{"id":"https://openalex.org/W3167124826","doi":"https://doi.org/10.1587/transinf.2020edp7226","title":"Deep Metric Learning for Multi-Label and Multi-Object Image Retrieval","display_name":"Deep Metric Learning for Multi-Label and Multi-Object Image Retrieval","publication_year":2021,"publication_date":"2021-05-31","ids":{"openalex":"https://openalex.org/W3167124826","doi":"https://doi.org/10.1587/transinf.2020edp7226","mag":"3167124826"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2020edp7226","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2020edp7226","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E104.D/6/E104.D_2020EDP7226/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/transinf/E104.D/6/E104.D_2020EDP7226/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020315332","display_name":"Jonathan Mojoo","orcid":null},"institutions":[{"id":"https://openalex.org/I113306721","display_name":"Hiroshima University","ror":"https://ror.org/03t78wx29","country_code":"JP","type":"education","lineage":["https://openalex.org/I113306721"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jonathan MOJOO","raw_affiliation_strings":["Department of Information Engineering, Graduate School of Engineering, Hiroshima University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Graduate School of Engineering, Hiroshima University","institution_ids":["https://openalex.org/I113306721"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086456461","display_name":"Takio Kurita","orcid":"https://orcid.org/0000-0003-3982-6750"},"institutions":[{"id":"https://openalex.org/I113306721","display_name":"Hiroshima University","ror":"https://ror.org/03t78wx29","country_code":"JP","type":"education","lineage":["https://openalex.org/I113306721"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takio KURITA","raw_affiliation_strings":["Graduate School of Advanced Science and Engineering, Hiroshima University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Advanced Science and Engineering, Hiroshima University","institution_ids":["https://openalex.org/I113306721"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I113306721"],"apc_list":null,"apc_paid":null,"fwci":0.0942,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.35891348,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"E104.D","issue":"6","first_page":"873","last_page":"880"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998999834060669,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998999834060669,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9979000091552734,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9948999881744385,"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":0.7669861316680908},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7264522910118103},{"id":"https://openalex.org/keywords/jaccard-index","display_name":"Jaccard index","score":0.6895387768745422},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6061813831329346},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5392322540283203},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.53401118516922},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46273431181907654},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.44686219096183777},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.4456756114959717},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.43950724601745605},{"id":"https://openalex.org/keywords/similarity-learning","display_name":"Similarity learning","score":0.42820116877555847},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3627421259880066},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.361230731010437}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7669861316680908},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7264522910118103},{"id":"https://openalex.org/C203519979","wikidata":"https://www.wikidata.org/wiki/Q865360","display_name":"Jaccard index","level":3,"score":0.6895387768745422},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6061813831329346},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5392322540283203},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.53401118516922},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46273431181907654},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.44686219096183777},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.4456756114959717},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.43950724601745605},{"id":"https://openalex.org/C2779597229","wikidata":"https://www.wikidata.org/wiki/Q17146505","display_name":"Similarity learning","level":3,"score":0.42820116877555847},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3627421259880066},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.361230731010437},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transinf.2020edp7226","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2020edp7226","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E104.D/6/E104.D_2020EDP7226/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1587/transinf.2020edp7226","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2020edp7226","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E104.D/6/E104.D_2020EDP7226/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2705815190","display_name":"Training of deep learning models by introducing prior knowledge","funder_award_id":"21K12049","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3167124826.pdf","grobid_xml":"https://content.openalex.org/works/W3167124826.