{"id":"https://openalex.org/W7128909294","doi":"https://doi.org/10.1007/s44443-026-00546-4","title":"Frequency-adaptive prototype learning for long-tail scene graph generation","display_name":"Frequency-adaptive prototype learning for long-tail scene graph generation","publication_year":2026,"publication_date":"2026-02-14","ids":{"openalex":"https://openalex.org/W7128909294","doi":"https://doi.org/10.1007/s44443-026-00546-4"},"language":"en","primary_location":{"id":"doi:10.1007/s44443-026-00546-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44443-026-00546-4","pdf_url":null,"source":{"id":"https://openalex.org/S2764955546","display_name":"Journal of King Saud University - Computer and Information Sciences","issn_l":"1319-1578","issn":["1319-1578","2213-1248"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of King Saud University Computer and Information Sciences","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1007/s44443-026-00546-4","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126020111","display_name":"Funing Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Funing Xie","raw_affiliation_strings":["Jiangsu Key Laboratory of Intelligent Information Processing and Communication Technology, Nanjing University of Posts and Telecommunications, Nanjing, 210003, JiangSu, China","School of Communications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, 210003, JiangSu, China"],"raw_orcid":"https://orcid.org/0009-0001-0533-5729","affiliations":[{"raw_affiliation_string":"Jiangsu Key Laboratory of Intelligent Information Processing and Communication Technology, Nanjing University of Posts and Telecommunications, Nanjing, 210003, JiangSu, China","institution_ids":["https://openalex.org/I41198531"]},{"raw_affiliation_string":"School of Communications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, 210003, JiangSu, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027520275","display_name":"Yahong Wu","orcid":"https://orcid.org/0000-0002-9536-0011"},"institutions":[{"id":"https://openalex.org/I4210101451","display_name":"Nanjing University of Industry Technology","ror":"https://ror.org/00qf07q44","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210101451"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"YaHong Wu","raw_affiliation_strings":["Nanjing Vocational University of Industry Technology, Nanjing, 210023, JiangSu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing Vocational University of Industry Technology, Nanjing, 210023, JiangSu, China","institution_ids":["https://openalex.org/I4210101451"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126004715","display_name":"Feng Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Feng Liu","raw_affiliation_strings":["Jiangsu Key Laboratory of Intelligent Information Processing and Communication Technology, Nanjing University of Posts and Telecommunications, Nanjing, 210003, JiangSu, China","School of Communications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, 210003, JiangSu, China"],"raw_orcid":"https://orcid.org/0000-0003-2750-0315","affiliations":[{"raw_affiliation_string":"Jiangsu Key Laboratory of Intelligent Information Processing and Communication Technology, Nanjing University of Posts and Telecommunications, Nanjing, 210003, JiangSu, China","institution_ids":["https://openalex.org/I41198531"]},{"raw_affiliation_string":"School of Communications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, 210003, JiangSu, China","institution_ids":["https://openalex.org/I41198531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5126004715"],"corresponding_institution_ids":["https://openalex.org/I41198531"],"apc_list":{"value":1350,"currency":"USD","value_usd":1350},"apc_paid":{"value":1350,"currency":"USD","value_usd":1350},"fwci":19.7937,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.98915633,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"38","issue":"4","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8826000094413757,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8826000094413757,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.03020000085234642,"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":0.019700000062584877,"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/scene-graph","display_name":"Scene graph","score":0.5623999834060669},{"id":"https://openalex.org/keywords/confusion","display_name":"Confusion","score":0.5472999811172485},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4950999915599823},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.490200012922287},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.46869999170303345},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.36890000104904175},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.36649999022483826}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7608000040054321},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5814999938011169},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.5623999834060669},{"id":"https://openalex.org/C2781140086","wikidata":"https://www.wikidata.org/wiki/Q557945","display_name":"Confusion","level":2,"score":0.5472999811172485},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4950999915599823},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.490200012922287},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4864000082015991},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.46869999170303345},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.36890000104904175},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.36649999022483826},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.34439998865127563},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3425000011920929},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.33559998869895935},{"id":"https://openalex.org/C47177190","wikidata":"https://www.wikidata.org/wiki/Q207137","display_name":"Curriculum","level":2,"score":0.32260000705718994},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3190999925136566},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2924000024795532},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.2651999890804291}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s44443-026-00546-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44443-026-00546-4","pdf_url":null,"source":{"id":"https://openalex.org/S2764955546","display_name":"Journal