{"id":"https://openalex.org/W7125766939","doi":"https://doi.org/10.1109/tcsvt.2026.3657756","title":"DHPT: Dual-Modality Heterogeneous Prompt Tuning for Online Test-Time Adaption in Vision-Language Models","display_name":"DHPT: Dual-Modality Heterogeneous Prompt Tuning for Online Test-Time Adaption in Vision-Language Models","publication_year":2026,"publication_date":"2026-01-27","ids":{"openalex":"https://openalex.org/W7125766939","doi":"https://doi.org/10.1109/tcsvt.2026.3657756"},"language":null,"primary_location":{"id":"doi:10.1109/tcsvt.2026.3657756","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3657756","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-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/A5123910889","display_name":"Guiqin Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guiqin Wang","raw_affiliation_strings":["National Engineering Laboratory for Big Data Analytics and the School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0002-3369-5043","affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Big Data Analytics and the School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124028402","display_name":"Peng Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Zhao","raw_affiliation_strings":["National Engineering Laboratory for Big Data Analytics and the School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0001-7033-9315","affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Big Data Analytics and the School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124051674","display_name":"Xiang Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Wang","raw_affiliation_strings":["Advanced Computing and Storage Laboratory, Huawei Technologies Company Ltd., Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Computing and Storage Laboratory, Huawei Technologies Company Ltd., Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123890939","display_name":"Haoran Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoran Guo","raw_affiliation_strings":["National Engineering Laboratory for Big Data Analytics and the School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Big Data Analytics and the School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123937271","display_name":"Nan Qi","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nan Qi","raw_affiliation_strings":["National Engineering Laboratory for Big Data Analytics and the School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an, China"],"raw_orcid":"https://orcid.org/0009-0005-7492-8308","affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Big Data Analytics and the School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123994285","display_name":"Shusen Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shusen Yang","raw_affiliation_strings":["National Engineering Laboratory for Big Data Analytics and the School of Mathematics and Statistics, Xi’an Jiaotong University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0002-4495-6237","affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Big Data Analytics and the School of Mathematics and Statistics, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123980757","display_name":"Qinghai Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinghai Guo","raw_affiliation_strings":["Advanced Computing and Storage Laboratory, Huawei Technologies Company Ltd., Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-4697-9464","affiliations":[{"raw_affiliation_string":"Advanced Computing and Storage Laboratory, Huawei Technologies Company Ltd., Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]}],"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":0.08839705,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"6","first_page":"8590","last_page":"8601"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.4948999881744385,"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":0.4948999881744385,"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":0.37619999051094055,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.04270000010728836,"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/leverage","display_name":"Leverage (statistics)","score":0.7922999858856201},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.6550999879837036},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.633899986743927},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5396999716758728},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.516700029373169},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.47690001130104065},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.46939998865127563},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.45500001311302185}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8325999975204468},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7922999858856201},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.6550999879837036},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.633899986743927},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5396999716758728},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5205000042915344},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.516700029373169},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4837999939918518},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.47690