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W968110725","https://openalex.org/W1487583988","https://openalex.org/W1495538789","https://openalex.org/W1510632636","https://openalex.org/W1532499126","https://openalex.org/W1593906416","https://openalex.org/W1786967778","https://openalex.org/W1861492603","https://openalex.org/W1907282891","https://openalex.org/W1909903157","https://openalex.org/W1923967535","https://openalex.org/W1929856797","https://openalex.org/W1939575207","https://openalex.org/W1955055330","https://openalex.org/W1975517671","https://openalex.org/W2007972815","https://openalex.org/W2032042098","https://openalex.org/W2062118960","https://openalex.org/W2073768304","https://openalex.org/W2077069816","https://openalex.org/W2096733369","https://openalex.org/W2100799972","https://openalex.org/W2101498401","https://openalex.org/W2123402141","https://openalex.org/W2146022472","https://openalex.org/W2163605009","https://openalex.org/W2293824885","https://openalex.org/W2296447001","https://openalex.org/W2518092658","https://openalex.org/W2555535051","https://openalex.org/W2562322388","https://openalex.org/W2598634450","https://openalex.org/W2624614404","https://openalex.org/W2738649458","https://openalex.org/W2897656415","https://openalex.org/W2912177220","https://openalex.org/W2963775347","https://openalex.org/W2963907629","https://openalex.org/W2963988212","https://openalex.org/W2966218308","https://openalex.org/W3099206234","https://openalex.org/W3103919331","https://openalex.org/W3125882365","https://openalex.org/W4300560153"],"related_works":["https://openalex.org/W1994775821","https://openalex.org/W2012019886","https://openalex.org/W2091133150","https://openalex.org/W2945869148","https://openalex.org/W2398781203","https://openalex.org/W2009279505","https://openalex.org/W4206503171","https://openalex.org/W4366711670","https://openalex.org/W2558988915","https://openalex.org/W2972216353"],"abstract_inverted_index":{"Content-based":[0],"image":[1,58,89,180,192,252],"retrieval":[2,253],"has":[3],"been":[4,18],"a":[5,13,126,225,238,259,289],"hot":[6],"topic":[7],"among":[8],"computer":[9],"vision":[10],"researchers":[11],"for":[12,109,142,177,285],"long":[14],"time.":[15],"There":[16],"have":[17],"many":[19,42],"advances":[20],"over":[21,214],"the":[22,26,35,123,154,162,184,204,212,265],"years,":[23],"one":[24],"of":[25,37,48,88,125,156,165,168,187,216],"recent":[27],"ones":[28],"being":[29],"deep":[30,38,101,179,267],"metric":[31,49,102,201,236,282],"learning,":[32],"inspired":[33],"by":[34],"success":[36],"neural":[39,62],"networks":[40],"in":[41,100,114,158],"machine":[43],"learning":[44,50,103,178],"tasks.":[45,254],"The":[46],"goal":[47],"is":[51,94,104,119,136,150,209],"to":[52,73,106,151,211,229],"extract":[53],"good":[54,247],"high-level":[55],"features":[56,65],"from":[57],"pixel":[59],"data":[60],"using":[61,258],"networks.":[63],"These":[64],"provide":[66],"useful":[67],"abstractions,":[68],"which":[69,208],"can":[70,269],"enable":[71],"algorithms":[72],"perform":[74],"visual":[75],"comparison":[76],"between":[77,130],"images":[78,287],"with":[79,241],"human-like":[80],"accuracy.":[81],"To":[82],"learn":[83],"these":[84],"features,":[85],"supervised":[86],"information":[87],"similarity":[90,93,108,118,186,200,206,223,235,281],"or":[91,111,144],"relative":[92,185],"often":[95],"used.":[96],"One":[97],"important":[98],"issue":[99],"how":[105],"define":[107],"multi-label":[110,143,189],"multi-object":[112,145,163,191,286],"scenes":[113],"images.":[115,132],"Traditionally,":[116],"pairwise":[117],"defined":[120],"based":[121,182,202],"on":[122,183,203,251,302],"presence":[124],"single":[127],"common":[128,148],"label":[129,218],"two":[131,217,303],"However,":[133],"this":[134,234],"definition":[135],"very":[137],"coarse":[138],"and":[139,190,198,245],"not":[140],"suitable":[141],"data.":[146,193],"Another":[147],"mistake":[149],"completely":[152],"ignore":[153],"multiplicity":[155],"objects":[157],"images,":[159],"hence":[160],"ignoring":[161],"facet":[164],"certain":[166],"types":[167],"datasets.":[169,305],"In":[170],"our":[171,279],"work,":[172],"we":[173,221],"propose":[174],"an":[175,196,242],"approach":[176],"representations":[181],"both":[188],"We":[194,232,255,275],"introduce":[195],"intuitive":[197],"effective":[199],"Jaccard":[205],"coefficient,":[207],"equivalent":[210],"intersection":[213],"union":[215],"sets.":[219],"Hence":[220],"treat":[222],"as":[224,227],"continuous,":[226],"opposed":[228],"discrete":[230],"quantity.":[231],"incorporate":[233],"into":[237],"triplet":[239],"loss":[240],"adaptive":[243],"margin,":[244],"achieve":[246],"mean":[248],"average":[249],"precision":[250],"further":[256],"show,":[257],"recently":[260],"proposed":[261,280,291,296],"quantization":[262],"method,":[263],"that":[264,278],"resulting":[266],"feature":[268],"be":[270],"quantized":[271],"whilst":[272],"preserving":[273],"similarity.":[274],"also":[276],"show":[277],"performs":[283],"better":[284],"than":[288],"previously":[290],"cosine":[292],"similarity-based":[293],"metric.":[294],"Our":[295],"method":[297],"outperforms":[298],"several":[299],"state-of-the-art":[300],"methods":[301],"benchmark":[304]},"counts_by_year":[{"year":2025,"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"}