{"id":"https://openalex.org/W4416513609","doi":"https://doi.org/10.1109/tpami.2025.3635152","title":"Human-Inspired Scene Understanding: A Grounded Cognition Method for Unbiased Scene Graph Generation","display_name":"Human-Inspired Scene Understanding: A Grounded Cognition Method for Unbiased Scene Graph Generation","publication_year":2025,"publication_date":"2025-11-21","ids":{"openalex":"https://openalex.org/W4416513609","doi":"https://doi.org/10.1109/tpami.2025.3635152","pmid":"https://pubmed.ncbi.nlm.nih.gov/41269850"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3635152","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3635152","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","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/A5091839207","display_name":"Ruonan Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ruonan Zhang","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114831821","display_name":"Yiqing Hao","orcid":"https://orcid.org/0000-0002-8102-4498"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]},{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiqing Hao","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China","School of Computer Science and TechnologyBeijing Jiaotong University"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"School of Computer Science and TechnologyBeijing Jiaotong University","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100401194","display_name":"Feng Zhang","orcid":"https://orcid.org/0000-0001-5747-5275"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Zhang","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054342134","display_name":"Gaoyun An","orcid":"https://orcid.org/0000-0002-2843-843X"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gaoyun An","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103052909","display_name":"Binyang Song","orcid":"https://orcid.org/0000-0002-0322-796X"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Binyang Song","raw_affiliation_strings":["School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001469325","display_name":"Dapeng Wu","orcid":"https://orcid.org/0000-0003-1755-0183"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Dapeng Oliver Wu","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Kowloon, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5091839207"],"corresponding_institution_ids":["https://openalex.org/I21193070"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.36745586,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"48","issue":"3","first_page":"3286","last_page":"3303"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9884999990463257,"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":0.9884999990463257,"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":0.005200000014156103,"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":0.0008999999845400453,"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/situated","display_name":"Situated","score":0.6432999968528748},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.517300009727478},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.48969998955726624},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.48590001463890076},{"id":"https://openalex.org/keywords/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.4494999945163727},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4320000112056732},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4171999990940094},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.3603000044822693},{"id":"https://openalex.org/keywords/predicate","display_name":"Predicate (mathematical logic)","score":0.3513000011444092}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6972000002861023},{"id":"https://openalex.org/C132829578","wikidata":"https://www.wikidata.org/wiki/Q581151","display_name":"Situated","level":2,"score":0.6432999968528748},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5989999771118164},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.517300009727478},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.48969998955726624},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.48590001463890076},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.4494999945163727},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4474000036716461},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4320000112056732},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4171999990940094},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3691999912261963},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3603000044822693},{"id":"https://openalex.org/C140146324","wikidata":"https://www.wikidata.org/wiki/Q1144319","display_name":"Predicate (mathematical logic)","level":2,"score":0.3513000011444092},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.34700000286102295},{"id":"https://openalex.org/C161407221","wikidata":"https://www.wikidata.org/wiki/Q4382939","display_name":"Cognitive model","level":3,"score":0.32280001044273376},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.31459999084472656},{"id":"https://openalex.org/C197654239","wikidata":"https://www.wikidata.org/wiki/Q7430757","display_name":"Scene statistics","level":3,"score":0.30979999899864197},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.3095000088214874},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.30090001225471497},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.28999999165534973},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C80944243","wikidata":"https://www.wikidata.org/wiki/Q7532125","display_name":"Situated