{"id":"https://openalex.org/W7163009462","doi":"https://doi.org/10.1007/s11263-026-02855-7","title":"Multi-level Compositional Feature Augmentation for Unbiased Scene Graph Generation","display_name":"Multi-level Compositional Feature Augmentation for Unbiased Scene Graph Generation","publication_year":2026,"publication_date":"2026-06-01","ids":{"openalex":"https://openalex.org/W7163009462","doi":"https://doi.org/10.1007/s11263-026-02855-7"},"language":"en","primary_location":{"id":"doi:10.1007/s11263-026-02855-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-026-02855-7","pdf_url":null,"source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1007/s11263-026-02855-7","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137564190","display_name":"Lin Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137599998","display_name":"Xingchen Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xingchen Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137586229","display_name":"Chong Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chong Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137543182","display_name":"Chen Li","orcid":"https://orcid.org/0000-0002-3782-0737"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137582951","display_name":"Long Chen","orcid":"https://orcid.org/0000-0001-6148-9709"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Long Chen","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-6148-9709","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2890,"currency":"EUR","value_usd":3690},"apc_paid":{"value":2890,"currency":"EUR","value_usd":3690},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.68740398,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"134","issue":"6","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":0.9426000118255615,"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":0.9426000118255615,"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":0.019500000402331352,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.01119999960064888,"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/debiasing","display_name":"Debiasing","score":0.7560999989509583},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.6093000173568726},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5640000104904175},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.5175999999046326},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48500001430511475},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.4805000126361847},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.461899995803833}],"concepts":[{"id":"https://openalex.org/C2779458634","wikidata":"https://www.wikidata.org/wiki/Q24963715","display_name":"Debiasing","level":2,"score":0.7560999989509583},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7166000008583069},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.618399977684021},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.6093000173568726},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5640000104904175},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.5175999999046326},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48500001430511475},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.4805000126361847},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.461899995803833},{"id":"https://openalex.org/C140146324","wikidata":"https://www.wikidata.org/wiki/Q1144319","display_name":"Predicate (mathematical logic)","level":2,"score":0.4521999955177307},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3939000070095062},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.34310001134872437},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2896000146865845},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C68537008","wikidata":"https://www.wikidata.org/wiki/Q247932","display_name":"Stereopsis","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2678999900817871}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s11263-026-02855-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-026-02855-7","pdf_url":null,"source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-172360","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-172360","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1007/s11263-026-02855-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-026-02855-7","pdf_url":null,"source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3968723235","display_name":null,"funder_award_id":"General Research Fund (16219025)","funder_id":"https://openalex.org/F4320329815","funder_display_name":"Hong Kong Government"},{"id":"https://openalex.org/G6641844733","display_name":null,"funder_award_id":"62522216","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8097908279","display_name":null,"funder_award_id":"Early Career Scheme (26208924)","funder_id":"https://openalex.org/F4320329815","funder_display_name":"Hong Kong