{"id":"https://openalex.org/W4413278173","doi":"https://doi.org/10.1109/icip55913.2025.11084554","title":"GIP: Gated Interaction Prompt for Parameter Efficient Vision-Language Fine-Tuning","display_name":"GIP: Gated Interaction Prompt for Parameter Efficient Vision-Language Fine-Tuning","publication_year":2025,"publication_date":"2025-08-18","ids":{"openalex":"https://openalex.org/W4413278173","doi":"https://doi.org/10.1109/icip55913.2025.11084554"},"language":"en","primary_location":{"id":"doi:10.1109/icip55913.2025.11084554","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip55913.2025.11084554","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Image Processing (ICIP)","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/A5101835173","display_name":"Xiang Lin","orcid":"https://orcid.org/0009-0003-5234-880X"},"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":"Xiang Lin","raw_affiliation_strings":["Beihang University,SKLCCSE,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University,SKLCCSE,Beijing,China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100662467","display_name":"Weixin Li","orcid":"https://orcid.org/0000-0002-5093-5635"},"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":"Weixin Li","raw_affiliation_strings":["SCSE, Beihang University,IRIP Lab,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SCSE, Beihang University,IRIP Lab,Beijing,China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101856560","display_name":"Shu Guo","orcid":"https://orcid.org/0000-0002-6200-4934"},"institutions":[{"id":"https://openalex.org/I4210087772","display_name":"National Computer Network Emergency Response Technical Team/Coordination Center of Chinar","ror":"https://ror.org/00247dh76","country_code":"CN","type":"nonprofit","lineage":["https://openalex.org/I4210087772"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shu Guo","raw_affiliation_strings":["National Computer Network Emergency Response Technical Team/Coordination Center of China,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Computer Network Emergency Response Technical Team/Coordination Center of China,Beijing,China","institution_ids":["https://openalex.org/I4210087772"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100443578","display_name":"Lihong Wang","orcid":"https://orcid.org/0000-0003-0179-2364"},"institutions":[{"id":"https://openalex.org/I4210087772","display_name":"National Computer Network Emergency Response Technical Team/Coordination Center of Chinar","ror":"https://ror.org/00247dh76","country_code":"CN","type":"nonprofit","lineage":["https://openalex.org/I4210087772"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lihong Wang","raw_affiliation_strings":["National Computer Network Emergency Response Technical Team/Coordination Center of China,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Computer Network Emergency Response Technical Team/Coordination Center of China,Beijing,China","institution_ids":["https://openalex.org/I4210087772"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006464250","display_name":"Di Huang","orcid":"https://orcid.org/0000-0001-5059-1185"},"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":"Di Huang","raw_affiliation_strings":["Beihang University,SKLCCSE,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University,SKLCCSE,Beijing,China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25851531,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"617","last_page":"622"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13382","display_name":"Robotics and Automated Systems","score":0.9921000003814697,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13382","display_name":"Robotics and Automated Systems","score":0.9921000003814697,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9115999937057495,"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":0.9010999798774719,"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":0.6992026567459106},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.425496369600296},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.39272183179855347}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6992026567459106},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.425496369600296},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39272183179855347}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip55913.2025.11084554","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip55913.2025.11084554","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334978","display_name":"Beijing Nova Program","ror":"https://ror.org/034k14f91"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2560730294","https://openalex.org/W2963518342","https://openalex.org/W2963530300","https://openalex.org/W3034999214","https://openalex.org/W3174770825","https://openalex.org/W3176828726","https://openalex.org/W3198377975","https://openalex.org/W3206816211","https://openalex.org/W4312310776","https://openalex.org/W4312651322","https://openalex.org/W4312784228","https://openalex.org/W4312884055","https://openalex.org/W4313156423","https://openalex.org/W4322766882","https://openalex.org/W4382463911","https://openalex.org/W4385245566","https://openalex.org/W4386071547","https://openalex.org/W4386071687","https://openalex.org/W4390874513"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Existing":[0],"Parameter":[1],"Efficient":[2],"Fine-Tuning":[3],"(PEFT)":[4],"methods":[5,22,140],"in":[6,17,160],"vision-language":[7],"(VL)":[8],"domains,":[9],"primarily":[10],"adapted":[11],"from":[12],"single-modality":[13],"approaches,":[14],"face":[15],"limitations":[16],"modeling":[18],"cross-modal":[19,101],"interactions.":[20],"These":[21],"often":[23],"unify":[24],"visual":[25,75,86],"and":[26,76,87,111,141,152,171,180],"textual":[27,77,88],"features":[28,89],"without":[29],"explicit":[30],"modality-specific":[31],"processing,":[32],"or":[33],"rely":[34],"on":[35,127,149],"unidirectional":[36],"interaction,":[37],"leading":[38],"to":[39,64,109,177],"suboptimal":[40],"task":[41],"adaptation":[42,63],"for":[43,100],"pre-trained":[44],"Vision-Language":[45],"Models":[46],"(VLMs).":[47],"To":[48],"address":[49],"this":[50],"issue,":[51],"we":[52],"propose":[53],"a":[54,61,98,157],"Gated":[55],"Interaction":[56],"Prompt":[57],"(GIP)":[58],"module":[59,81],"as":[60,97],"plug-and-play":[62],"existing":[65,139],"PEFT":[66],"methods,":[67],"which":[68],"effectively":[69],"enhances":[70],"the":[71,91,113],"two-way":[72],"interaction":[73],"between":[74],"features.":[78],"Our":[79],"GIP":[80,104],"integrates":[82],"learnable":[83],"prompts":[84,116],"alongside":[85],"into":[90],"attention":[92],"layers":[93],"of":[94,115,168],"VLMs,":[95],"serving":[96],"bridge":[99],"interaction.":[102],"Furthermore,":[103],"introduces":[105],"task-specific":[106],"gating":[107],"mechanisms":[108],"regulate":[110],"adapt":[112],"influence":[114],"across":[117,173],"different":[118],"tasks,":[119],"thereby":[120],"further":[121],"enhancing":[122],"model":[123],"performance.":[124],"Extensive":[125],"experiments":[126],"four":[128,174],"VL":[129],"tasks":[130],"demonstrate":[131],"that":[132],"our":[133,163],"approach":[134],"can":[135],"seamlessly":[136],"integrate":[137],"with":[138,146],"achieves":[142,165],"significant":[143],"performance":[144,166],"improvements":[145],"minimal":[147],"impact":[148],"parameter":[150],"counts":[151],"computational":[153],"costs.":[154],"With":[155],"only":[156],"0.02%":[158],"increase":[159],"trainable":[161],"parameters,":[162],"method":[164],"gains":[167],"0.6%,":[169],"0.8%,":[170],"1.2%":[172],"tasks\u2014when":[175],"applied":[176],"VL-PET,":[178],"VL-Adapter,":[179],"LoRA,":[181],"respectively.":[182]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}