{"id":"https://openalex.org/W4417434120","doi":"https://doi.org/10.1109/iccv51701.2025.00184","title":"Hierarchical Cross-Modal Prompt Learning for Vision-Language Models","display_name":"Hierarchical Cross-Modal Prompt Learning for Vision-Language Models","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417434120","doi":"https://doi.org/10.1109/iccv51701.2025.00184"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00184","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00184","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.14976","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085132445","display_name":"Hao Zheng","orcid":"https://orcid.org/0000-0003-0829-9660"},"institutions":[{"id":"https://openalex.org/I187400657","display_name":"South China Normal University","ror":"https://ror.org/01kq0pv72","country_code":"CN","type":"education","lineage":["https://openalex.org/I187400657"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hao Zheng","raw_affiliation_strings":["South China Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China Normal University","institution_ids":["https://openalex.org/I187400657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072540443","display_name":"Shunzhi Yang","orcid":"https://orcid.org/0000-0003-0621-2525"},"institutions":[{"id":"https://openalex.org/I182722699","display_name":"Shenzhen Polytechnic University","ror":"https://ror.org/00d2w9g53","country_code":"CN","type":"education","lineage":["https://openalex.org/I182722699"]},{"id":"https://openalex.org/I4210120584","display_name":"The Polytechnic University of Japan","ror":"https://ror.org/02f0psx94","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210120584"]}],"countries":["CN","JP"],"is_corresponding":false,"raw_author_name":"Shunzhi Yang","raw_affiliation_strings":["Shenzhen Polytechnic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Polytechnic University","institution_ids":["https://openalex.org/I182722699","https://openalex.org/I4210120584"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101206305","display_name":"Zhuoxin He","orcid":null},"institutions":[{"id":"https://openalex.org/I187400657","display_name":"South China Normal University","ror":"https://ror.org/01kq0pv72","country_code":"CN","type":"education","lineage":["https://openalex.org/I187400657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuoxin He","raw_affiliation_strings":["South China Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China Normal University","institution_ids":["https://openalex.org/I187400657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027644159","display_name":"Jinfeng Yang","orcid":"https://orcid.org/0000-0002-0769-1655"},"institutions":[{"id":"https://openalex.org/I182722699","display_name":"Shenzhen Polytechnic University","ror":"https://ror.org/00d2w9g53","country_code":"CN","type":"education","lineage":["https://openalex.org/I182722699"]},{"id":"https://openalex.org/I4210120584","display_name":"The Polytechnic University of Japan","ror":"https://ror.org/02f0psx94","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210120584"]}],"countries":["CN","JP"],"is_corresponding":false,"raw_author_name":"Jinfeng Yang","raw_affiliation_strings":["Shenzhen Polytechnic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Polytechnic University","institution_ids":["https://openalex.org/I182722699","https://openalex.org/I4210120584"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101655410","display_name":"Zhenhua Huang","orcid":"https://orcid.org/0000-0002-0389-9061"},"institutions":[{"id":"https://openalex.org/I187400657","display_name":"South China Normal University","ror":"https://ror.org/01kq0pv72","country_code":"CN","type":"education","lineage":["https://openalex.org/I187400657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenhua Huang","raw_affiliation_strings":["South China Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China Normal University","institution_ids":["https://openalex.org/I187400657"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5085132445"],"corresponding_institution_ids":["https://openalex.org/I187400657"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38772893,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1891","last_page":"1901"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9926999807357788,"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":0.9926999807357788,"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":0.0019000000320374966,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0007999999797903001,"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/semantics","display_name":"Semantics (computer science)","score":0.650600016117096},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5845999717712402},{"id":"https://openalex.org/keywords/knowledge-representation-and-reasoning","display_name":"Knowledge representation and