{"id":"https://openalex.org/W4415540172","doi":"https://doi.org/10.1145/3746027.3755636","title":"AttriPrompt: Dynamic Prompt Composition Learning for CLIP","display_name":"AttriPrompt: Dynamic Prompt Composition Learning for CLIP","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540172","doi":"https://doi.org/10.1145/3746027.3755636"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755636","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755636","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-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/A5120132281","display_name":"Qiqi Zhan","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qiqi Zhan","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056107157","display_name":"Shiwei Li","orcid":"https://orcid.org/0000-0002-8765-9283"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiwei Li","raw_affiliation_strings":["Hangzhou Innovation Institute, Beihang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Hangzhou Innovation Institute, Beihang University, Hangzhou, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056847110","display_name":"Qingjie Liu","orcid":"https://orcid.org/0000-0002-5181-6451"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingjie Liu","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100398953","display_name":"Yunhong Wang","orcid":"https://orcid.org/0000-0001-8001-2703"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunhong Wang","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5120132281"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":2.856,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.92417327,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4856","last_page":"4865"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9980999827384949,"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":0.9980999827384949,"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":0.9941999912261963,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9889000058174133,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.7857999801635742},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.526199996471405},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.4977000057697296},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.45879998803138733},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4368000030517578},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.4124000072479248},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3605000078678131}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8004000186920166},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7857999801635742},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6251999735832214},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.526199996471405},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.4977000057697296},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.45879998803138733},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4368000030517578},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.4124000072479248},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40610000491142273},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36719998717308044},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3605000078678131},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.32100000977516174},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.3138999938964844},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.31200000643730164},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29499998688697815},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.27390000224113464}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755636","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755636","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1977295328","https://openalex.org/W2047643928","https://openalex.org/W2108598243","https://openalex.org/W2138011018","https://openalex.org/W2155904486","https://openalex.org/W2194775991","https://openalex.org/W2533598788","https://openalex.org/W2964194231","https://openalex.org/W3037492894","https://openalex.org/W3177096435","https://openalex.org/W3198377975","https://openalex.org/W4226058394","https://openalex.org/W4310557340","https://openalex.org/W4312310776","https://openalex.org/W4312420092","https://openalex.org/W4312935996","https://openalex.org/W4386071547","https://openalex.org/W4386254667","https://openalex.org/W4386790226","https://openalex.org/W4390872773","https://openalex.org/W4390873161","https://openalex.org/W4390873312","https://openalex.org/W4390873714"],"related_works":[],"abstract_inverted_index":{"The":[0,90,179],"evolution":[1],"of":[2,9,72,109,182],"prompt":[3,11,100],"learning":[4,31],"methodologies":[5],"has":[6],"driven":[7],"exploration":[8],"deeper":[10],"designs":[12],"to":[13,106,130,152,172],"enhance":[14],"model":[15],"performance.":[16],"However,":[17],"current":[18],"deep":[19],"text":[20,114,123,150],"prompting":[21],"approaches":[22],"suffer":[23],"from":[24,87,98],"two":[25],"critical":[26],"limitations:":[27],"Over-reliance":[28],"on":[29,155],"constrastive":[30],"objectives":[32],"that":[33,60,82],"prioritize":[34],"high-level":[35],"semantic":[36,65],"alignment,":[37],"neglecting":[38],"fine-grained":[39,132],"feature":[40],"optimization;":[41],"Static":[42],"prompts":[43,97],"across":[44,161],"all":[45],"input":[46,108],"categories,":[47],"preventing":[48],"content-aware":[49],"adaptation.":[50],"To":[51],"address":[52],"these":[53],"limitations,":[54],"we":[55,125,135],"propose":[56],"AttriPrompt-a":[57],"novel":[58],"framework":[59],"enhances":[61],"and":[62,148],"refines":[63],"textual":[64],"representations":[66],"by":[67,140],"leveraging":[68],"the":[69,107,113,146,176],"intermediate-layer":[70],"features":[71,86,93,151],"CLIP's":[73],"vision":[74],"encoder.":[75,115],"We":[76],"designed":[77],"an":[78],"Attribute":[79],"Retrieval":[80],"module":[81],"first":[83],"clusters":[84],"visual":[85,92,118],"each":[88],"layer.":[89],"aggregated":[91],"retrieve":[94],"semantically":[95],"similar":[96],"a":[99,137],"pool,":[101],"which":[102],"are":[103],"then":[104],"concatenated":[105],"every":[110],"layer":[111],"in":[112,121,175,185],"Leveraging":[116],"hierarchical":[117],"information":[119],"embedded":[120],"prompted":[122,147],"features,":[124],"introduce":[126,136],"Dual-stream":[127],"Contrastive":[128],"Learning":[129],"realize":[131],"alignment.":[133],"Furthermore,":[134],"Self-Regularization":[138],"mechanism":[139],"applying":[141],"explicit":[142],"regularization":[143],"constraints":[144],"between":[145],"non-prompted":[149],"prevent":[153],"overfitting":[154],"limited":[156],"training":[157],"data.":[158],"Extensive":[159],"experiments":[160],"three":[162],"benchmarks":[163],"demonstrate":[164],"AttriPrompt's":[165],"superiority":[166],"over":[167],"state-of-the-art":[168],"methods,":[169],"achieving":[170],"up":[171],"7.37%":[173],"improvement":[174],"base-to-novel":[177],"setting.":[178],"observed":[180],"strength":[181],"our":[183],"method":[184],"cross-domain":[186],"knowledge":[187],"transfer":[188],"positions":[189],"vision-language":[190],"pre-trained":[191],"models":[192],"as":[193],"more":[194],"viable":[195],"solutions":[196],"for":[197],"real-world":[198],"implementation.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-25T00:00:00"}