cognition","level":3,"score":0.27230000495910645},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.26649999618530273},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.257099986076355},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25380000472068787},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2025.3635152","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3635152","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:41269850","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41269850","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 pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":69,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1595732857","https://openalex.org/W1892016050","https://openalex.org/W1976852883","https://openalex.org/W2019455361","https://openalex.org/W2069581519","https://openalex.org/W2077069816","https://openalex.org/W2086731674","https://openalex.org/W2132003317","https://openalex.org/W2148764920","https://openalex.org/W2150375089","https://openalex.org/W2250539671","https://openalex.org/W2277195237","https://openalex.org/W2591644541","https://openalex.org/W2963101956","https://openalex.org/W2963184176","https://openalex.org/W2963518342","https://openalex.org/W2963536419","https://openalex.org/W2963691377","https://openalex.org/W2963938081","https://openalex.org/W2969679616","https://openalex.org/W2992478697","https://openalex.org/W3035017890","https://openalex.org/W3103482818","https://openalex.org/W3106759358","https://openalex.org/W3181556077","https://openalex.org/W4207021923","https://openalex.org/W4207041113","https://openalex.org/W4212844288","https://openalex.org/W4221150632","https://openalex.org/W4225868495","https://openalex.org/W4230449744","https://openalex.org/W4235743066","https://openalex.org/W4285287023","https://openalex.org/W4288062562","https://openalex.org/W4288083516","https://openalex.org/W4310466354","https://openalex.org/W4312297403","https://openalex.org/W4312578903","https://openalex.org/W4313037583","https://openalex.org/W4319783489","https://openalex.org/W4379382409","https://openalex.org/W4380303580","https://openalex.org/W4382458076","https://openalex.org/W4386075638","https://openalex.org/W4387968684","https://openalex.org/W4387969215","https://openalex.org/W4387969367","https://openalex.org/W4388624399","https://openalex.org/W4390873633","https://openalex.org/W4392930798","https://openalex.org/W4393158871","https://openalex.org/W4394698791","https://openalex.org/W4394841770","https://openalex.org/W4396982232","https://openalex.org/W4402715983","https://openalex.org/W4402727472","https://openalex.org/W4402727771","https://openalex.org/W4402727824","https://openalex.org/W4402737612","https://openalex.org/W4402754270","https://openalex.org/W4402969097","https://openalex.org/W4403791539","https://openalex.org/W4403792144","https://openalex.org/W4403842483","https://openalex.org/W4404544782","https://openalex.org/W4406982839","https://openalex.org/W4408100020","https://openalex.org/W4415795196"],"related_works":[],"abstract_inverted_index":{"Scene":[0],"Graph":[1],"Generation":[2],"(SGG)":[3],"is":[4,68,98,119,141,201],"a":[5,88,136,153,195,237],"critical":[6],"cross-modal":[7],"task":[8],"for":[9,50,65,93,143,185],"scene":[10,95],"understanding,":[11],"which":[12,173,231],"aims":[13],"to":[14,59,79,121,165,177,183,203],"detect":[15],"visual":[16,125],"relations":[17],"in":[18],"an":[19,113,132],"image.":[20],"Most":[21],"SGG":[22,45],"methods":[23,46,234],"are":[24,57,109,162],"significantly":[25],"affected":[26],"by":[27,127,147],"highly":[28],"skewed":[29],"long-tailed":[30,53],"bias,":[31],"and":[32,106,211,221,235],"prefer":[33],"predicates":[34],"with":[35,208,213],"sufficient":[36],"samples":[37],"regardless":[38],"of":[39,76,170,188,228],"the":[40,51,69,74,85,102,123,129,160,167,175,180,186,189,205,209,226],"semantic":[41,155],"accuracy.":[42],"Current":[43],"unbiased":[44,94],"focus":[47],"on":[48,131,179,217],"compensating":[49],"imbalanced":[52],"distribution,":[54],"but":[55],"they":[56],"fragile":[58],"dataset":[60],"changes.":[61],"The":[62],"fundamental":[63],"cause":[64],"this":[66],"problem":[67],"limited":[70,168],"generalization":[71],"ability,":[72],"thus":[73],"diversity":[75],"classes":[77,151],"needs":[78],"be":[80],"modeled":[81],"explicitly.":[82],"By":[83],"imitating":[84],"human":[86],"cognition,":[87],"Grounded":[89],"Cognition":[90],"Method":[91],"(GCM)":[92],"graph":[96],"generation":[97],"proposed":[99,120,142,202],"here,":[100],"where":[101],"simulation,":[103],"bodily":[104,158],"states,":[105,159],"situated":[107,193],"action":[108],"modeled.":[110],"For":[111,157,192],"simulations,":[112],"Out":[114],"Domain":[115],"Knowledge":[116],"Injection":[117],"module":[118,200],"expand":[122],"model's":[124],"perception":[126,145],"reducing":[128],"reliance":[130],"isolated":[133],"class.":[134],"Meanwhile,":[135],"Semantic":[137],"Group":[138],"Aware":[139],"Synthesizer":[140],"linguistic":[144],"modeling":[146],"categorizing":[148],"specific":[149],"predicate":[150],"into":[152],"high-level":[154],"group.":[156],"modalities":[161],"erased":[163],"separately":[164],"imitate":[166],"state":[169],"physical":[171],"senses,":[172],"forces":[174],"model":[176,204],"rely":[178],"remaining":[181],"modality":[182],"compensate":[184],"understanding":[187],"whole":[190],"scene.":[191],"actions,":[194],"Shapley":[196],"Enhanced":[197],"Multimodal":[198],"Counterfactual":[199],"dynamic":[206],"interaction":[207],"environment":[210],"cope":[212],"diverse":[214],"contexts.":[215],"Experiments":[216],"Visual":[218],"Genome,":[219],"GQA,":[220],"Open":[222],"Images":[223],"V6":[224],"demonstrate":[225],"effectiveness":[227],"our":[229],"GCM,":[230],"outperforms":[232],"state-of-the-art":[233],"achieves":[236],"better":[238],"trade-off.":[239]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-11-23T00:00:00"}