{"id":"https://openalex.org/W4410244032","doi":"https://doi.org/10.32604/cmc.2025.064403","title":"Efficient Method for Trademark Image Retrieval: Leveraging Siamese and Triplet Networks with Examination-Informed Loss Adjustment","display_name":"Efficient Method for Trademark Image Retrieval: Leveraging Siamese and Triplet Networks with Examination-Informed Loss Adjustment","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4410244032","doi":"https://doi.org/10.32604/cmc.2025.064403"},"language":"en","primary_location":{"id":"doi:10.32604/cmc.2025.064403","is_oa":true,"landing_page_url":"https://doi.org/10.32604/cmc.2025.064403","pdf_url":null,"source":{"id":"https://openalex.org/S4210191605","display_name":"Computers, materials & continua/Computers, materials & continua (Print)","issn_l":"1546-2218","issn":["1546-2218","1546-2226"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers, Materials & Continua","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.32604/cmc.2025.064403","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044051305","display_name":"Thanh Bui-Minh","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Thanh Bui-Minh","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073341529","display_name":"Nguy\u1ec5n Long Giang","orcid":"https://orcid.org/0000-0001-6184-1469"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nguyen Long Giang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5091557333","display_name":"Luan Thanh Le","orcid":"https://orcid.org/0000-0002-3850-180X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luan Thanh Le","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5044051305"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.2762,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.95558968,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"84","issue":"1","first_page":"1203","last_page":"1226"},"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":0.9976000189781189,"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":0.9976000189781189,"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":0.9959999918937683,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.9514999985694885,"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/trademark","display_name":"Trademark","score":0.9060993194580078},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.550334095954895},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.49178841710090637},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.44812294840812683},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.37702131271362305},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3355679214000702},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3250353932380676}],"concepts":[{"id":"https://openalex.org/C2779027411","wikidata":"https://www.wikidata.org/wiki/Q167270","display_name":"Trademark","level":2,"score":0.9060993194580078},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.550334095954895},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49178841710090637},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.44812294840812683},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37702131271362305},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3355679214000702},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3250353932380676},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.32604/cmc.2025.064403","is_oa":true,"landing_page_url":"https://doi.org/10.32604/cmc.2025.064403","pdf_url":null,"source":{"id":"https://openalex.org/S4210191605","display_name":"Computers, materials & continua/Computers, materials & continua (Print)","issn_l":"1546-2218","issn":["1546-2218","1546-2226"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers, Materials & Continua","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.32604/cmc.2025.064403","is_oa":true,"landing_page_url":"https://doi.org/10.32604/cmc.2025.064403","pdf_url":null,"source":{"id":"https://openalex.org/S4210191605","display_name":"Computers, materials & continua/Computers, materials & continua (Print)","issn_l":"1546-2218","issn":["1546-2218","1546-2226"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers, Materials & Continua","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2026911973","https://openalex.org/W2088548213","https://openalex.org/W2119605622","https://openalex.org/W2151103935","https://openalex.org/W2900397111","https://openalex.org/W3013726901","https://openalex.org/W3033624263","https://openalex.org/W3044838616","https://openalex.org/W3048723005","https://openalex.org/W3119247219","https://openalex.org/W3119589206","https://openalex.org/W3134001904","https://openalex.org/W3158402395","https://openalex.org/W3193269151","https://openalex.org/W4205460046","https://openalex.org/W4289638459","https://openalex.org/W4293499194","https://openalex.org/W4384131097","https://openalex.org/W4385194761","https://openalex.org/W4385362240","https://openalex.org/W4399088426","https://openalex.org/W4400930124","https://openalex.org/W4403741394","https://openalex.org/W4404438122","https://openalex.org/W4404673216"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Image-based":[0],"similar":[1,55],"trademark":[2,12,20,58,74,128,192,243,252,257],"retrieval":[3,129,253],"is":[4],"a":[5,43,87,198],"time-consuming":[6],"and":[7,56,73,85,104,166,178,180,184,249],"labor-intensive":[8],"task":[9],"in":[10,141,259],"the":[11,80,113,127,135,190,206,223,231,235,238,247],"examination":[13],"process.":[14],"This":[15,77],"paper":[16,236],"aims":[17],"to":[18,111,133,245],"support":[19],"examiners":[21,258],"by":[22],"training":[23,92],"Deep":[24],"Convolutional":[25],"Neural":[26],"Network":[27],"(DCNN)":[28],"models":[29,100],"for":[30,82,91,126],"effective":[31,115],"Trademark":[32],"Image":[33],"Retrieval":[34],"(TIR).":[35],"To":[36],"achieve":[37],"this":[38],"goal,":[39],"we":[40,118,215],"first":[41],"develop":[42],"novel":[44],"labeling":[45,84],"method":[46],"that":[47,148,217],"automatically":[48,142],"generates":[49],"hundreds":[50],"of":[51,53,137,176,182,203,222,240,251],"thousands":[52],"labeled":[54],"dissimilar":[57],"image":[59],"pairs":[60],"using":[61],"accompanying":[62],"data":[63,244],"fields":[64],"such":[65],"as":[66],"citation":[67],"lists,":[68],"Vienna":[69],"classification":[70],"(VC)":[71],"codes,":[72],"ownership":[75],"information.":[76],"approach":[78],"eliminates":[79],"need":[81],"manual":[83],"provides":[86],"large-scale":[88],"dataset":[89,193],"suitable":[90],"deep":[93],"learning":[94],"models.":[95],"We":[96],"then":[97],"train":[98],"DCNN":[99],"based":[101],"on":[102,189,212],"Siamese":[103],"Triplet":[105],"architectures,":[106],"evaluating":[107],"various":[108],"feature":[109],"extractors":[110],"determine":[112],"most":[114],"configuration.":[116],"Furthermore,":[117],"present":[119],"an":[120],"Adapted":[121],"Contrastive":[122],"Loss":[123],"Function":[124],"(ACLF)":[125],"task,":[130],"specifically":[131],"engineered":[132],"mitigate":[134],"influence":[136],"noisy":[138],"labels":[139],"found":[140],"created":[143],"datasets.":[144],"Experimental":[145],"results":[146],"indicate":[147],"our":[149,195],"proposed":[150],"model":[151,196],"(Efficient-Net_v21_Siamese)":[152],"performs":[153],"best":[154],"at":[155],"both":[156],"True":[157,172],"Negative":[158],"Rate":[159],"(TNR)":[160],"threshold":[161],"levels,":[162],"TNR":[163,167],"=":[164,168],"0.9":[165],"0.95,":[169],"with":[170],"respective":[171],"Positive":[173],"Rates":[174],"(TPRs)":[175],"77.7%":[177],"70.8%":[179],"accuracies":[181],"83.9%":[183],"80.4%.":[185],"Additionally,":[186],"when":[187],"testing":[188],"public":[191],"METU_v2,":[194],"achieves":[197],"normalized":[199],"average":[200],"rank":[201],"(NAR)":[202],"0.0169,":[204],"outperforming":[205],"current":[207],"state-of-the-art":[208],"(SOTA)":[209],"model.":[210],"Based":[211],"these":[213],"findings,":[214],"estimate":[216],"considering":[218],"only":[219],"approximately":[220],"10%":[221],"returned":[224],"trademarks":[225],"would":[226],"be":[227],"sufficient,":[228],"significantly":[229],"reducing":[230],"review":[232],"time.":[233],"Therefore,":[234],"highlights":[237],"potential":[239],"utilizing":[241],"national":[242],"enhance":[246],"accuracy":[248],"efficiency":[250],"systems,":[254],"ultimately":[255],"supporting":[256],"their":[260],"evaluation":[261],"tasks.":[262]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}