{"id":"https://openalex.org/W7164808665","doi":"https://doi.org/10.1145/3805622.3810741","title":"KG-CPEN: Knowledge-Guided Compositional Prototype Evolution for Unbiased Scene Graph Generation","display_name":"KG-CPEN: Knowledge-Guided Compositional Prototype Evolution for Unbiased Scene Graph Generation","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164808665","doi":"https://doi.org/10.1145/3805622.3810741"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810741","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810741","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810741","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045395286","display_name":"Yujun Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I21945476","display_name":"Shanghai Normal University","ror":"https://ror.org/01cxqmw89","country_code":"CN","type":"education","lineage":["https://openalex.org/I21945476"]},{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yujun Hu","raw_affiliation_strings":["School of Computer Science and Technology, East China Normal University, Shanghai, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0003-5449-1087","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, East China Normal University, Shanghai, Shanghai, China","institution_ids":["https://openalex.org/I66867065","https://openalex.org/I21945476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138648800","display_name":"Changbo Wang","orcid":"https://orcid.org/0009-0006-8604-8495"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changbo Wang","raw_affiliation_strings":["School of Data Science and Engineering, East China Normal University, Shanghai, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0006-8604-8495","affiliations":[{"raw_affiliation_string":"School of Data Science and Engineering, East China Normal University, Shanghai, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001077607","display_name":"Gaoqi He","orcid":"https://orcid.org/0000-0001-8365-0970"},"institutions":[{"id":"https://openalex.org/I21945476","display_name":"Shanghai Normal University","ror":"https://ror.org/01cxqmw89","country_code":"CN","type":"education","lineage":["https://openalex.org/I21945476"]},{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gaoqi He","raw_affiliation_strings":["School of Computer Science and Technology, East China Normal University, Shanghai, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-8365-0970","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, East China Normal University, Shanghai, Shanghai, China","institution_ids":["https://openalex.org/I66867065","https://openalex.org/I21945476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.93396637,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"635","last_page":"644"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9682999849319458,"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":0.9682999849319458,"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":0.009700000286102295,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.005100000184029341,"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/discriminative-model","display_name":"Discriminative model","score":0.6858000159263611},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.5565999746322632},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5401999950408936},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5209000110626221},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.462799996137619},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4244000017642975},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.4205999970436096},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.397599995136261},{"id":"https://openalex.org/keywords/semantic-matching","display_name":"Semantic matching","score":0.39649999141693115}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.781000018119812},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6858000159263611},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6166999936103821},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.5565999746322632},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5401999950408936},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5209000110626221},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.462799996137619},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4244000017642975},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.4205999970436096},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.397599995136261},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.39649999141693115},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3652999997138977},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.36489999294281006},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36469998955726624},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.35679998993873596},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.35589998960494995},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3434000015258789},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.3434000015258789},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33079999685287476},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3082999885082245},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3068999946117401},{"id":"https://openalex.org/C115908005","wikidata":"https://www.wikidata.org/wiki/Q2668364","display_name":"Combinatorial