{"id":"https://openalex.org/W4310642348","doi":"https://doi.org/10.1109/tip.2022.3224872","title":"State-Aware Compositional Learning Toward Unbiased Training for Scene Graph Generation","display_name":"State-Aware Compositional Learning Toward Unbiased Training for Scene Graph Generation","publication_year":2022,"publication_date":"2022-12-02","ids":{"openalex":"https://openalex.org/W4310642348","doi":"https://doi.org/10.1109/tip.2022.3224872","pmid":"https://pubmed.ncbi.nlm.nih.gov/36459603"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2022.3224872","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2022.3224872","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100761497","display_name":"Tao He","orcid":"https://orcid.org/0000-0001-8676-7429"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Tao He","raw_affiliation_strings":["Department of Data Science and AI, Faculty of Information Technology, Monash University, Clayton, VIC, Australia"],"raw_orcid":"https://orcid.org/0000-0001-8676-7429","affiliations":[{"raw_affiliation_string":"Department of Data Science and AI, Faculty of Information Technology, Monash University, Clayton, VIC, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066645546","display_name":"Lianli Gao","orcid":"https://orcid.org/0000-0002-2522-6394"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lianli Gao","raw_affiliation_strings":["Center for Future Media, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-2522-6394","affiliations":[{"raw_affiliation_string":"Center for Future Media, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036987388","display_name":"Jingkuan Song","orcid":"https://orcid.org/0000-0002-2549-8322"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingkuan Song","raw_affiliation_strings":["Center for Future Media, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-2549-8322","affiliations":[{"raw_affiliation_string":"Center for Future Media, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017943466","display_name":"Yuan-Fang Li","orcid":"https://orcid.org/0000-0003-4651-2821"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yuan-Fang Li","raw_affiliation_strings":["Department of Data Science and AI, Faculty of Information Technology, Monash University, Clayton, VIC, Australia"],"raw_orcid":"https://orcid.org/0000-0003-4651-2821","affiliations":[{"raw_affiliation_string":"Department of Data Science and AI, Faculty of Information Technology, Monash University, Clayton, VIC, Australia","institution_ids":["https://openalex.org/I56590836"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.664,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.85349955,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"32","issue":null,"first_page":"43","last_page":"56"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","score":0.996399998664856,"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"}},{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.991100013256073,"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/computer-science","display_name":"Computer science","score":0.6885489821434021},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5041321516036987},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.47987738251686096},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4486076831817627},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.36224448680877686},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3605791926383972},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3440936207771301}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6885489821434021},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5041321516036987},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.47987738251686096},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4486076831817627},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.36224448680877686},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3605791926383972},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3440936207771301},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2022.3224872","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2022.3224872","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:36459603","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36459603","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2521105531","display_name":null,"funder_award_id":"HR001121S0024","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":67,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1933349210","https://openalex.org/W2127265454","https://openalex.org/W2187089797","https://openalex.org/W2188365844","https://openalex.org/W2250539671","https://openalex.org/W2277195237","https://openalex.org/W2462523589","https://openalex.org/W2479423890","https://openalex.org/W2549139847","https://openalex.org/W2579549467","https://openalex.org/W2591644541","https://openalex.org/W2607855566","https://openalex.org/W2629538667","https://openalex.org/W2771035597","https://openalex.org/W2786947658","https://openalex.org/W2886970679","https://openalex.org/W2890531016","https://openalex.org/W2896659472","https://openalex.org/W2909383239","https://openalex.org/W2917792613","https://openalex.org/W2941109201","https://openalex.org/W2950096400","https://openalex.org/W2962779575","https://openalex.org/W2962785943","https://openalex.org/W2963101956","https://openalex.org/W2963150697","https://openalex.org/W2963518342","https://openalex.org/W2963536419","https://openalex.org/W2963938081","https://openalex.org/W2982147439","https://openalex.org/W2990129662","https://openalex.org/W2997072136","https://openalex.org/W3034538190","https://openalex.org/W3034638741","https://openalex.org/W3035017890","https://openalex.org/W3058790345","https://openalex.org/W3108230874","https://openalex.org/W3108864070","https://openalex.org/W3109754877","https://openalex.org/W3113148327","https://openalex.org/W3155644662","https://openalex.org/W3171381086","https://openalex.org/W3173271937","https://openalex.org/W3174865181","https://openalex.org/W3175616662","https://openalex.org/W3177350810","https://openalex.org/W3181556077","https://openalex.org/W3184370138","https://openalex.org/W3195860412","https://openalex.org/W3210856765","https://openalex.org/W4200498145","https://openalex.org/W4295246696","https://openalex.org/W4312873085","https://openalex.org/W4385245566","https://openalex.org/W6620707391","https://openalex.org/W6678984984","https://openalex.org/W6687045409","https://openalex.org/W6721769334","https://openalex.org/W6739901393","https://openalex.org/W6739930931","https://openalex.org/W6746313456","https://openalex.org/W6748508754","https://openalex.org/W6758420182","https://openalex.org/W6781405847","https://openalex.org/W6797417516","https://openalex.org/W6805018690"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W2495260952","https://openalex.org/W4366179611","https://openalex.org/W2996078371"],"abstract_inverted_index":{"How":[0],"to":[1,108,114,148],"avoid":[2],"biased":[3,39,73],"predictions":[4],"is":[5,69,201],"an":[6],"important":[7],"and":[8,26,129,145,164,177,187,203],"active":[9],"research":[10],"question":[11],"in":[12,35,60,195],"scene":[13],"graph":[14],"generation":[15],"(SGG).":[16],"Current":[17],"state-of-the-art":[18,215],"methods":[19],"employ":[20],"debiasing":[21],"techniques":[22],"such":[23],"as":[24],"resampling":[25],"causality":[27],"analysis.":[28],"However,":[29],"the":[30,36,48,53,61,116,124,130,143,150,158,171,193,196,207],"role":[31],"of":[32,63,86,154,209],"intrinsic":[33,126],"cues":[34],"features":[37,119,128],"causing":[38],"training":[40],"has":[41],"remained":[42],"under-explored.":[43],"In":[44],"this":[45,104],"paper,":[46],"for":[47,72],"first":[49],"time,":[50],"we":[51,106,166],"make":[52],"surprising":[54],"observation":[55],"that":[56,183],"object":[57,64,99,146],"identity":[58,127],"information,":[59],"form":[62],"label":[65,100],"embeddings":[66],"(e.g.":[67],"GLOVE),":[68],"principally":[70],"responsible":[71],"predictions.":[74],"We":[75,135],"empirically":[76],"observe":[77],"that,":[78],"even":[79,94],"without":[80],"any":[81],"visual":[82,118],"features,":[83],"a":[84,110],"number":[85],"recent":[87,210],"SGG":[88,211],"models":[89],"can":[90],"produce":[91],"comparable":[92],"or":[93],"better":[95],"results":[96],"solely":[97],"from":[98],"embeddings.":[101],"Motivated":[102],"by":[103],"insight,":[105],"propose":[107],"leverage":[109],"conditional":[111],"variational":[112],"auto-encoder":[113],"decouple":[115],"entangled":[117],"into":[120],"two":[121,138,159],"meaningful":[122],"components:":[123],"object's":[125],"extrinsic,":[131],"relation-dependent":[132],"state":[133],"feature.":[134],"further":[136],"develop":[137],"compositional":[139],"learning":[140],"strategies":[141],"on":[142,170],"relation":[144,197],"levels":[147],"mitigate":[149],"data":[151],"scarcity":[152],"issue":[153],"rare":[155],"relations.":[156],"On":[157],"benchmark":[160],"datasets":[161],"Visual":[162],"Genome":[163],"GQA,":[165],"conduct":[167],"extensive":[168],"experiments":[169],"three":[172],"scenarios,":[173],"i.e.,":[174],"conventional,":[175],"few-shot":[176],"zero-shot":[178],"SGG.":[179],"Results":[180],"consistently":[181],"demonstrate":[182],"our":[184],"proposed":[185],"Decomposition":[186],"Composition":[188],"(DeC)":[189],"method":[190],"effectively":[191],"alleviates":[192],"biases":[194],"prediction.":[198],"Moreover,":[199],"DeC":[200],"model-free,":[202],"it":[204],"significantly":[205],"improves":[206],"performance":[208],"models,":[212],"establishing":[213],"new":[214],"performance.":[216]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}