of King Saud University - Computer and Information Sciences","issn_l":"1319-1578","issn":["1319-1578","2213-1248"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of King Saud University Computer and Information Sciences","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:7216b0747db74afd9adcb3c30fb21c80","is_oa":true,"landing_page_url":"https://doaj.org/article/7216b0747db74afd9adcb3c30fb21c80","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":"Journal of King Saud University: Computer and Information Sciences, Vol 38, Iss 4 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s44443-026-00546-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44443-026-00546-4","pdf_url":null,"source":{"id":"https://openalex.org/S2764955546","display_name":"Journal of King Saud University - Computer and Information Sciences","issn_l":"1319-1578","issn":["1319-1578","2213-1248"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of King Saud University Computer and Information Sciences","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.45432284474372864,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G6357699058","display_name":null,"funder_award_id":"62177029","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2077069816","https://openalex.org/W2086161653","https://openalex.org/W2277195237","https://openalex.org/W2340690086","https://openalex.org/W2591644541","https://openalex.org/W2896348597","https://openalex.org/W2963351448","https://openalex.org/W2963518342","https://openalex.org/W2963536419","https://openalex.org/W2963938081","https://openalex.org/W3034538190","https://openalex.org/W3035017890","https://openalex.org/W3092900959","https://openalex.org/W3095707208","https://openalex.org/W3174865181","https://openalex.org/W3181556077","https://openalex.org/W3182902595","https://openalex.org/W3185895012","https://openalex.org/W3191092153","https://openalex.org/W3196936439","https://openalex.org/W4214693531","https://openalex.org/W4225868495","https://openalex.org/W4280538209","https://openalex.org/W4283463548","https://openalex.org/W4288083516","https://openalex.org/W4367316179","https://openalex.org/W4386075638","https://openalex.org/W4387968447","https://openalex.org/W4390873633","https://openalex.org/W4393154528","https://openalex.org/W4399565495","https://openalex.org/W4404544782","https://openalex.org/W4405056285","https://openalex.org/W4409365924","https://openalex.org/W4414359857"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Scene":[1],"graph":[2],"generation":[3],"aims":[4],"to":[5,61,90,102,144,204],"detect":[6],"visual":[7,18],"objects":[8],"and":[9,30,119,173,185,212],"their":[10],"relationships":[11,146],"in":[12],"images,":[13],"providing":[14],"structured":[15],"representations":[16],"for":[17,123,130],"scene":[19],"understanding.":[20,152],"However,":[21],"it":[22],"faces":[23],"fundamental":[24],"challenges":[25],"from":[26,105,142],"extreme":[27],"long-tail":[28],"distribution":[29],"semantic":[31,113,151],"ambiguities":[32],"between":[33,116],"related":[34,117],"predicates.":[35],"The":[36],"severe":[37],"class":[38],"imbalance\u2014where":[39],"head":[40,88,162],"classes":[41,48,66],"dominate":[42],"with":[43,196],"abundant":[44],"samples":[45],"while":[46,96,126,218],"tail":[47,97,177],"have":[49],"scarce":[50],"training":[51,140],"instances\u2014creates":[52],"distinct":[53],"learning":[54,104,135,163],"dynamics":[55],"that":[56,77,86,111,137,191],"existing":[57],"re-balancing":[58],"methods":[59],"fail":[60],"address":[62],"by":[63],"treating":[64],"all":[65],"uniformly.":[67],"We":[68],"propose":[69],"Frequency-Adaptive":[70],"Prototype":[71],"Learning":[72],"(FAPL),":[73],"a":[74,156],"unified":[75],"framework":[76],"introduces":[78],"three":[79],"key":[80],"innovations:":[81],"(1)":[82],"frequency-aware":[83],"momentum":[84],"scheduling":[85,175],"enables":[87],"prototypes":[89,98],"stabilize":[91],"early":[92,161],"as":[93,147],"knowledge":[94,166],"sources":[95],"maintain":[99],"aggressive":[100],"adaptation":[101],"maximize":[103],"limited":[106],"samples;":[107],"(2)":[108],"pattern-aware":[109,168],"supervision":[110,129,169],"learns":[112],"confusion":[114,171],"patterns":[115],"predicates":[118],"adaptively":[120],"reduces":[121,170],"penalties":[122],"plausible":[124],"errors":[125],"maintaining":[127],"full":[128],"implausible":[131],"ones;":[132],"(3)":[133],"curriculum":[134,174],"integration":[136],"progressively":[138],"shifts":[139],"emphasis":[141],"frequent":[143],"rare":[145],"the":[148],"model":[149],"accumulates":[150],"These":[153],"components":[154],"form":[155],"mutually":[157],"reinforcing":[158],"system":[159],"where":[160],"establishes":[164],"reliable":[165],"bases,":[167],"noise,":[172],"maximizes":[176],"exploitation.":[178],"Extensive":[179],"experiments":[180],"on":[181,206,210,214,223],"Visual":[182,207],"Genome,":[183,208],"GQA,":[184,211],"Open":[186,215],"Images":[187,216],"V6":[188],"datasets":[189],"demonstrate":[190],"FAPL":[192],"achieves":[193],"state-of-the-art":[194],"performance":[195],"substantial":[197],"improvements":[198],"over":[199],"previous":[200],"best":[201],"methods:":[202],"up":[203],"30.3%":[205],"28.8%":[209],"19.9%":[213],"V6,":[217],"showing":[219],"superior":[220],"generalization":[221],"capability":[222],"recognizing":[224],"unseen":[225],"relationship":[226],"combinations.":[227]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-02-15T00:00:00"}