{"id":"https://openalex.org/W4386721807","doi":"https://doi.org/10.1145/3581783.3613845","title":"Towards Visual Taxonomy Expansion","display_name":"Towards Visual Taxonomy Expansion","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4386721807","doi":"https://doi.org/10.1145/3581783.3613845"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3613845","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3613845","pdf_url":null,"source":null,"license":null,"license_id":null,"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":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2309.06105","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101427458","display_name":"Tinghui Zhu","orcid":"https://orcid.org/0000-0001-7673-712X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tinghui Zhu","raw_affiliation_strings":["Shanghai Key Laboratory of Data Science, School of Computer Science, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-7673-712X","affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Data Science, School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100746224","display_name":"Jingping Liu","orcid":"https://orcid.org/0000-0002-8671-2302"},"institutions":[{"id":"https://openalex.org/I143593769","display_name":"East China University of Science and Technology","ror":"https://ror.org/01vyrm377","country_code":"CN","type":"education","lineage":["https://openalex.org/I143593769"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingping Liu","raw_affiliation_strings":["School of Information Science and Engineering, East China University of Science and Technology, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-8671-2302","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, East China University of Science and Technology, Shanghai, China","institution_ids":["https://openalex.org/I143593769"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075507821","display_name":"Jiaqing Liang","orcid":"https://orcid.org/0000-0003-0670-5602"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaqing Liang","raw_affiliation_strings":["Shanghai Key Laboratory of Data Science, School of Computer Science, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-0670-5602","affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Data Science, School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103218236","display_name":"Haiyun Jiang","orcid":"https://orcid.org/0000-0001-9026-7515"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haiyun Jiang","raw_affiliation_strings":["Shanghai Key Laboratory of Data Science, School of Computer Science, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-9026-7515","affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Data Science, School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090455375","display_name":"Yanghua Xiao","orcid":"https://orcid.org/0000-0001-8403-9591"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanghua Xiao","raw_affiliation_strings":["Shanghai Key Laboratory of Data Science, School of Computer Science, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-8403-9591","affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Data Science, School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062489498","display_name":"Z. L. Wang","orcid":"https://orcid.org/0009-0004-9515-7947"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zongyu Wang","raw_affiliation_strings":["Meituan, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0004-9515-7947","affiliations":[{"raw_affiliation_string":"Meituan, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101796552","display_name":"Rui Xie","orcid":"https://orcid.org/0000-0002-1116-7418"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rui Xie","raw_affiliation_strings":["Meituan, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-1116-7418","affiliations":[{"raw_affiliation_string":"Meituan, Shanghai, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086726545","display_name":"Yunsen Xian","orcid":"https://orcid.org/0000-0002-5303-9641"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yunsen Xian","raw_affiliation_strings":["Meituan, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-5303-9641","affiliations":[{"raw_affiliation_string":"Meituan, Shanghai, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3368,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.58828128,"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":"6481","last_page":"6490"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9965999722480774,"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":0.9965999722480774,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9883999824523926,"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":0.98580002784729,"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":0.7964967489242554},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.7602976560592651},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5997726917266846},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5689350962638855},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5654093623161316},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5146399736404419},{"id":"https://openalex.org/keywords/distributional-semantics","display_name":"Distributional semantics","score":0.45191675424575806},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4327419400215149},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.409873902797699},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.15461483597755432},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11824303865432739}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7964967489242554},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.7602976560592651},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5997726917266846},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5689350962638855},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5654093623161316},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5146399736404419},{"id":"https://openalex.org/C2778828372","wikidata":"https://www.wikidata.org/wiki/Q5283209","display_name":"Distributional semantics","level":3,"score":0.45191675424575806},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4327419400215149},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.409873902797699},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.15461483597755432},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11824303865432739},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3581783.3613845","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3613845","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2309.06105","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.06105","pdf_url":"https://arxiv.org/pdf/2309.06105","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2309.06105","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.06105","pdf_url":"https://arxiv.org/pdf/2309.06105","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.7799999713897705,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G4389483464","display_name":null,"funder_award_id":"2021SHZDZX0103","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"},{"id":"https://openalex.org/G8821772859","display_name":null,"funder_award_id":"22511105902","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"}],"funders":[{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386721807.pdf","grobid_xml":"https://content.openalex.org/works/W4386721807.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W90362830","https://openalex.org/W2068737686","https://openalex.org/W2081580037","https://openalex.org/W2094728533","https://openalex.org/W2103931177","https://openalex.org/W2296076036","https://openalex.org/W2465217376","https://openalex.org/W2740452428","https://openalex.org/W2804796012","https://openalex.org/W2895715183","https://openalex.org/W2962724755","https://openalex.org/W2963173796","https://openalex.org/W2964121744","https://openalex.org/W3012615229","https://openalex.org/W3012823870","https://openalex.org/W3036413095","https://openalex.org/W3103941499","https://openalex.org/W3168349005","https://openalex.org/W3173065403","https://openalex.org/W3176459892","https://openalex.org/W3206278318","https://openalex.org/W4221153270","https://openalex.org/W4224326644","https://openalex.org/W4253001967"],"related_works":["https://openalex.org/W2941608206","https://openalex.org/W2963364736","https://openalex.org/W2808113865","https://openalex.org/W2112408611","https://openalex.org/W3176691509","https://openalex.org/W4366284213","https://openalex.org/W4235405867","https://openalex.org/W3181580843","https://openalex.org/W909526553","https://openalex.org/W4322735487"],"abstract_inverted_index":{"Taxonomy":[0,45],"expansion":[1,54],"task":[2,62,68],"is":[3,101],"essential":[4],"in":[5],"organizing":[6],"the":[7,35,52,78,113,132],"ever-increasing":[8],"volume":[9],"of":[10],"new":[11],"concepts":[12],"into":[13,51],"existing":[14,17],"taxonomies.":[15],"Most":[16],"methods":[18],"focus":[19],"exclusively":[20],"on":[21,80,103,112,131],"using":[22],"textual":[23,59,71,90],"semantics,":[24],"leading":[25],"to":[26,29,31,69,77,94],"an":[27],"inability":[28],"generalize":[30],"unseen":[32],"terms":[33],"and":[34,63,72,91],"\"Prototypical":[36],"Hypernym":[37],"Problem.\"":[38],"In":[39,75],"this":[40],"paper,":[41],"we":[42,83,107],"propose":[43,57],"Visual":[44],"Expansion":[46],"(VTE),":[47],"introducing":[48],"visual":[49,65,73,92,97],"features":[50],"taxonomy":[53,115,134],"task.":[55],"We":[56],"a":[58,64,85],"hypernymy":[60],"learning":[61,67],"prototype":[66],"cluster":[70],"semantics.":[74,98],"addition":[76],"tasks":[79],"respective":[81],"modalities,":[82],"introduce":[84],"hyper-proto":[86],"constraint":[87],"that":[88],"integrates":[89],"semantics":[93],"produce":[95],"fine-grained":[96],"Our":[99],"method":[100,118],"evaluated":[102],"two":[104],"datasets,":[105],"where":[106],"obtain":[108],"compelling":[109],"results.":[110],"Specifically,":[111],"Chinese":[114,133],"dataset,":[116],"our":[117,125],"significantly":[119],"improves":[120],"accuracy":[121],"by":[122],"8.75%.":[123],"Additionally,":[124],"approach":[126],"performs":[127],"better":[128],"than":[129],"ChatGPT":[130],"dataset.":[135]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}