{"id":"https://openalex.org/W2996232404","doi":"https://doi.org/10.1109/tmm.2019.2959433","title":"Hierarchical Prototype Learning for Zero-Shot Recognition","display_name":"Hierarchical Prototype Learning for Zero-Shot Recognition","publication_year":2019,"publication_date":"2019-12-12","ids":{"openalex":"https://openalex.org/W2996232404","doi":"https://doi.org/10.1109/tmm.2019.2959433","mag":"2996232404"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2019.2959433","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2019.2959433","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","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/A5100343569","display_name":"Xingxing Zhang","orcid":"https://orcid.org/0000-0003-4012-3796"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xingxing Zhang","raw_affiliation_strings":["Beijing Key Laboratory of Advanced Information Science and Network Technology, Beijing Jiaotong University, Beijing, China","Institute of Information Science, Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Advanced Information Science and Network Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048634974","display_name":"Shupeng Gui","orcid":"https://orcid.org/0000-0003-4744-4680"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shupeng Gui","raw_affiliation_strings":["Department of Computer Science, University of Rochester, Rochester, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Rochester, Rochester, USA","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101867605","display_name":"Zhenfeng Zhu","orcid":"https://orcid.org/0000-0001-7315-3276"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenfeng Zhu","raw_affiliation_strings":["Beijing Key Laboratory of Advanced Information Science and Network Technology, Beijing Jiaotong University, Beijing, China","Institute of Information Science, Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Advanced Information Science and Network Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100362745","display_name":"Yao Zhao","orcid":"https://orcid.org/0000-0002-8581-9554"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Zhao","raw_affiliation_strings":["Beijing Key Laboratory of Advanced Information Science and Network Technology, Beijing Jiaotong University, Beijing, China","Institute of Information Science, Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Advanced Information Science and Network Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100396318","display_name":"Ji Liu","orcid":"https://orcid.org/0000-0002-0240-8881"},"institutions":[{"id":"https://openalex.org/I58610484","display_name":"Seattle University","ror":"https://ror.org/02jqc0m91","country_code":"US","type":"education","lineage":["https://openalex.org/I58610484"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ji Liu","raw_affiliation_strings":["Ytech Seattle AI Lab, Kwai, Inc., Seattle, USA"],"affiliations":[{"raw_affiliation_string":"Ytech Seattle AI Lab, Kwai, Inc., Seattle, USA","institution_ids":["https://openalex.org/I58610484"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100343569"],"corresponding_institution_ids":["https://openalex.org/I21193070"],"apc_list":null,"apc_paid":null,"fwci":2.9403,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.93190713,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"22","issue":"7","first_page":"1692","last_page":"1703"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9986000061035156,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9269999861717224,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8125909566879272},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.7706031799316406},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6645171046257019},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.58042311668396},{"id":"https://openalex.org/keywords/semantic-gap","display_name":"Semantic gap","score":0.5014832019805908},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.4823884069919586},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.47567668557167053},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4680855870246887},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4579038619995117},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4424327611923218},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4349871873855591},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4230755567550659},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.417946457862854},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4139890670776367},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.41217541694641113},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3406411409378052},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.2710421085357666},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1003512442111969}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8125909566879272},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7706031799316406},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6645171046257019},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.58042311668396},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.5014832019805908},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.4823884069919586},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.47567668557167053},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4680855870246887},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4579038619995117},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4424327611923218},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4349871873855591},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4230755567550659},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.417946457862854},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4139890670776367},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.41217541694641113},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3406411409378052},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.2710421085357666},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1003512442111969},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2019.2959433","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2019.2959433","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.6899999976158142,"id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