{"id":"https://openalex.org/W4224865296","doi":"https://doi.org/10.1109/icme52920.2022.9859991","title":"Diverse Instance Discovery: Vision-Transformer for Instance-Aware Multi-Label Image Recognition","display_name":"Diverse Instance Discovery: Vision-Transformer for Instance-Aware Multi-Label Image Recognition","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4224865296","doi":"https://doi.org/10.1109/icme52920.2022.9859991"},"language":"en","primary_location":{"id":"doi:10.1109/icme52920.2022.9859991","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9859991","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-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/A5101977006","display_name":"Yunqing Hu","orcid":"https://orcid.org/0009-0003-5828-2768"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yunqing Hu","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University,Hangzhou,China","College of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University,Hangzhou,China","institution_ids":["https://openalex.org/I168879160"]},{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083349849","display_name":"Jin Xuan","orcid":"https://orcid.org/0000-0002-6718-9018"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuan Jin","raw_affiliation_strings":["Alibaba Group,Hangzhou,China","Alibaba Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,Hangzhou,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100343699","display_name":"Yin Zhang","orcid":"https://orcid.org/0000-0001-6986-4227"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yin Zhang","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University,Hangzhou,China","College of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University,Hangzhou,China","institution_ids":["https://openalex.org/I168879160"]},{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045259909","display_name":"Haiwen Hong","orcid":null},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haiwen Hong","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University,Hangzhou,China","College of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University,Hangzhou,China","institution_ids":["https://openalex.org/I168879160"]},{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100749004","display_name":"Jingfeng Zhang","orcid":"https://orcid.org/0000-0003-3491-8074"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingfeng Zhang","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University,Hangzhou,China","College of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University,Hangzhou,China","institution_ids":["https://openalex.org/I168879160"]},{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112658742","display_name":"Feihu Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feihu Yan","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University,Hangzhou,China","College of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University,Hangzhou,China","institution_ids":["https://openalex.org/I168879160"]},{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101802340","display_name":"Yuan He","orcid":"https://orcid.org/0000-0002-6885-1341"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan He","raw_affiliation_strings":["Alibaba Group,Hangzhou,China","Alibaba Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,Hangzhou,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100337747","display_name":"Hui Xue","orcid":"https://orcid.org/0000-0002-2093-2839"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Xue","raw_affiliation_strings":["Alibaba Group,Hangzhou,China","Alibaba Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,Hangzhou,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5101977006"],"corresponding_institution_ids":["https://openalex.org/I168879160"],"apc_list":null,"apc_paid":null,"fwci":0.2079,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.37190261,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"23","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9976999759674072,"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":0.9937999844551086,"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/computer-science","display_name":"Computer science","score":0.8029676675796509},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6819096803665161},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6457691788673401},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5207514762878418},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4952372610569},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47642096877098083},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.47002100944519043},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.41000401973724365},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.37416988611221313},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3310914635658264}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8029676675796509},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6819096803665161},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6457691788673401},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5207514762878418},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4952372610569},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47642096877098083},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.47002100944519043},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.41000401973724365},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.37416988611221313},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3310914635658264},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme52920.2022.9859991","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9859991","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.5299999713897705}],"awards":[{"id":"https://openalex.org/G5705787842","display_name":null,"funder_award_id":"62072399,U19B2042","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1567302070","https://openalex.org/W1861492603","https://openalex.org/W2031489346","https://openalex.org/W2037227137","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2295107390","https://openalex.org/W2518918709","https://openalex.org/W2932399282","https://openalex.org/W2963300078","https://openalex.org/W2964015378","https://openalex.org/W2966628364","https://openalex.org/W2982112268","https://openalex.org/W2997136715","https://openalex.org/W3035050607","https://openalex.org/W3035422918","https://openalex.org/W3035665101","https://openalex.org/W3094502228","https://openalex.org/W3099518117","https://openalex.org/W3109067582","https://openalex.org/W3167456680","https://openalex.org/W3172863135","https://openalex.org/W3174396085","https://openalex.org/W3189532445","https://openalex.org/W3192931333","https://openalex.org/W4214673031","https://openalex.org/W4297816851","https://openalex.org/W6639102338","https://openalex.org/W6676297131","https://openalex.org/W6726873649","https://openalex.org/W6744897953","https://openalex.org/W6776929863","https://openalex.org/W6779650173","https://openalex.org/W6784333009"],"related_works":["https://openalex.org/W3037187668","https://openalex.org/W4234772502","https://openalex.org/W2787993192","https://openalex.org/W2380685755","https://openalex.org/W2252100032","https://openalex.org/W2963436428","https://openalex.org/W4400978025","https://openalex.org/W2734796617","https://openalex.org/W2158269427","https://openalex.org/W3083218341"],"abstract_inverted_index":{"Previous":[0],"works":[1,181],"on":[2,170],"multi-label":[3,55,92],"image":[4],"recognition":[5],"(MLIR)":[6],"usually":[7],"use":[8,32,72],"CNNs":[9,47],"as":[10,25],"a":[11,104,109,120,131,144],"starting":[12],"point":[13],"for":[14,54],"research.":[15],"In":[16],"this":[17,100],"paper,":[18],"we":[19,102,129],"take":[20],"pure":[21],"Vision":[22],"Transformer":[23,37],"(ViT)":[24],"the":[26,34,44,117,155],"research":[27],"base":[28],"and":[29,64,84,108,114,182],"make":[30],"full":[31],"of":[33,36,46],"advantages":[35],"with":[38],"long-range":[39],"dependency":[40],"modeling":[41],"to":[42,49,71,79,87,123,137,142],"circumvent":[43],"disadvantages":[45],"limited":[48],"local":[50,140],"receptive":[51],"field.":[52],"However,":[53],"images":[56],"containing":[57],"multiple":[58],"objects":[59],"from":[60],"different":[61],"categories,":[62],"scales,":[63],"spatial":[65,110],"relations,":[66],"it":[67],"is":[68,78,167],"not":[69],"optimal":[70],"global":[73],"information":[74,153,166],"alone.":[75],"Our":[76,147],"goal":[77],"leverage":[80],"ViT's":[81],"patch":[82],"tokens":[83],"self-attention":[85],"mechanism":[86],"mine":[88],"rich":[89],"instances":[90],"in":[91],"images,":[93],"named":[94],"diverse":[95],"instance":[96],"discovery":[97],"(DiD).":[98],"To":[99],"end,":[101],"propose":[103,130],"semantic":[105],"category-aware":[106],"module":[107],"relationship-aware":[111],"module,":[112],"respectively,":[113],"then":[115],"combine":[116],"two":[118],"by":[119],"re-constraint":[121],"strategy":[122],"obtain":[124],"instance-aware":[125],"attention":[126],"maps.":[127],"Finally,":[128],"weakly":[132,151],"supervised":[133,152,165],"object":[134],"localization-based":[135],"approach":[136],"extract":[138],"multi-scale":[139],"features,":[141],"form":[143],"multi-view":[145],"pipeline.":[146],"method":[148,177],"requires":[149],"only":[150],"at":[154],"label":[156],"level,":[157],"no":[158],"additional":[159],"knowledge":[160],"injection":[161],"or":[162],"other":[163],"strongly":[164],"required.":[168],"Experiments":[169],"three":[171],"benchmark":[172],"datasets":[173],"show":[174],"that":[175],"our":[176],"significantly":[178],"outperforms":[179],"previous":[180],"achieves":[183],"state-of-the-art":[184],"results":[185],"under":[186],"fair":[187],"experimental":[188],"comparisons.":[189]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}