{"id":"https://openalex.org/W4387969338","doi":"https://doi.org/10.1145/3581783.3611988","title":"Hierarchical Prompt Learning Using CLIP for Multi-label Classification with Single Positive Labels","display_name":"Hierarchical Prompt Learning Using CLIP for Multi-label Classification with Single Positive Labels","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387969338","doi":"https://doi.org/10.1145/3581783.3611988"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3611988","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3611988","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3611988","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 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3611988","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086294753","display_name":"Ao Wang","orcid":"https://orcid.org/0000-0003-0030-551X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ao Wang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100334231","display_name":"Hui Chen","orcid":"https://orcid.org/0000-0003-4180-5801"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Chen","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077882811","display_name":"Zijia Lin","orcid":"https://orcid.org/0000-0002-1390-7424"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zijia Lin","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003869666","display_name":"Z. Ding","orcid":"https://orcid.org/0000-0002-2362-6802"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zixuan Ding","raw_affiliation_strings":["Xidian University & Zhuoxi Institute of Brain and Intelligence, Beijing & Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Xidian University & Zhuoxi Institute of Brain and Intelligence, Beijing & Hangzhou, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054904119","display_name":"Pengzhang Liu","orcid":"https://orcid.org/0000-0002-6031-5245"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengzhang Liu","raw_affiliation_strings":["jd.com, Beijing, China"],"affiliations":[{"raw_affiliation_string":"jd.com, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033318669","display_name":"Yongjun Bao","orcid":"https://orcid.org/0000-0002-7816-0587"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongjun Bao","raw_affiliation_strings":["jd.com, Beijing, China"],"affiliations":[{"raw_affiliation_string":"jd.com, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076034357","display_name":"W. P. Yan","orcid":"https://orcid.org/0000-0002-5702-8384"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weipeng Yan","raw_affiliation_strings":["jd.com, Beijing, China"],"affiliations":[{"raw_affiliation_string":"jd.com, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057732142","display_name":"Guiguang Ding","orcid":"https://orcid.org/0000-0003-0137-9975"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guiguang Ding","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5086294753"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":2.9579,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.92908443,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5594","last_page":"5604"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9997000098228455,"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":0.9962000250816345,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9944999814033508,"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":0.8195885419845581},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6367447376251221},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.5933036804199219},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5871356129646301},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5586698651313782},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5396722555160522},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5343590974807739},{"id":"https://openalex.org/keywords/multi-label-classification","display_name":"Multi-label classification","score":0.510330855846405},{"id":"https://openalex.org/keywords/grasp","display_name":"GRASP","score":0.4481557309627533},{"id":"https://openalex.org/keywords/hierarchical-database-model","display_name":"Hierarchical database model","score":0.4246354103088379},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.41464653611183167},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.25642430782318115},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.09908202290534973}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8195885419845581},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6367447376251221},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.5933036804199219},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5871356129646301},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5586698651313782},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5396722555160522},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5343590974807739},{"id":"https://openalex.org/C2776482837","wikidata":"https://www.wikidata.org/wiki/Q3553958","display_name":"Multi-label