explosion","level":2,"score":0.29280000925064087},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.2705000042915344},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C146380142","wikidata":"https://www.wikidata.org/wiki/Q1137726","display_name":"Directed graph","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C74197172","wikidata":"https://www.wikidata.org/wiki/Q1195339","display_name":"Directed acyclic graph","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810741","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810741","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810741","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810741","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7396256923675537}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1594039573","https://openalex.org/W2277195237","https://openalex.org/W2479423890","https://openalex.org/W2579549467","https://openalex.org/W2886970679","https://openalex.org/W2947385066","https://openalex.org/W2948519073","https://openalex.org/W2950096400","https://openalex.org/W2955882737","https://openalex.org/W2962779575","https://openalex.org/W2963101956","https://openalex.org/W2963514444","https://openalex.org/W2963518342","https://openalex.org/W2963536419","https://openalex.org/W2963691377","https://openalex.org/W2963938081","https://openalex.org/W2990129662","https://openalex.org/W2992478697","https://openalex.org/W3034275286","https://openalex.org/W3034538190","https://openalex.org/W3035017890","https://openalex.org/W3081642947","https://openalex.org/W3108864070","https://openalex.org/W3155644662","https://openalex.org/W3167308647","https://openalex.org/W3173181410","https://openalex.org/W3174865181","https://openalex.org/W3181556077","https://openalex.org/W3182902595","https://openalex.org/W3198299822","https://openalex.org/W3215287157","https://openalex.org/W4214685694","https://openalex.org/W4223425316","https://openalex.org/W4225868495","https://openalex.org/W4285287023","https://openalex.org/W4288062562","https://openalex.org/W4288083516","https://openalex.org/W4293518226","https://openalex.org/W4293795093","https://openalex.org/W4312429751","https://openalex.org/W4312555984","https://openalex.org/W4312744661","https://openalex.org/W4313037583","https://openalex.org/W4319783489","https://openalex.org/W4366352717","https://openalex.org/W4382466430","https://openalex.org/W4386072171","https://openalex.org/W4386075638","https://openalex.org/W4386090265","https://openalex.org/W4408100020"],"related_works":[],"abstract_inverted_index":{"Scene":[0],"Graph":[1],"Generation":[2],"(SGG)":[3],"serves":[4],"as":[5,90],"a":[6,81,91,142,170],"pivotal":[7],"bridge":[8],"between":[9,136],"Computer":[10],"Vision":[11],"and":[12,39,109,138,150,161],"Natural":[13],"Language":[14],"Processing,":[15],"aiming":[16],"to":[17,94],"parse":[18],"unstructured":[19],"imagery":[20],"into":[21,51],"structured":[22],"semantic":[23,92],"summaries.":[24],"When":[25],"dealing":[26],"with":[27],"long-tailed":[28,108],"distributions,":[29],"existing":[30],"discriminative":[31],"methods":[32],"often":[33],"suffer":[34],"from":[35],"severe":[36],"data-dependency":[37],"bias":[38],"ignore":[40],"the":[41,60,69,100,134],"compositional":[42],"semantics":[43],"of":[44,71],"predicates,":[45],"resulting":[46],"in":[47,99,107],"predictions":[48],"inevitably":[49],"collapsing":[50],"high-frequency":[52],"head":[53,119,152],"classes.":[54],"To":[55,67],"address":[56],"this,":[57],"we":[58,79,121],"propose":[59],"Knowledge-Guided":[61,82],"Compositional":[62],"Prototype":[63,83],"Evolution":[64,84],"Network":[65],"(KG-CPEN).":[66],"tackle":[68],"paucity":[70],"feature":[72,105],"space":[73],"caused":[74],"by":[75,132],"tail":[76,97],"sample":[77],"scarcity,":[78],"introduce":[80],"mechanism,":[85],"which":[86],"utilizes":[87],"external":[88],"knowledge":[89],"engine":[93],"synthesize":[95],"missing":[96],"prototypes":[98],"visual":[101,137],"manifold,":[102],"effectively":[103],"replenishing":[104],"representations":[106],"zero-shot":[110],"scenarios.":[111],"Furthermore,":[112],"since":[113],"traditional":[114],"local":[115],"greedy":[116],"matching":[117,131],"exacerbates":[118],"bias,":[120],"design":[122],"an":[123],"Optimal":[124],"Transport":[125],"Alignment":[126],"module.":[127],"This":[128],"achieves":[129],"unbiased":[130,175],"minimizing":[133],"distance":[135],"prototype":[139],"distributions":[140],"on":[141,157],"global":[143],"scale,":[144],"thereby":[145],"reducing":[146],"decision":[147],"layer":[148],"difficulty":[149],"eliminating":[151],"class":[153],"dominance.":[154],"Extensive":[155],"experiments":[156],"Visual":[158],"Genome,":[159],"GQA,":[160],"Open":[162],"Images":[163],"V6":[164],"consistently":[165],"demonstrate":[166],"that":[167],"KG-CPEN":[168],"establishes":[169],"new":[171],"State-Of-The-Art":[172],"(SOTA)":[173],"for":[174],"scene":[176],"graph":[177],"generation.":[178]},"counts_by_year":[],"updated_date":"2026-06-16T07:37:23.134862","created_date":"2026-06-16T00:00:00"}