001130104065},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.46939998865127563},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.45500001311302185},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4278999865055084},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.3801000118255615},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.37369999289512634},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3562000095844269},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.33469998836517334},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.3278000056743622},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3249000012874603},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.32120001316070557},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C2989514635","wikidata":"https://www.wikidata.org/wiki/Q5164377","display_name":"Constrained optimization problem","level":3,"score":0.2662999927997589},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.25380000472068787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2026.3657756","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3657756","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5427951812744141,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W12634471","https://openalex.org/W1977295328","https://openalex.org/W2047643928","https://openalex.org/W2068704019","https://openalex.org/W2155904486","https://openalex.org/W2296864500","https://openalex.org/W2533598788","https://openalex.org/W2896457183","https://openalex.org/W2964194231","https://openalex.org/W3037492894","https://openalex.org/W3048593389","https://openalex.org/W3080883198","https://openalex.org/W3096719817","https://openalex.org/W3177096435","https://openalex.org/W3198377975","https://openalex.org/W4297697565","https://openalex.org/W4312310776","https://openalex.org/W4312897837","https://openalex.org/W4313175608","https://openalex.org/W4360993849","https://openalex.org/W4390872773","https://openalex.org/W4390874140","https://openalex.org/W4391136507","https://openalex.org/W4392172801","https://openalex.org/W4392426151","https://openalex.org/W4393160269","https://openalex.org/W4399526356","https://openalex.org/W4399568701","https://openalex.org/W4400767051","https://openalex.org/W4402703015","https://openalex.org/W4402716070","https://openalex.org/W4402727025","https://openalex.org/W4402774099","https://openalex.org/W4403780517","https://openalex.org/W4404175738","https://openalex.org/W4405754089","https://openalex.org/W4406171215","https://openalex.org/W4409129027","https://openalex.org/W4409262538","https://openalex.org/W4411799456","https://openalex.org/W4413157083","https://openalex.org/W4413344199","https://openalex.org/W4415709494","https://openalex.org/W4415797258","https://openalex.org/W4415797985","https://openalex.org/W7133232273"],"related_works":[],"abstract_inverted_index":{"Test-Time":[0],"Adaptation":[1],"(TTA)":[2],"has":[3,30],"recently":[4],"emerged":[5],"as":[6],"a":[7,49,66,88,110,130,146],"promising":[8],"research":[9],"direction,":[10],"enabling":[11],"vision-language":[12],"models":[13],"(VLMs)":[14],"to":[15,17,56,92,114],"adapt":[16],"unlabeled":[18],"test":[19],"data":[20],"in":[21,71,103],"zero-shot":[22],"settings.":[23],"Among":[24],"TTA":[25,177],"approaches,":[26],"test-time":[27,75],"prompt":[28,157],"tuning":[29,158],"shown":[31],"great":[32],"potential":[33],"for":[34,119,179],"enhancing":[35],"the":[36,104,120,125,152],"practical":[37],"applicability":[38],"of":[39,156],"VLMs.":[40,180],"However,":[41],"existing":[42,176],"methods":[43,178],"typically":[44],"either":[45],"focus":[46],"on":[47,124,165],"adapting":[48],"single":[50],"modality":[51],"or":[52],"apply":[53],"uniform":[54],"optimization":[55,63,148],"both":[57],"modalities,":[58],"without":[59],"explicitly":[60],"defining":[61],"modality-specific":[62],"objectives.":[64],"Such":[65],"one-size-fits-all":[67],"strategy":[68],"often":[69],"results":[70],"suboptimal":[72],"performance":[73],"under":[74,159],"conditions.":[76],"To":[77],"address":[78],"this":[79],"limitation,":[80],"we":[81,108,128,144],"propose":[82],"Dual-modality":[83],"Heterogeneous":[84],"Prompt":[85],"Tuning":[86],"(DHPT),":[87],"novel":[89],"framework":[90],"designed":[91],"simultaneously":[93],"capture":[94],"fine-grained":[95],"textual":[96,116],"semantics":[97],"and":[98,154,173],"alleviate":[99],"domain":[100,137],"shift":[101,138],"noise":[102,139],"visual":[105],"modality.":[106],"Specifically,":[107],"leverage":[109],"large":[111],"language":[112],"model":[113],"provide":[115],"cognition":[117],"guidance":[118],"text":[121],"encoder,":[122],"while":[123],"vision":[126],"side,":[127],"develop":[129],"lightweight":[131],"calibration":[132],"module":[133],"that":[134,150,170],"adaptively":[135],"mitigates":[136],"across":[140],"different":[141],"scales.":[142],"Furthermore,":[143],"introduce":[145],"cluster-tight":[147],"objective":[149],"enhances":[151],"stability":[153],"generalizability":[155],"distribution":[160],"shifts.":[161],"Extensive":[162],"experiments":[163],"conducted":[164],"11":[166],"benchmark":[167],"datasets":[168],"demonstrate":[169],"DHPT":[171],"consistently":[172],"significantly":[174],"outperforms":[175]},"counts_by_year":[],"updated_date":"2026-06-07T06:13:29.825681","created_date":"2026-01-28T00:00:00"}