{"id":"https://openalex.org/W4408354535","doi":"https://doi.org/10.1109/icassp49660.2025.10890675","title":"Learning Hierarchical Attribute Prompt for Vision-Language Models","display_name":"Learning Hierarchical Attribute Prompt for Vision-Language Models","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354535","doi":"https://doi.org/10.1109/icassp49660.2025.10890675"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890675","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890675","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5091325326","display_name":"Jun Liang","orcid":"https://orcid.org/0000-0002-0805-2425"},"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":"Jun Liang","raw_affiliation_strings":["South China Normal University,School of Artificial Intelligence,Foshan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China Normal University,School of Artificial Intelligence,Foshan,China","institution_ids":["https://openalex.org/I187400657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101698101","display_name":"Yang Peng","orcid":"https://orcid.org/0009-0003-2824-5843"},"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":"Yang Peng","raw_affiliation_strings":["South China Normal University,School of Artificial Intelligence,Foshan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China Normal University,School of Artificial Intelligence,Foshan,China","institution_ids":["https://openalex.org/I187400657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010402856","display_name":"Rui Luo","orcid":"https://orcid.org/0000-0002-7333-1711"},"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":"Rui Luo","raw_affiliation_strings":["South China Normal University,School of Artificial Intelligence,Foshan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China Normal University,School of Artificial Intelligence,Foshan,China","institution_ids":["https://openalex.org/I187400657"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yunyu Zou","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":"Yunyu Zou","raw_affiliation_strings":["South China Normal University,School of Artificial Intelligence,Foshan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China Normal University,School of Artificial Intelligence,Foshan,China","institution_ids":["https://openalex.org/I187400657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101810043","display_name":"Yalong Cheng","orcid":"https://orcid.org/0000-0003-1548-0003"},"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":"Yalong Cheng","raw_affiliation_strings":["South China Normal University,School of Artificial Intelligence,Foshan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China Normal University,School of Artificial Intelligence,Foshan,China","institution_ids":["https://openalex.org/I187400657"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055183002","display_name":"Bingzhi Chen","orcid":"https://orcid.org/0000-0002-2497-6214"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]},{"id":"https://openalex.org/I4210165204","display_name":"Zhuhai Institute of Advanced Technology","ror":"https://ror.org/05r1mzq61","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761","https://openalex.org/I4210165204"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bingzhi Chen","raw_affiliation_strings":["Beijing Institute of Technology, Zhuhai,School of Artificial Intelligence,Zhuhai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Zhuhai,School of Artificial Intelligence,Zhuhai,China","institution_ids":["https://openalex.org/I4210165204","https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9349,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.72361263,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.996999979019165,"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":0.996999979019165,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9830999970436096,"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/T10028","display_name":"Topic Modeling","score":0.9714999794960022,"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/computer-science","display_name":"Computer science","score":0.761559784412384},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5194801092147827},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4608362317085266}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.761559784412384},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5194801092147827},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4608362317085266}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890675","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890675","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W12634471","https://openalex.org/W1977295328","https://openalex.org/W2017814585","https://openalex.org/W2047643928","https://openalex.org/W2108598243","https://openalex.org/W2138011018","https://openalex.org/W2155904486","https://openalex.org/W2533598788","https://openalex.org/W2964194231","https://openalex.org/W3037492894","https://openalex.org/W3177096435","https://openalex.org/W3198377975","https://openalex.org/W4297697565","https://openalex.org/W4312310776","https://openalex.org/W4386071547","https://openalex.org/W4386072228","https://openalex.org/W4386076527","https://openalex.org/W4386076680","https://openalex.org/W4390872306","https://openalex.org/W4392426151","https://openalex.org/W4393148291","https://openalex.org/W4393148494","https://openalex.org/W4393155041","https://openalex.org/W4393158953","https://openalex.org/W4401367304","https://openalex.org/W4402726965","https://openalex.org/W4402727025","https://openalex.org/W4402753597","https://openalex.org/W4402961681","https://openalex.org/W4404690880","https://openalex.org/W6638677478","https://openalex.org/W6763468762","https://openalex.org/W6764990469","https://openalex.org/W6790019176","https://openalex.org/W6791353385","https://openalex.org/W6796581206","https://openalex.org/W6802744804","https://openalex.org/W6810738896"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Prompt":[0,62],"learning":[1],"is":[2],"a":[3],"common":[4],"strategy":[5],"for":[6,18],"adapting":[7],"Visual":[8],"Language":[9],"Models":[10],"(VLMs)":[11],"to":[12,29,35,85,93],"downstream":[13],"tasks":[14],"by":[15],"fine-tuning":[16],"prompts":[17,83,91],"task-specific":[19],"performance.":[20],"However,":[21],"existing":[22],"methods":[23],"face":[24],"two":[25],"key":[26],"challenges:":[27],"overfitting":[28],"base":[30],"classes,":[31,37],"which":[32,47,65],"limits":[33],"generalization":[34,106],"novel":[36],"and":[38,50,89,101,111,128],"the":[39,58,126],"dependence":[40],"on":[41,120],"manually":[42],"generated":[43],"or":[44,115],"LLM-based":[45,116],"descriptions,":[46],"are":[48],"time-consuming":[49],"error-prone.":[51],"To":[52],"address":[53],"these":[54],"issues,":[55],"we":[56],"propose":[57],"Learning":[59],"Hierarchical":[60],"Attribute":[61],"(LHAP)":[63],"method,":[64],"introduces":[66],"fine-grained":[67,87],"semantic":[68],"alignment":[69],"through":[70],"hierarchical":[71],"prompts.":[72],"By":[73],"autonomously":[74],"extracting":[75],"visual":[76],"attributes":[77],"from":[78,113],"images,":[79],"LHAP":[80,131],"generates":[81],"local-level":[82],"(LLP)":[84],"capture":[86],"semantics":[88],"global-level":[90],"(GLP)":[92],"model":[94],"overall":[95],"semantics.":[96],"The":[97],"combination":[98],"of":[99,130],"LLP":[100],"GLP":[102],"not":[103],"only":[104],"improves":[105],"but":[107],"also":[108],"mitigates":[109],"errors":[110],"inefficiencies":[112],"manual":[114],"descriptions.":[117],"Extensive":[118],"experiments":[119],"multiple":[121],"benchmark":[122],"datasets":[123],"consistently":[124],"demonstrate":[125],"superiority":[127],"robustness":[129],"over":[132],"state-of-the-art":[133],"methods.":[134]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}