{"id":"https://openalex.org/W4402979610","doi":"https://doi.org/10.1109/icme57554.2024.10687898","title":"Multi-Attentional Distance for Zero-Shot Classification with Text-to-Image Diffusion Model","display_name":"Multi-Attentional Distance for Zero-Shot Classification with Text-to-Image Diffusion Model","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402979610","doi":"https://doi.org/10.1109/icme57554.2024.10687898"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10687898","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10687898","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5043877072","display_name":"Kailai Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kailai Feng","raw_affiliation_strings":["Harbin Institute of Technology,Faculty of Computing,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Faculty of Computing,Harbin,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003777635","display_name":"Minheng Ni","orcid":"https://orcid.org/0000-0001-6483-0650"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minheng Ni","raw_affiliation_strings":["Harbin Institute of Technology,Faculty of Computing,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Faculty of Computing,Harbin,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111346906","display_name":"Jiaxiu Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxiu Jiang","raw_affiliation_strings":["Harbin Institute of Technology,Faculty of Computing,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Faculty of Computing,Harbin,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013177603","display_name":"Zhilu Zhang","orcid":"https://orcid.org/0000-0002-5758-5949"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhilu Zhang","raw_affiliation_strings":["Harbin Institute of Technology,Faculty of Computing,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Faculty of Computing,Harbin,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100636655","display_name":"Wangmeng Zuo","orcid":"https://orcid.org/0000-0002-3330-783X"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wangmeng Zuo","raw_affiliation_strings":["Harbin Institute of Technology,Faculty of Computing,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Faculty of Computing,Harbin,China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I204983213"],"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":"1","last_page":"6"},"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":0.8937000036239624,"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":0.8937000036239624,"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/shot","display_name":"Shot (pellet)","score":0.6638008952140808},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.638140082359314},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6032358407974243},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5791751742362976},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.532121479511261},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.47854524850845337},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3979976177215576},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38321542739868164},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12475046515464783}],"concepts":[{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6638008952140808},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.638140082359314},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6032358407974243},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5791751742362976},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.532121479511261},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.47854524850845337},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3979976177215576},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38321542739868164},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12475046515464783},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/icme57554.2024.10687898","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10687898","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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":12,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2924476266","https://openalex.org/W2963283377","https://openalex.org/W2963960318","https://openalex.org/W3109728025","https://openalex.org/W3198377975","https://openalex.org/W4312933868","https://openalex.org/W4382450414","https://openalex.org/W4386790226","https://openalex.org/W4390872669","https://openalex.org/W4390873429","https://openalex.org/W4401733277"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W2325697621"],"abstract_inverted_index":{"Text-to-image":[0],"diffusion":[1,15,49,128],"models":[2,16],"have":[3],"demonstrated":[4],"rich":[5],"visual-linguistic":[6],"capability.":[7],"However,":[8],"existing":[9],"image":[10],"classification":[11],"methods":[12],"based":[13],"on":[14,99],"simply":[17],"choose":[18],"the":[19,24,60,66,76,106,127],"best-predicted":[20],"noise,":[21],"not":[22],"exploiting":[23],"relationships":[25],"between":[26,78],"visual":[27],"elements":[28],"and":[29,55,62,80,102,109,135],"text":[30],"adequately.":[31],"To":[32],"this":[33],"end,":[34],"we":[35,88],"propose":[36],"a":[37],"novel":[38],"Multi-attentional":[39],"Distance":[40],"Classifier":[41],"(MDC)":[42],"by":[43,123],"exploring":[44],"some":[45],"beneficial":[46],"information":[47,137],"in":[48,126],"models.":[50],"Specifically,":[51],"MDC":[52,98,112,130],"joints":[53],"self-":[54],"cross-attention":[56],"maps":[57],"to":[58,116],"model":[59],"semantic":[61,134],"structural":[63],"distances":[64,86],"of":[65,69,85,138],"latent":[67],"variables":[68],"images":[70,79],"under":[71,105],"different":[72],"category":[73,92],"conditions,":[74],"measuring":[75],"relevance":[77],"categories.":[81],"With":[82],"two":[83],"types":[84],"integrated,":[87],"can":[89,131],"classify":[90],"image's":[91],"with":[93],"minimum":[94],"distance.":[95],"We":[96],"evaluate":[97],"CIFAR-10,":[100],"STL-10,":[101],"CIFAR-100":[103],"datasets":[104],"zero-shot":[107],"setting":[108],"it":[110],"shows":[111],"achieves":[113],"superior":[114],"performance":[115],"prior":[117],"works.":[118],"Further":[119],"experiments":[120],"prove":[121],"that":[122],"introducing":[124],"attention":[125],"process,":[129],"discover":[132],"key":[133],"structure":[136],"categories":[139],"among":[140],"images.":[141],"Codes":[142],"are":[143],"publicly":[144],"available":[145],"at":[146],"https://github.com/Carlofkl/MDC.":[147]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
