{"id":"https://openalex.org/W4415538374","doi":"https://doi.org/10.1145/3746027.3754858","title":"Visual Instance-aware Prompt Tuning","display_name":"Visual Instance-aware Prompt Tuning","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538374","doi":"https://doi.org/10.1145/3746027.3754858"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754858","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3754858","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3754858","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102340211","display_name":"Xi Xiao","orcid":"https://orcid.org/0009-0000-0931-6982"},"institutions":[{"id":"https://openalex.org/I32389192","display_name":"University of Alabama at Birmingham","ror":"https://ror.org/008s83205","country_code":"US","type":"education","lineage":["https://openalex.org/I32389192"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xi Xiao","raw_affiliation_strings":["University of Alabama at Brimingham, Birmingham, AL, USA"],"raw_orcid":"https://orcid.org/0009-0000-0931-6982","affiliations":[{"raw_affiliation_string":"University of Alabama at Brimingham, Birmingham, AL, USA","institution_ids":["https://openalex.org/I32389192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104139277","display_name":"Yunbei Zhang","orcid":"https://orcid.org/0009-0002-3092-5920"},"institutions":[{"id":"https://openalex.org/I114832834","display_name":"Tulane University","ror":"https://ror.org/04vmvtb21","country_code":"US","type":"education","lineage":["https://openalex.org/I114832834"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yunbei Zhang","raw_affiliation_strings":["Tulane University, New Orleans, Louisiana, USA"],"raw_orcid":"https://orcid.org/0009-0002-3092-5920","affiliations":[{"raw_affiliation_string":"Tulane University, New Orleans, Louisiana, USA","institution_ids":["https://openalex.org/I114832834"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100770663","display_name":"Xingjian Li","orcid":"https://orcid.org/0000-0001-8073-7552"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xingjian Li","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":"https://orcid.org/0000-0001-8073-7552","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100656834","display_name":"Tianyang Wang","orcid":"https://orcid.org/0000-0003-3184-0566"},"institutions":[{"id":"https://openalex.org/I32389192","display_name":"University of Alabama at Birmingham","ror":"https://ror.org/008s83205","country_code":"US","type":"education","lineage":["https://openalex.org/I32389192"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tianyang Wang","raw_affiliation_strings":["University of Alabama at Birmingham, Birmingham, Alabama, USA"],"raw_orcid":"https://orcid.org/0000-0003-3184-0566","affiliations":[{"raw_affiliation_string":"University of Alabama at Birmingham, Birmingham, Alabama, USA","institution_ids":["https://openalex.org/I32389192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100411431","display_name":"Xiao Wang","orcid":"https://orcid.org/0000-0001-6545-1943"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiao Wang","raw_affiliation_strings":["Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"raw_orcid":"https://orcid.org/0000-0001-6545-1943","affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035324352","display_name":"Yuxiang Wei","orcid":"https://orcid.org/0000-0001-6552-8912"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuxiang Wei","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":"https://orcid.org/0000-0001-6552-8912","affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085659523","display_name":"Jihun Hamm","orcid":"https://orcid.org/0000-0002-0680-0901"},"institutions":[{"id":"https://openalex.org/I114832834","display_name":"Tulane University","ror":"https://ror.org/04vmvtb21","country_code":"US","type":"education","lineage":["https://openalex.org/I114832834"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jihun Hamm","raw_affiliation_strings":["Tulane University, New Orleans, Louisiana, USA"],"raw_orcid":"https://orcid.org/0000-0002-0680-0901","affiliations":[{"raw_affiliation_string":"Tulane University, New Orleans, Louisiana, USA","institution_ids":["https://openalex.org/I114832834"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000807861","display_name":"Min Xu","orcid":"https://orcid.org/0000-0002-0881-5891"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Min Xu","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":"https://orcid.org/0000-0002-0881-5891","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2880","last_page":"2889"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9991999864578247,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9991999864578247,"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.995199978351593,"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/dimension","display_name":"Dimension (graph theory)","score":0.4577000141143799},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.42640000581741333},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.4154999852180481},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.41350001096725464},{"id":"https://openalex.org/keywords/principal-component-analysis","display_name":"Principal component analysis","score":0.41019999980926514},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.3887999951839447},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.3774999976158142}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7465000152587891},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6010000109672546},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.4577000141143799},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.42640000581741333},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4154999852180481},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.41350001096725464},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.41019999980926514},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4043000042438507},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.3887999951839447},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.3774999976158142},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3637000024318695},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3531000018119812},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.3305000066757202},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32739999890327454},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C2779200073","wikidata":"https://www.wikidata.org/wiki/Q18395575","display_name":"Visual masking","level":4,"score":0.2630999982357025},{"id":"https://openalex.org/C2986089797","wikidata":"https://www.wikidata.org/wiki/Q6501338","display_name":"Visual attention","level":3,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754858","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3754858","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":{"id":"doi:10.1145/3746027.3754858","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3754858","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1954152232","https://openalex.org/W2962935523","https://openalex.org/W2963446712","https://openalex.org/W4312310776","https://openalex.org/W4386083033","https://openalex.org/W4386897466","https://openalex.org/W4390874124","https://openalex.org/W4406098393"],"related_works":[],"abstract_inverted_index":{"Visual":[0,50],"Prompt":[1,52],"Tuning":[2,53],"(VPT)":[3],"has":[4],"emerged":[5],"as":[6],"a":[7,93,154],"parameter-efficient":[8],"fine-tuning":[9],"paradigm":[10,156],"for":[11,157,163],"vision":[12,164],"transformers,":[13],"with":[14,67],"conventional":[15],"approaches":[16],"utilizing":[17],"dataset-level":[18,68,125],"prompts":[19,58,110,162],"that":[20,30,83,146],"remain":[21],"the":[22,115,131],"same":[23],"across":[24,141],"all":[25],"input":[26,63],"instances.":[27],"We":[28],"observe":[29],"this":[31,46],"strategy":[32],"results":[33],"in":[34,41,96],"sub-optimal":[35],"performance":[36,113],"due":[37],"to":[38,75,100,137],"high":[39],"variance":[40],"downstream":[42],"datasets.":[43],"To":[44],"address":[45],"challenge,":[47],"we":[48,81],"propose":[49],"Instance-aware":[51],"(ViaPT),":[54],"which":[55,97],"generates":[56],"instance-aware":[57],"based":[59,91],"on":[60,92,109],"each":[61],"individual":[62],"and":[64,85,126,159],"fuses":[65],"them":[66],"prompts,":[69],"leveraging":[70],"Principal":[71],"Component":[72],"Analysis":[73],"(PCA)":[74],"retain":[76],"important":[77],"prompting":[78],"information.":[79],"Moreover,":[80],"reveal":[82],"VPT-Deep":[84],"VPT-Shallow":[86],"represent":[87],"two":[88,116],"corner":[89],"cases":[90],"conceptual":[94],"understanding,":[95],"they":[98],"fail":[99],"effectively":[101],"capture":[102],"instance-specific":[103],"information,":[104],"while":[105,129],"random":[106],"dimension":[107],"reduction":[108],"only":[111],"yields":[112],"between":[114],"extremes.":[117],"Instead,":[118],"ViaPT":[119],"overcomes":[120],"these":[121],"limitations":[122],"by":[123],"balancing":[124],"instance-level":[127],"knowledge,":[128],"reducing":[130],"amount":[132],"of":[133],"learnable":[134],"parameters":[135],"compared":[136],"VPT-Deep.":[138],"Extensive":[139],"experiments":[140],"34":[142],"diverse":[143],"datasets":[144],"demonstrate":[145],"our":[147],"method":[148],"consistently":[149],"outperforms":[150],"state-of-the-art":[151],"baselines,":[152],"establishing":[153],"new":[155],"analyzing":[158],"optimizing":[160],"visual":[161],"transformers.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}