G1724347139","display_name":null,"funder_award_id":"2018AAA0102101","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G43915001","display_name":null,"funder_award_id":"61572068","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4994914903","display_name":null,"funder_award_id":"61976018","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7072385062","display_name":null,"funder_award_id":"61532005","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7536822468","display_name":null,"funder_award_id":"U1936212","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/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":78,"referenced_works":["https://openalex.org/W652269744","https://openalex.org/W1797268635","https://openalex.org/W1999818274","https://openalex.org/W2044913453","https://openalex.org/W2070148066","https://openalex.org/W2088748973","https://openalex.org/W2091917610","https://openalex.org/W2098411764","https://openalex.org/W2117539524","https://openalex.org/W2123024445","https://openalex.org/W2123921497","https://openalex.org/W2124033848","https://openalex.org/W2128532956","https://openalex.org/W2134270519","https://openalex.org/W2141350700","https://openalex.org/W2151575489","https://openalex.org/W2153579005","https://openalex.org/W2157133710","https://openalex.org/W2158199200","https://openalex.org/W2165232124","https://openalex.org/W2171061940","https://openalex.org/W2194775991","https://openalex.org/W2209594346","https://openalex.org/W2289084343","https://openalex.org/W2293561010","https://openalex.org/W2405223529","https://openalex.org/W2463762378","https://openalex.org/W2552383788","https://openalex.org/W2603705233","https://openalex.org/W2604808168","https://openalex.org/W2605805765","https://openalex.org/W2609698233","https://openalex.org/W2611632661","https://openalex.org/W2724492314","https://openalex.org/W2744242754","https://openalex.org/W2748618181","https://openalex.org/W2789002497","https://openalex.org/W2798913983","https://openalex.org/W2799215068","https://openalex.org/W2804697066","https://openalex.org/W2808657737","https://openalex.org/W2883124384","https://openalex.org/W2889587173","https://openalex.org/W2892236829","https://openalex.org/W2900393952","https://openalex.org/W2910453440","https://openalex.org/W2949533609","https://openalex.org/W2962677366","https://openalex.org/W2962716320","https://openalex.org/W2962762077","https://openalex.org/W2962903908","https://openalex.org/W2963255320","https://openalex.org/W2963283377","https://openalex.org/W2963486920","https://openalex.org/W2963499153","https://openalex.org/W2963545832","https://openalex.org/W2963846885","https://openalex.org/W2963936013","https://openalex.org/W2963960318","https://openalex.org/W2964086552","https://openalex.org/W2964307109","https://openalex.org/W3010805239","https://openalex.org/W3099554308","https://openalex.org/W3100093508","https://openalex.org/W3143107425","https://openalex.org/W4248880341","https://openalex.org/W4294170691","https://openalex.org/W6638319203","https://openalex.org/W6678360021","https://openalex.org/W6678470764","https://openalex.org/W6682402173","https://openalex.org/W6682691769","https://openalex.org/W6748774398","https://openalex.org/W6749074686","https://openalex.org/W6751702825","https://openalex.org/W6752146845","https://openalex.org/W6754700304","https://openalex.org/W6755057408"],"related_works":["https://openalex.org/W2750434199","https://openalex.org/W4386924096","https://openalex.org/W2129428289","https://openalex.org/W2347374138","https://openalex.org/W1658719554","https://openalex.org/W2050635624","https://openalex.org/W2091753323","https://openalex.org/W2101447046","https://openalex.org/W2168037874","https://openalex.org/W2119303512"],"abstract_inverted_index":{"Zero-Shot":[0],"Learning":[1],"(ZSL)":[2],"has":[3,75],"received":[4],"extensive":[5,179],"attention":[6],"and":[7,20,72,115,144,187,197],"successes":[8],"in":[9,13,52,63,83,141],"recent":[10],"years":[11],"especially":[12],"areas":[14],"of":[15,69,132,165,173,175,181],"fine-grained":[16],"object":[17],"recognition,":[18],"retrieval,":[19],"image":[21],"captioning.":[22],"Key":[23],"to":[24,27,33,59,95,109],"ZSL":[25],"is":[26,107],"transfer":[28],"knowledge":[29],"from":[30],"the":[31,34,47,67,80,125,130,138,148,163,171],"seen":[32,114],"unseen":[35,116],"classes":[36],"via":[37],"auxiliary":[38],"semantic":[39,64,145,176],"prototypes":[40,71,122],"(e.g.,":[41],"word":[42],"or":[43],"attribute":[44],"vectors).":[45],"However,":[46],"popularly":[48],"learned":[49],"projection":[50],"functions":[51],"previous":[53],"works":[54],"cannot":[55],"generalize":[56],"well":[57],"due":[58],"non-visual":[60],"components":[61],"included":[62],"prototypes.":[65,177],"Besides,":[66],"incompleteness":[68],"provided":[70],"captured":[73],"images":[74],"less":[76],"been":[77],"considered":[78],"by":[79,119,154],"state-of-the-art":[81],"approaches":[82],"ZSL.":[84],"In":[85],"this":[86],"paper,":[87],"we":[88,135],"propose":[89],"a":[90,97],"hierarchical":[91],"prototype":[92],"learning":[93,120],"formulation":[94],"provide":[96],"systematical":[98],"solution":[99],"(named":[100],"HPL)":[101],"for":[102],"zero-shot":[103],"recognition.":[104],"Specifically,":[105],"HPL":[106,191],"able":[108],"obtain":[110],"discriminability":[111],"on":[112],"both":[113,142],"class":[117],"domains":[118],"visual":[121,143,166],"respectively":[123],"under":[124,203],"transductive":[126],"setting.":[127],"To":[128],"narrow":[129],"gap":[131],"two":[133,149],"domains,":[134],"further":[136,152],"learn":[137],"interpretable":[139],"super-prototypes":[140],"spaces.":[146],"Meanwhile,":[147],"spaces":[150],"are":[151,183],"bridged":[153],"maximizing":[155],"their":[156],"structural":[157],"consistency.":[158],"This":[159],"not":[160],"only":[161],"facilitates":[162],"representativeness":[164],"prototypes,":[167],"but":[168],"also":[169],"alleviates":[170],"loss":[172],"information":[174],"An":[178],"group":[180],"experiments":[182],"then":[184],"carefully":[185],"designed":[186],"presented,":[188],"demonstrating":[189],"that":[190],"obtains":[192],"remarkably":[193],"more":[194],"favorable":[195],"efficiency":[196],"effectiveness,":[198],"over":[199],"currently":[200],"available":[201],"alternatives":[202],"various":[204],"settings.":[205]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}