{"id":"https://openalex.org/W3095203785","doi":"https://doi.org/10.1109/access.2020.3036185","title":"A Novel Soft Margin Loss Function for Deep Discriminative Embedding Learning","display_name":"A Novel Soft Margin Loss Function for Deep Discriminative Embedding Learning","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3095203785","doi":"https://doi.org/10.1109/access.2020.3036185","mag":"3095203785"},"language":"en","primary_location":{"id":"doi:10.1109/access.2020.3036185","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3036185","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09249024.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09249024.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101946741","display_name":"Zhao Yang","orcid":"https://orcid.org/0000-0003-4688-1395"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao Yang","raw_affiliation_strings":["Huangpu Research and Graduate School, Guangzhou University, Guangzhou, China","School of Electronics and Communication Engineering, Guangzhou University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-4688-1395","affiliations":[{"raw_affiliation_string":"Huangpu Research and Graduate School, Guangzhou University, Guangzhou, China","institution_ids":["https://openalex.org/I37987034"]},{"raw_affiliation_string":"School of Electronics and Communication Engineering, Guangzhou University, Guangzhou, China","institution_ids":["https://openalex.org/I37987034"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100321097","display_name":"Tie Liu","orcid":"https://orcid.org/0000-0002-0968-1645"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tie Liu","raw_affiliation_strings":["Huangpu Research and Graduate School, Guangzhou University, Guangzhou, China","School of Electronics and Communication Engineering, Guangzhou University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huangpu Research and Graduate School, Guangzhou University, Guangzhou, China","institution_ids":["https://openalex.org/I37987034"]},{"raw_affiliation_string":"School of Electronics and Communication Engineering, Guangzhou University, Guangzhou, China","institution_ids":["https://openalex.org/I37987034"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051667418","display_name":"Jiehao Liu","orcid":"https://orcid.org/0000-0002-9835-2797"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiehao Liu","raw_affiliation_strings":["Huangpu Research and Graduate School, Guangzhou University, Guangzhou, China","School of Electronics and Communication Engineering, Guangzhou University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huangpu Research and Graduate School, Guangzhou University, Guangzhou, China","institution_ids":["https://openalex.org/I37987034"]},{"raw_affiliation_string":"School of Electronics and Communication Engineering, Guangzhou University, Guangzhou, China","institution_ids":["https://openalex.org/I37987034"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100336188","display_name":"Li Wang","orcid":"https://orcid.org/0000-0003-1817-8213"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Wang","raw_affiliation_strings":["Huangpu Research and Graduate School, Guangzhou University, Guangzhou, China","School of Electronics and Communication Engineering, Guangzhou University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huangpu Research and Graduate School, Guangzhou University, Guangzhou, China","institution_ids":["https://openalex.org/I37987034"]},{"raw_affiliation_string":"School of Electronics and Communication Engineering, Guangzhou University, Guangzhou, China","institution_ids":["https://openalex.org/I37987034"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003101676","display_name":"Sai Zhao","orcid":"https://orcid.org/0000-0001-6572-5289"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sai Zhao","raw_affiliation_strings":["Huangpu Research and Graduate School, Guangzhou University, Guangzhou, China","School of Electronics and Communication Engineering, Guangzhou University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-6572-5289","affiliations":[{"raw_affiliation_string":"Huangpu Research and Graduate School, Guangzhou University, Guangzhou, China","institution_ids":["https://openalex.org/I37987034"]},{"raw_affiliation_string":"School of Electronics and Communication Engineering, Guangzhou University, Guangzhou, China","institution_ids":["https://openalex.org/I37987034"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.6852,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.7261625,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"8","issue":null,"first_page":"202785","last_page":"202794"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","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/T10331","display_name":"Video Surveillance and Tracking Methods","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/T11448","display_name":"Face recognition and analysis","score":0.9980999827384949,"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/T12740","display_name":"Gait Recognition and Analysis","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.9429421424865723},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7755991220474243},{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.7707763314247131},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7389721870422363},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7340608835220337},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.7331287860870361},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7190159559249878},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.664749264717102},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6255781650543213},{"id":"https://openalex.org/keywords/hypersphere","display_name":"Hypersphere","score":0.6226096749305725},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5740925669670105},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5417112112045288},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5380316376686096},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5104535818099976},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4143143892288208},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.28855717182159424}],"concepts":[{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.9429421424865723},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7755991220474243},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.7707763314247131},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7389721870422363},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7340608835220337},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.7331287860870361},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7190159559249878},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.664749264717102},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6255781650543213},{"id":"https://openalex.org/C2776562905","wikidata":"https://www.wikidata.org/wiki/Q306610","display_name":"Hypersphere","level":2,"score":0.6226096749305725},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5740925669670105},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5417112112045288},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5380316376686096},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5104535818099976},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4143143892288208},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28855717182159424},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2020.3036185","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3036185","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09249024.