800","display_name":"Wengang Zhou","orcid":"https://orcid.org/0000-0003-1690-9836"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wengang Zhou","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0003-1690-9836","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078141810","display_name":"Houqiang Li","orcid":"https://orcid.org/0000-0003-2188-3028"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Houqiang Li","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0003-2188-3028","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5099043531"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.9523,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.75229492,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"46","last_page":"54"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9993000030517578,"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/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":0.7910423278808594},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.7366763353347778},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5803887248039246},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.541507363319397},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5380264520645142},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5289304852485657},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4952296316623688},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.4439130425453186},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.43632978200912476},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4253949522972107},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4207262694835663},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3918799161911011},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3622656464576721}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7910423278808594},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.7366763353347778},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5803887248039246},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.541507363319397},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5380264520645142},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5289304852485657},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4952296316623688},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.4439130425453186},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.43632978200912476},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4253949522972107},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4207262694835663},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3918799161911011},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3622656464576721},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3652583.3658049","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658049","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658049","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3652583.3658049","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658049","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658049","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399418385.pdf","grobid_xml":"https://content.openalex.org/works/W4399418385.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W12634471","https://openalex.org/W1977295328","https://openalex.org/W2017814585","https://openalex.org/W2047643928","https://openalex.org/W2138011018","https://openalex.org/W2166049352","https://openalex.org/W2533598788","https://openalex.org/W2970476646","https://openalex.org/W2982756474","https://openalex.org/W3037492894","https://openalex.org/W3167602185","https://openalex.org/W3177096435","https://openalex.org/W3196731672","https://openalex.org/W4205991051","https://openalex.org/W4239072543","https://openalex.org/W4283379644","https://openalex.org/W4283385403","https://openalex.org/W4312480274","https://openalex.org/W4312651322","https://openalex.org/W4312747482","https://openalex.org/W4379929050","https://openalex.org/W4386065763","https://openalex.org/W4386071547","https://openalex.org/W4390873714","https://openalex.org/W6714454088"],"related_works":["https://openalex.org/W3204184292","https://openalex.org/W3176564347","https://openalex.org/W1985458517","https://openalex.org/W2355833770","https://openalex.org/W3031039437","https://openalex.org/W183202219","https://openalex.org/W3095877357","https://openalex.org/W2072565696","https://openalex.org/W2050451745","https://openalex.org/W2378903222"],"abstract_inverted_index":{"Pre-trained":[0],"vision-language":[1,41],"models":[2],"(VLMs)":[3],"have":[4,58],"shown":[5],"remarkable":[6],"generalization":[7,234],"capabilities":[8],"via":[9,155],"prompting,":[10,30,136,139],"which":[11,31],"leverages":[12],"VLMs":[13],"as":[14],"knowledge":[15],"bases":[16],"to":[17,38,53,126,162,181,189,202,212],"extract":[18],"information":[19],"beneficial":[20],"for":[21,108],"downstream":[22],"tasks.":[23],"However,":[24],"existing":[25,224],"methods":[26,225],"primarily":[27],"employ":[28],"uni-modal":[29,35],"only":[32],"engages":[33],"a":[34,59,67,78,99,114,118,156,178],"branch,":[36],"failing":[37],"simultaneously":[39],"adjust":[40],"(V-L)":[42],"features.":[43],"Additionally,":[44],"the":[45,214],"one-pass":[46],"forward":[47],"pipeline":[48],"in":[49,209],"VLM":[50],"encoding":[51,92,109],"struggles":[52],"align":[54],"V-L":[55,84,193],"features":[56,85,124,154,161,174,194],"that":[57,121,185,221],"huge":[60],"gap.":[61],"Confronting":[62],"these":[63],"challenges,":[64],"we":[65],"propose":[66],"novel":[68],"method,":[69],"Progressive":[70],"Multi-modal":[71],"conditional":[72],"Prompt":[73],"Tuning":[74],"(ProMPT).":[75],"ProMPT":[76,222],"exploits":[77],"recurrent":[79],"structure,":[80],"optimizing":[81],"and":[82,90,98,111,140,235],"aligning":[83],"by":[86,117],"iteratively":[87],"utilizing":[88],"image":[89,160,173],"current":[91],"information.":[93],"It":[94],"comprises":[95],"an":[96],"initialization":[97],"multi-modal":[100,131],"iterative":[101],"evolution":[102],"(MIE)":[103],"module.":[104],"Initialization":[105],"is":[106,238],"responsible":[107],"images":[110],"text":[112,123,138,153,179,183],"using":[113],"VLM,":[115],"followed":[116],"feature":[119,141],"filter":[120],"selects":[122],"similar":[125],"image.":[127],"MIE":[128,145],"then":[129],"facilitates":[130],"prompting":[132],"through":[133],"class-conditional":[134],"vision":[135,147,157,169],"instance-conditional":[137],"filtering.":[142],"In":[143],"each":[144],"iteration,":[146],"prompts":[148,184],"are":[149,175,186,195,207],"obtained":[150],"from":[151,200],"filtered":[152],"generator,":[158],"promoting":[159],"focus":[163],"more":[164,187],"on":[165,226],"target":[166],"object":[167],"during":[168],"prompting.":[170],"The":[171,218],"encoded":[172],"fed":[176],"into":[177],"generator":[180],"produce":[182],"robust":[188],"class":[190],"shifts.":[191],"Thus,":[192],"progressively":[196],"aligned,":[197],"enabling":[198],"advance":[199],"coarse":[201],"exact":[203],"prediction.":[204],"Extensive":[205],"experiments":[206],"conducted":[208],"three":[210],"settings":[211],"evaluate":[213],"efficacy":[215],"of":[216],"ProMPT.":[217],"results":[219],"indicate":[220],"outperforms":[223],"average":[227],"across":[228],"all":[229],"settings,":[230],"demonstrating":[231],"its":[232],"superior":[233],"robustness.":[236],"Code":[237],"available":[239],"at":[240],"https://github.com/qiuxiaoyu9954/ProMPT.":[241]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}