classification","level":2,"score":0.510330855846405},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.4481557309627533},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.4246354103088379},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.41464653611183167},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25642430782318115},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.09908202290534973},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3611988","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3611988","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3611988","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 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3581783.3611988","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3611988","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3611988","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 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Decent work and economic growth","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/8"}],"awards":[{"id":"https://openalex.org/G6998854227","display_name":null,"funder_award_id":"62271281, 61925107, U1936202, 62021002","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/F4320338464","display_name":"Natural Science Foundation of Zhejiang Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387969338.pdf","grobid_xml":"https://content.openalex.org/works/W4387969338.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2007972815","https://openalex.org/W2081580037","https://openalex.org/W2605997098","https://openalex.org/W2932399282","https://openalex.org/W2963745697","https://openalex.org/W2969792713","https://openalex.org/W2992049873","https://openalex.org/W2998420437","https://openalex.org/W3035087309","https://openalex.org/W3044438666","https://openalex.org/W3092779813","https://openalex.org/W3096609285","https://openalex.org/W3165691894","https://openalex.org/W3198377975","https://openalex.org/W3216083537","https://openalex.org/W4214673031","https://openalex.org/W4225930680","https://openalex.org/W4304014049","https://openalex.org/W4312310776","https://openalex.org/W4312648273","https://openalex.org/W4319300294","https://openalex.org/W6600855501","https://openalex.org/W6607999579"],"related_works":["https://openalex.org/W2163296013","https://openalex.org/W2743859443","https://openalex.org/W2326995835","https://openalex.org/W165915117","https://openalex.org/W2059402478","https://openalex.org/W2123347777","https://openalex.org/W4387804363","https://openalex.org/W2019547100","https://openalex.org/W2250721602","https://openalex.org/W3026383394"],"abstract_inverted_index":{"Collecting":[0],"full":[1],"annotations":[2],"to":[3,15,50,57,110,137,152],"construct":[4],"multi-label":[5,22],"datasets":[6,167],"is":[7],"difficult":[8],"and":[9,31,121,157,162,181],"labor-consuming.":[10],"As":[11],"an":[12],"effective":[13],"solution":[14],"relieve":[16],"the":[17,52,60,76,139,154,174],"annotation":[18],"burden,":[19],"single":[20],"positive":[21,40],"learning":[23,100],"(SPML)":[24],"draws":[25],"increasing":[26],"attention":[27],"from":[28],"both":[29],"academia":[30],"industry.":[32],"It":[33],"only":[34],"annotates":[35],"each":[36],"image":[37],"with":[38,102],"one":[39],"label,":[41],"leaving":[42,74],"other":[43],"labels":[44,56,72,82,86],"unobserved.":[45],"Therefore,":[46],"existing":[47],"methods":[48],"strive":[49],"explore":[51],"cue":[53],"of":[54,62],"unobserved":[55],"compensate":[58],"for":[59,126],"insufficiency":[61],"label":[63],"supervision.":[64],"Though":[65],"achieving":[66],"promising":[67],"performance,":[68],"they":[69],"generally":[70],"consider":[71],"independently,":[73],"out":[75],"inherent":[77],"hierarchical":[78,98,113,140],"semantic":[79,114],"relationship":[80],"among":[81],"which":[83],"reveals":[84],"that":[85,169],"can":[87],"be":[88,186],"clustered":[89],"into":[90],"groups.":[91],"In":[92],"this":[93],"paper,":[94],"we":[95,144],"propose":[96],"a":[97,103,117,131,146],"prompt":[99],"method":[101,171],"novel":[104],"Hierarchical":[105,132,147],"Semantic":[106],"Prompt":[107,134],"Network":[108,150],"(HSPNet)":[109],"harness":[111],"such":[112],"relationships":[115],"using":[116],"large-scale":[118],"pretrained":[119],"vision":[120],"language":[122],"model,":[123],"i.e.,":[124],"CLIP,":[125],"SPML.":[127],"We":[128],"first":[129],"introduce":[130],"Conditional":[133],"(HCP)":[135],"strategy":[136],"grasp":[138],"label-group":[141],"dependency.":[142],"Then":[143],"equip":[145],"Graph":[148],"Convolutional":[149],"(HGCN)":[151],"capture":[153],"high-order":[155],"inter-label":[156],"inter-group":[158],"dependencies.":[159],"Comprehensive":[160],"experiments":[161],"analyses":[163],"on":[164],"several":[165],"benchmark":[166],"show":[168],"our":[170],"significantly":[172],"outperforms":[173],"state-of-the-art":[175],"methods,":[176],"well":[177],"demonstrating":[178],"its":[179],"superiority":[180],"effectiveness.":[182],"Our":[183],"code":[184],"will":[185],"available":[187],"at":[188],"https://github.com/jameslahm/HSPNet.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":4}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}