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:ed93ffffd4a34a4d86eb3bddbddcade2","is_oa":true,"landing_page_url":"https://doaj.org/article/ed93ffffd4a34a4d86eb3bddbddcade2","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 8, Pp 202785-202794 (2020)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2020.3036185","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3036185","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09249024.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7400000095367432}],"awards":[{"id":"https://openalex.org/G1651591002","display_name":null,"funder_award_id":"YB201712","funder_id":"https://openalex.org/F4320328715","funder_display_name":"Guangzhou University"},{"id":"https://openalex.org/G3963971169","display_name":null,"funder_award_id":"2018KTSCX174","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4826948058","display_name":null,"funder_award_id":"YB201712","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5267856620","display_name":null,"funder_award_id":"61902084","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8603763248","display_name":null,"funder_award_id":"61501177","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/F4320328715","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3095203785.pdf","grobid_xml":"https://content.openalex.org/works/W3095203785.grobid-xml"},"referenced_works_count":59,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1982925187","https://openalex.org/W2096733369","https://openalex.org/W2108598243","https://openalex.org/W2112796928","https://openalex.org/W2138621090","https://openalex.org/W2145287260","https://openalex.org/W2194775991","https://openalex.org/W2467139031","https://openalex.org/W2502225121","https://openalex.org/W2512434173","https://openalex.org/W2519904008","https://openalex.org/W2520774990","https://openalex.org/W2581377246","https://openalex.org/W2584637367","https://openalex.org/W2598634450","https://openalex.org/W2606377603","https://openalex.org/W2756012011","https://openalex.org/W2768610172","https://openalex.org/W2798775284","https://openalex.org/W2799251491","https://openalex.org/W2810967842","https://openalex.org/W2885476150","https://openalex.org/W2889513363","https://openalex.org/W2894016331","https://openalex.org/W2903318697","https://openalex.org/W2919317477","https://openalex.org/W2962706983","https://openalex.org/W2962898354","https://openalex.org/W2962926870","https://openalex.org/W2963161580","https://openalex.org/W2963200533","https://openalex.org/W2963383990","https://openalex.org/W2963466847","https://openalex.org/W2963656735","https://openalex.org/W2963744743","https://openalex.org/W2963842104","https://openalex.org/W2964121744","https://openalex.org/W2964130064","https://openalex.org/W2969985801","https://openalex.org/W2996695408","https://openalex.org/W2997686768","https://openalex.org/W2998508940","https://openalex.org/W3018349615","https://openalex.org/W3021068195","https://openalex.org/W3099206234","https://openalex.org/W3105077954","https://openalex.org/W4297798436","https://openalex.org/W6631190155","https://openalex.org/W6724544503","https://openalex.org/W6726373078","https://openalex.org/W6726946684","https://openalex.org/W6732696085","https://openalex.org/W6735013348","https://openalex.org/W6735531217","https://openalex.org/W6744010052","https://openalex.org/W6747428963","https://openalex.org/W6755604751","https://openalex.org/W6772526470"],"related_works":["https://openalex.org/W2810967842","https://openalex.org/W4283819496","https://openalex.org/W2970046029","https://openalex.org/W3095152779","https://openalex.org/W2963466847","https://openalex.org/W2609296554","https://openalex.org/W3128220219","https://openalex.org/W2969546590","https://openalex.org/W4200526356","https://openalex.org/W3119773509"],"abstract_inverted_index":{"Deep":[0],"embedding":[1,86,200],"learning":[2],"aims":[3],"to":[4,99,178,194],"learn":[5,166],"discriminative":[6],"feature":[7,34,63],"representations":[8],"through":[9],"a":[10,18,21,25,70,81,129],"deep":[11,85],"convolutional":[12],"neural":[13],"network":[14,22],"model.":[15],"Commonly,":[16],"such":[17],"model":[19,164],"contains":[20],"architecture":[23,29],"and":[24,51,95,119,143,215],"loss":[26,38,57,72,77,110],"function.":[27],"The":[28],"is":[30,59,133],"responsible":[31],"for":[32,61,84],"hierarchical":[33],"extraction,":[35],"while":[36],"the":[37,41,45,62,92,96,103,112,115,125,136,140,155,163,180,183,196],"function":[39,58,73],"supervises":[40],"training":[42,157],"procedure":[43],"with":[44,111,128,158,168],"purpose":[46],"of":[47,146,182,199],"maximizing":[48],"inter-class":[49,121,141],"separability":[50],"intra-class":[52,117,144],"compactness.":[53],"By":[54,123],"considering":[55],"that":[56,132],"crucial":[60],"performance,":[64],"in":[65,135],"this":[66],"article":[67],"we":[68,89,107],"propose":[69],"new":[71],"called":[74],"soft":[75,130],"margin":[76,131],"(SML)":[78],"based":[79],"on":[80,173,188,207,218],"classification":[82,97],"framework":[83],"learning.":[87,201],"Specifically,":[88,202],"first":[90],"normalize":[91],"learned":[93,147],"features":[94,148,167],"weights":[98],"map":[100],"them":[101],"into":[102],"hypersphere.":[104],"After":[105],"that,":[106],"construct":[108],"our":[109],"difference":[113,127],"between":[114],"maximum":[116],"distance":[118,126],"minimum":[120],"distance.":[122],"constraining":[124],"inherent":[134],"proposed":[137,184],"loss,":[138,162],"both":[139],"discrepancy":[142],"compactness":[145],"can":[149,165],"be":[150],"effectively":[151],"improved.":[152],"Finally,":[153],"under":[154],"joint":[156],"an":[159],"improved":[160],"softmax":[161],"strong":[169],"discriminability.":[170],"Toy":[171],"experiments":[172,187],"MNIST":[174],"dataset":[175,212,220],"are":[176,191,223],"conducted":[177],"show":[179],"effectiveness":[181],"method.":[185],"Additionally,":[186],"re-identification":[189],"tasks":[190],"also":[192],"provided":[193],"demonstrate":[195],"superior":[197],"performance":[198],"65.48%":[203],"/":[204,210],"62.68%":[205],"mAP":[206,217],"CUHK03":[208],"labeled":[209],"detected":[211],"(person":[213],"re-id)":[214,222],"74.36%":[216],"VeRi-776":[219],"(vehicle":[221],"achieved":[224],"respectively.":[225]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}