Government"},{"id":"https://openalex.org/G8814884665","display_name":null,"funder_award_id":"62402408","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320316083","display_name":"Tencent","ror":"https://ror.org/00hhjss72"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324196","display_name":"Innovation and Technology Commission - Hong Kong","ror":"https://ror.org/04vf9tr09"},{"id":"https://openalex.org/F4320329815","display_name":"Hong Kong Government","ror":"https://ror.org/034179816"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W2250539671","https://openalex.org/W2277195237","https://openalex.org/W2479423890","https://openalex.org/W2565639579","https://openalex.org/W2579549467","https://openalex.org/W2591644541","https://openalex.org/W2896659472","https://openalex.org/W2948672349","https://openalex.org/W2962785943","https://openalex.org/W2962933664","https://openalex.org/W2963518342","https://openalex.org/W2963536419","https://openalex.org/W2963938081","https://openalex.org/W2987123286","https://openalex.org/W2998508940","https://openalex.org/W3035017890","https://openalex.org/W3081642947","https://openalex.org/W3095624694","https://openalex.org/W3096609285","https://openalex.org/W3096688134","https://openalex.org/W3109754877","https://openalex.org/W3181556077","https://openalex.org/W3191092153","https://openalex.org/W3196936439","https://openalex.org/W3197395033","https://openalex.org/W3201861986","https://openalex.org/W3205051885","https://openalex.org/W4206162816","https://openalex.org/W4214611271","https://openalex.org/W4214693531","https://openalex.org/W4221150632","https://openalex.org/W4225868495","https://openalex.org/W4225998785","https://openalex.org/W4312429751","https://openalex.org/W4312555984","https://openalex.org/W4312682661","https://openalex.org/W4313037583","https://openalex.org/W4313161463","https://openalex.org/W4380303580","https://openalex.org/W4386075933","https://openalex.org/W4386076027","https://openalex.org/W4388191728","https://openalex.org/W4390873003","https://openalex.org/W4390873633","https://openalex.org/W4402715983","https://openalex.org/W4402944023","https://openalex.org/W4403791750","https://openalex.org/W4404544782","https://openalex.org/W4406982839","https://openalex.org/W4416513609"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Scene":[1],"Graph":[2],"Generation":[3],"(SGG)":[4],"aims":[5,139],"to":[6,51,64,101,140,182,201,210],"detect":[7],"all":[8,96],"the":[9,21,31,46,52,65,69,84,103,106,142,146,150,170,199,235],"visual":[10,174,205],"relation":[11,38,107],"triplets":[12,177],"<,":[13],",":[14,164,193],">":[15],"in":[16,36],"a":[17,124,230],"given":[18],"image.":[19],"With":[20],"emergence":[22],"of":[23,86,105,110,148,152,176],"various":[24,220],"advanced":[25],"techniques":[26],"for":[27,74,116,187,207],"better":[28],"utilizing":[29],"both":[30],"intrinsic":[32,171],"and":[33],"extrinsic":[34,173],"information":[35],"each":[37,111],"triplet,":[39],"SGG":[40,58,75,221],"has":[41],"achieved":[42],"great":[43],"progress":[44],"over":[45],"recent":[47],"years.":[48],"However,":[49],"due":[50],"ubiquitous":[53],"long-tailed":[54],"predicate":[55],"distributions,":[56],"today\u2019s":[57],"models":[59],"are":[60,76],"still":[61],"easily":[62],"biased":[63],"head":[66],"predicates.":[67],"Currently,":[68],"most":[70],"prevalent":[71],"debiasing":[72],"solutions":[73],"re-balancing":[77,98],"methods,":[78],"e":[79,167,196],".":[80,166,195],"g":[81],".,":[82,168,197],"changing":[83],"distributions":[85],"original":[87],"training":[88],"samples.":[89],"In":[90],"this":[91,120],"paper,":[92],"we":[93,122,156],"argue":[94],"that":[95,227],"existing":[97],"strategies":[99],"fail":[100],"increase":[102],"diversity":[104,151,159],"triplet":[108,153],"features":[109,175],"predicate,":[112],"which":[113,138],"is":[114],"critical":[115],"robust":[117],"SGG.":[118],"To":[119],"end,":[121],"propose":[123],"novel":[125,184],"M":[126],"ulti-level":[127],"C":[128],"ompositional":[129],"F":[130],"eature":[131],"A":[132],"ugmentation":[133],"(":[134],"MCFA":[135,214,228],")":[136],"strategy,":[137],"mitigate":[141],"bias":[143],"issue":[144],"from":[145],"perspective":[147],"increasing":[149],"features.":[154],"Specifically,":[155],"enhance":[157],"relationship":[158],"on":[160,234],"not":[161],"only":[162],"feature-level":[163],"i":[165,194],"replacing":[169],"or":[172],"with":[178],"other":[179],"correlated":[180],"samples":[181],"create":[183],"feature":[185],"compositions":[186],"tail":[188],"predicates,":[189],"but":[190],"also":[191],"image-level":[192],"manipulating":[198],"image":[200],"generate":[202],"brand":[203],"new":[204,231],"appearance":[206],"triplets.":[208],"Due":[209],"its":[211],"model-agnostic":[212],"nature,":[213],"can":[215],"be":[216],"seamlessly":[217],"incorporated":[218],"into":[219],"frameworks.":[222],"Extensive":[223],"ablations":[224],"have":[225],"shown":[226],"achieves":[229],"state-of-the-art":[232],"performance":[233],"trade-off":[236],"between":[237],"different":[238],"metrics.":[239]},"counts_by_year":[],"updated_date":"2026-06-02T06:25:09.198175","created_date":"2026-06-02T00:00:00"}