{"id":"https://openalex.org/W7152403667","doi":"https://doi.org/10.1145/3774904.3792293","title":"PLIKD: Prompt Learning with Instance-aware Knowledge Distillation for Web-scale Semantic Image Classification","display_name":"PLIKD: Prompt Learning with Instance-aware Knowledge Distillation for Web-scale Semantic Image Classification","publication_year":2026,"publication_date":"2026-04-09","ids":{"openalex":"https://openalex.org/W7152403667","doi":"https://doi.org/10.1145/3774904.3792293"},"language":null,"primary_location":{"id":"doi:10.1145/3774904.3792293","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792293","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 ACM Web Conference 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774904.3792293","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129670604","display_name":"Jianye Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I4210162190","display_name":"China University of Petroleum, East China","ror":"https://ror.org/05gbn2817","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210162190"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianye Xie","raw_affiliation_strings":["College of Computer Science and Technology, China University of Petroleum (East China), Qingdao, China and Shandong Key Laboratory of Intelligent Oil and Gas Industrial Software, Qingdao, China"],"raw_orcid":"https://orcid.org/0009-0001-9727-0028","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, China University of Petroleum (East China), Qingdao, China and Shandong Key Laboratory of Intelligent Oil and Gas Industrial Software, Qingdao, China","institution_ids":["https://openalex.org/I4210162190"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123959669","display_name":"Chunhua Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I49934816","display_name":"Hunan University of Technology","ror":"https://ror.org/04j3vr751","country_code":"CN","type":"education","lineage":["https://openalex.org/I49934816"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunhua Hu","raw_affiliation_strings":["Institute of Big Data and Internet Innovation, Hunan University of Technology and Business, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0003-0317-2687","affiliations":[{"raw_affiliation_string":"Institute of Big Data and Internet Innovation, Hunan University of Technology and Business, Changsha, China","institution_ids":["https://openalex.org/I49934816"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006514077","display_name":"Lianyong Qi","orcid":"https://orcid.org/0000-0001-9875-9856"},"institutions":[{"id":"https://openalex.org/I4210162190","display_name":"China University of Petroleum, East China","ror":"https://ror.org/05gbn2817","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210162190"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lianyong Qi","raw_affiliation_strings":["College of Computer Science and Technology, China University of Petroleum (East China), Qingdao, China and Shandong Key Laboratory of Intelligent Oil and Gas Industrial Software, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0001-9875-9856","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, China University of Petroleum (East China), Qingdao, China and Shandong Key Laboratory of Intelligent Oil and Gas Industrial Software, Qingdao, China","institution_ids":["https://openalex.org/I4210162190"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088784958","display_name":"Fan Wang","orcid":"https://orcid.org/0000-0002-0953-6923"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Wang","raw_affiliation_strings":["College of Computer Science, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-0953-6923","affiliations":[{"raw_affiliation_string":"College of Computer Science, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiaolong Xu","orcid":"https://orcid.org/0000-0003-4879-9803"},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaolong Xu","raw_affiliation_strings":["School of Computer and Software, Nanjing University of Information Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-4879-9803","affiliations":[{"raw_affiliation_string":"School of Computer and Software, Nanjing University of Information Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I200845125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126292179","display_name":"H. Xiang","orcid":null},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haolong Xiang","raw_affiliation_strings":["School of Software, Nanjing University of Information Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0002-6690-0020","affiliations":[{"raw_affiliation_string":"School of Software, Nanjing University of Information Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I200845125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076120553","display_name":"Xuyun Zhang","orcid":"https://orcid.org/0000-0001-7353-4159"},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xuyun Zhang","raw_affiliation_strings":["School of Computing, Macquarie University, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0001-7353-4159","affiliations":[{"raw_affiliation_string":"School of Computing, Macquarie University, Sydney, Australia","institution_ids":["https://openalex.org/I99043593"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034495880","display_name":"Shichao Pei","orcid":"https://orcid.org/0000-0002-0802-1506"},"institutions":[{"id":"https://openalex.org/I33434090","display_name":"University of Massachusetts Boston","ror":"https://ror.org/04ydmy275","country_code":"US","type":"education","lineage":["https://openalex.org/I33434090"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shichao Pei","raw_affiliation_strings":["Department of Computer Science, University of Massachusetts Boston, Boston, USA"],"raw_orcid":"https://orcid.org/0000-0002-0802-1506","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Massachusetts Boston, Boston, USA","institution_ids":["https://openalex.org/I33434090"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056293251","display_name":"Amin Beheshti","orcid":"https://orcid.org/0000-0002-5988-5494"},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Amin Beheshti","raw_affiliation_strings":["School of Computing, Macquarie University, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0002-5988-5494","affiliations":[{"raw_affiliation_string":"School of Computing, Macquarie University, Sydney, Australia","institution_ids":["https://openalex.org/I99043593"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038791483","display_name":"Wanchun Dou","orcid":"https://orcid.org/0000-0003-4833-2023"},"institutions":[{"id":"https://openalex.org/I134687103","display_name":"Nanjing Tech University","ror":"https://ror.org/03sd35x91","country_code":"CN","type":"education","lineage":["https://openalex.org/I134687103"]},{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanchun Dou","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, School of Computer Science and Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-4833-2023","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, School of Computer Science and Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I36399199","https://openalex.org/I134687103"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055675863","display_name":"Xiaokang Zhou","orcid":"https://orcid.org/0000-0003-3488-4679"},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xiaokang Zhou","raw_affiliation_strings":["Faculty of Business and Data Science, Kansai University, Suita, Japan and RIKEN Center for Advanced Intelligence Project, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0003-3488-4679","affiliations":[{"raw_affiliation_string":"Faculty of Business and Data Science, Kansai University, Suita, Japan and RIKEN Center for Advanced Intelligence Project, Tokyo, Japan","institution_ids":["https://openalex.org/I4210126580"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3788","last_page":"3799"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.361299991607666,"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":0.361299991607666,"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":0.15700000524520874,"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":0.10040000081062317,"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/image","display_name":"Image (mathematics)","score":0.39890000224113464},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3874000012874603},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.37459999322891235},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3160000145435333},{"id":"https://openalex.org/keywords/knowledge-based-systems","display_name":"Knowledge-based systems","score":0.2935999929904938},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.26969999074935913}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6636000275611877},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6284999847412109},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.39890000224113464},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3874000012874603},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.37459999322891235},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3495999872684479},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3416999876499176},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3160000145435333},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.2935999929904938},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2531999945640564}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774904.3792293","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792293","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 ACM Web Conference 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3774904.3792293","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792293","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 ACM Web Conference 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1946117621","https://openalex.org/W1977295328","https://openalex.org/W1989534515","https://openalex.org/W2047643928","https://openalex.org/W2081613070","https://openalex.org/W2107698128","https://openalex.org/W2108598243","https://openalex.org/W2138011018","https://openalex.org/W2155904486","https://openalex.org/W2159373756","https://openalex.org/W2533598788","https://openalex.org/W2964194231","https://openalex.org/W2986692991","https://openalex.org/W3012747158","https://openalex.org/W3034230713","https://openalex.org/W3037492894","https://openalex.org/W3044438666","https://openalex.org/W3139732141","https://openalex.org/W3177096435","https://openalex.org/W3198377975","https://openalex.org/W3213454282","https://openalex.org/W4312310776","https://openalex.org/W4312823897","https://openalex.org/W4385815641","https://openalex.org/W4386071547","https://openalex.org/W4390872306","https://openalex.org/W4390872773","https://openalex.org/W4391547487","https://openalex.org/W4393148527","https://openalex.org/W4393161065","https://openalex.org/W4396757580","https://openalex.org/W4396758723","https://openalex.org/W4402754281","https://openalex.org/W4402783842","https://openalex.org/W4407806353","https://openalex.org/W4408191766","https://openalex.org/W4409368316","https://openalex.org/W4412877238","https://openalex.org/W4414197146","https://openalex.org/W4415797312"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,8,59,65],"rapid":[2],"growth":[3],"of":[4,20,162],"multi-modal":[5,131],"content":[6],"on":[7,75,211],"Web,":[9],"robust":[10,116,171,203],"vision-language":[11,44],"models":[12,45,134],"are":[13],"essential":[14],"for":[15,42,115,143,170],"semantic":[16,47,118,213],"understanding":[17],"and":[18,25,35,78,94,172,176,183,198,201],"classification":[19,49],"web":[21],"images":[22],"under":[23,79,204],"diverse":[24],"dynamic":[26],"contexts,":[27],"supporting":[28],"Web":[29],"applications":[30],"such":[31],"as":[32],"multimedia":[33],"search":[34],"recommendation.":[36],"Prompt":[37],"learning":[38,108],"has":[39],"proven":[40],"effective":[41],"enhancing":[43],"in":[46,87],"image":[48,119,145,214],"tasks.":[50],"However,":[51],"previous":[52],"methods":[53,210],"often":[54],"suffer":[55],"from":[56],"poor":[57,73],"generalization:":[58],"learned":[60],"prompts":[61],"tend":[62],"to":[63,72,139,195],"overfit":[64],"base":[66],"classes":[67,77,92],"seen":[68,197],"during":[69],"training,":[70],"leading":[71],"performance":[74],"unseen":[76,199],"distribution":[80,205],"shifts.":[81],"This":[82],"issue":[83],"is":[84],"especially":[85],"challenging":[86],"Web-scale":[88,117,212],"data,":[89],"where":[90],"new":[91],"emerge":[93],"distributions":[95],"shift":[96],"dynamically.":[97],"To":[98,147],"address":[99],"these":[100],"limitations,":[101],"we":[102],"propose":[103],"PLIKD,":[104],"a":[105,136,167],"novel":[106],"prompt":[107],"method":[109],"that":[110,190],"integrates":[111],"instance-aware":[112,125,156],"knowledge":[113,126,142,157,174],"distillation":[114,158],"classification.":[120,215],"Specifically,":[121],"PLIKD":[122,152,191],"introduces":[123,154],"an":[124,155],"extraction":[127],"module,":[128,159],"which":[129,160],"leverages":[130],"large":[132],"language":[133],"through":[135],"step-by-step":[137],"strategy":[138,169],"extract":[140],"external":[141],"each":[144],"instance.":[146],"incorporate":[148],"this":[149],"extracted":[150],"knowledge,":[151],"further":[153],"consists":[161],"two":[163],"key":[164],"steps:":[165],"(1)":[166],"dual-teacher":[168],"informative":[173],"distillation,":[175],"(2)":[177],"fine-grained":[178],"cross-modal":[179],"alignment":[180],"via":[181],"Smooth":[182],"Sparse":[184],"Optimal":[185],"Transport.":[186],"Extensive":[187],"experiments":[188],"demonstrate":[189],"significantly":[192],"improves":[193],"generalization":[194],"both":[196],"classes,":[200],"remains":[202],"shifts,":[206],"outperforming":[207],"existing":[208],"state-of-the-art":[209]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-04-10T00:00:00"}