reasoning","score":0.43059998750686646},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.38960000872612},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.3862999975681305},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.3732999861240387},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.351500004529953}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8113999962806702},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.650600016117096},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5845999717712402},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5144000053405762},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.43059998750686646},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.38960000872612},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3862999975681305},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37369999289512634},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.3732999861240387},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.351500004529953},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.34360000491142273},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3343999981880188},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3059000074863434},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3059000074863434},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C160191386","wikidata":"https://www.wikidata.org/wiki/Q868299","display_name":"Control flow","level":2,"score":0.2572000026702881}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00184","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00184","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.14976","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.14976","pdf_url":"https://arxiv.org/pdf/2507.14976","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.14976","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.14976","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.14976","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.14976","pdf_url":"https://arxiv.org/pdf/2507.14976","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2609543366","display_name":null,"funder_award_id":"2022A1515011380","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G77659056","display_name":null,"funder_award_id":"62172166","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Pre-trained":[0],"Vision-Language":[1],"Models":[2],"(VLMs)":[3],"such":[4],"as":[5],"CLIP":[6],"have":[7,31],"shown":[8,32],"excellent":[9],"generalization":[10,23],"abilities.":[11],"However,":[12],"adapting":[13],"these":[14,53],"large-scale":[15],"models":[16],"to":[17,76,129,145,167],"downstream":[18],"tasks":[19,176],"while":[20],"preserving":[21],"their":[22,78],"capabilities":[24],"remains":[25],"challenging.":[26],"Although":[27],"prompt":[28],"learning":[29],"methods":[30],"promise,":[33],"they":[34],"suffer":[35],"from":[36],"two":[37],"fundamental":[38],"bottlenecks":[39],"that":[40,64,149],"limit":[41],"generalization:":[42],"(a)":[43],"modality":[44],"isolation,":[45],"and":[46,71,92],"(b)":[47],"hierarchical":[48,108,138],"semantic":[49],"decay.":[50],"To":[51],"address":[52],"limitations,":[54],"we":[55],"propose":[56],"HiCroPL,":[57],"a":[58,107,162],"Hierarchical":[59],"Cross-modal":[60],"Prompt":[61],"Learning":[62],"framework":[63],"establishes":[65],"bidirectional":[66],"knowledge":[67,83,109,139,165],"flow":[68,127],"between":[69],"text":[70,91,97,131],"vision":[72],"modalities,":[73],"enabling":[74,133],"them":[75],"refine":[77,130],"semantics":[79,102,155],"mutually.":[80],"HiCroPL":[81],"routes":[82],"flows":[84],"by":[85],"leveraging":[86],"the":[87,112],"complementary":[88],"strengths":[89],"of":[90,114],"vision.":[93],"In":[94,118],"early":[95],"layers,":[96,120],"prompts":[98,105,122],"inject":[99],"relatively":[100],"clear":[101],"into":[103],"visual":[104,116,121],"through":[106],"mapper,":[110],"enhancing":[111,157],"representation":[113],"low-level":[115],"semantics.":[117],"later":[119],"encoding":[123],"specific":[124],"task-relevant":[125],"objects":[126],"back":[128],"prompts,":[132],"deeper":[134,150],"alignment.":[135],"Crucially,":[136],"our":[137],"mapper":[140],"allows":[141],"representations":[142,151],"at":[143],"multi-scales":[144],"be":[146],"fused,":[147],"ensuring":[148],"retain":[152],"transferable":[153],"shallow":[154],"thereby":[156],"generalization.":[158],"We":[159],"further":[160],"introduce":[161],"lightweight":[163],"layer-specific":[164],"proxy":[166],"enable":[168],"efficient":[169],"cross-modal":[170],"interactions.":[171],"Extensive":[172],"evaluations":[173],"across":[174],"four":[175],"demonstrate":[177],"HiCroPL's":[178],"superior":[179],"performance,":[180],"achieving":[181],"state-of-the-art":[182],"results":[183],"on":[184],"11":[185],"benchmarks":[186],"with":[187],"significant":[188],"improvements.":[189],"Code":[190],"is":[191],"available":[192],"at:":[193],"https://github.com/zzeoZheng/HiCroPL.":[194]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}