{"id":"https://openalex.org/W7129081853","doi":"https://doi.org/10.1109/tmm.2026.3664986","title":"Hierarchical Scene Graph Generation With Coarse-to-Fine Reasoning","display_name":"Hierarchical Scene Graph Generation With Coarse-to-Fine Reasoning","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7129081853","doi":"https://doi.org/10.1109/tmm.2026.3664986"},"language":null,"primary_location":{"id":"doi:10.1109/tmm.2026.3664986","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3664986","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"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/A5017299417","display_name":"Zefang Han","orcid":"https://orcid.org/0000-0002-4048-1297"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zefang Han","raw_affiliation_strings":["School of Artificial Intelligence, Xidian University, Xi’an, China"],"raw_orcid":"https://orcid.org/0009-0007-7773-3834","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009400940","display_name":"Xiukun Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiukun Liu","raw_affiliation_strings":["School of Artificial Intelligence, Xidian University, Xi’an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xuemei Xie","orcid":"https://orcid.org/0000-0001-7857-0845"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuemei Xie","raw_affiliation_strings":["School of Artificial Intelligence, Xidian University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0001-7857-0845","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033547411","display_name":"Jianxiu Yang","orcid":"https://orcid.org/0000-0002-4718-9360"},"institutions":[{"id":"https://openalex.org/I5422934","display_name":"Shanxi Datong University","ror":"https://ror.org/03s8xc553","country_code":"CN","type":"education","lineage":["https://openalex.org/I5422934"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianxiu Yang","raw_affiliation_strings":["Shanxi Datong University, Datong, China"],"raw_orcid":"https://orcid.org/0000-0002-4718-9360","affiliations":[{"raw_affiliation_string":"Shanxi Datong University, Datong, China","institution_ids":["https://openalex.org/I5422934"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126099725","display_name":"Guangming Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangming Shi","raw_affiliation_strings":["School of Artificial Intelligence, Xidian University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0003-2179-3292","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.15541849,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":null,"first_page":"5380","last_page":"5394"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9962000250816345,"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":0.9962000250816345,"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":0.0005000000237487257,"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":0.00039999998989515007,"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":0.8518999814987183},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.6019999980926514},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.519599974155426},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.43560001254081726},{"id":"https://openalex.org/keywords/hierarchical-database-model","display_name":"Hierarchical database model","score":0.41839998960494995},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.3643999993801117},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.3409000039100647},{"id":"https://openalex.org/keywords/spatial-relation","display_name":"Spatial relation","score":0.3375000059604645}],"concepts":[{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.8518999814987183},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8514000177383423},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6019999980926514},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5444999933242798},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.519599974155426},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.43560001254081726},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.41839998960494995},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3643999993801117},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.35199999809265137},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35190001130104065},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.3409000039100647},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.3375000059604645},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3271999955177307},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.32429999113082886},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.32359999418258667},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.3091000020503998},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.29089999198913574},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.28360000252723694},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2565000057220459}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2026.3664986","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3664986","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W2579549467","https://openalex.org/W2886970679","https://openalex.org/W2963518342","https://openalex.org/W2963536419","https://openalex.org/W2963938081","https://openalex.org/W3023511145","https://openalex.org/W3034538190","https://openalex.org/W3035268124","https://openalex.org/W3155644662","https://openalex.org/W3184370138","https://openalex.org/W3197809352","https://openalex.org/W3198299822","https://openalex.org/W3203447128","https://openalex.org/W3203581965","https://openalex.org/W4226094317","https://openalex.org/W4250643848","https://openalex.org/W4288062562","https://openalex.org/W4312936847","https://openalex.org/W4317796337","https://openalex.org/W4366352717","https://openalex.org/W4379108576","https://openalex.org/W4382450654","https://openalex.org/W4382998936","https://openalex.org/W4385154451","https://openalex.org/W4387092463","https://openalex.org/W4389891300","https://openalex.org/W4390872479","https://openalex.org/W4390872897","https://openalex.org/W4396827020","https://openalex.org/W4401567187","https://openalex.org/W4402727018","https://openalex.org/W4402727624","https://openalex.org/W4402727764","https://openalex.org/W4402727771","https://openalex.org/W4402727824","https://openalex.org/W4402754270","https://openalex.org/W4402952458","https://openalex.org/W4403725720","https://openalex.org/W4403998586","https://openalex.org/W4404792503","https://openalex.org/W4409262174","https://openalex.org/W4409263066","https://openalex.org/W4413473452","https://openalex.org/W4415795395","https://openalex.org/W7118185822","https://openalex.org/W7133202489","https://openalex.org/W7133204206"],"related_works":[],"abstract_inverted_index":{"Scene":[0],"graph":[1,13,79,103,147,233],"generation":[2,104],"denotes":[3],"the":[4,63,87,117,121,125,131,171,209],"process":[5],"of":[6,58,65,120,166],"parsing":[7],"a":[8,12,81,100,143],"visual":[9,127],"input":[10,23],"into":[11],"representation":[14],"for":[15],"downstream":[16,69,226],"reasoning":[17,70,107],"tasks.":[18,71,195],"Most":[19],"existing":[20],"research":[21],"models":[22],"scenes":[24],"as":[25],"flat":[26,42],"scene":[27,43,66,78,91,102,146,206,232],"graphs,":[28],"capturing":[29],"solely":[30],"on":[31,225],"horizontal":[32],"relationships":[33,48,60],"between":[34,49],"two":[35],"objects,":[36,50],"while":[37,215],"disregarding":[38],"vertical":[39],"dependencies.":[40],"Such":[41],"graphs":[44,67,92],"merely":[45],"describe":[46,124],"direct":[47],"and":[51,133,161,181],"cannot":[52],"represent":[53],"higher-level":[54],"semantics.":[55],"The":[56,223],"lack":[57],"hierarchical":[59,77,101,145,231],"also":[61,185,228],"limits":[62],"performance":[64],"in":[68,213],"In":[72],"this":[73,98],"work,":[74],"we":[75],"propose":[76],"generation,":[80],"new":[82],"problem":[83],"task":[84],"that":[85,149,200,230],"requires":[86],"model":[88],"to":[89,130,192,236],"generate":[90],"with":[93,105,138],"clear":[94],"hierarchy.":[95],"To":[96,140],"achieve":[97,177],"goal,":[99],"coarse-to-fine":[106],"framework":[108,173],"is":[109,156],"proposed.":[110],"It":[111],"contains":[112],"three":[113],"stages:":[114],"first,":[115],"summarize":[116],"main":[118,126],"caption":[119],"scene;":[122],"second,":[123],"elements":[128,137],"related":[129],"theme;":[132],"finally,":[134],"add":[135],"secondary":[136],"background.":[139],"facilitate":[141],"training,":[142],"high-quality":[144],"dataset":[148],"comprises":[150],"40":[151],"K":[152],"image-scene":[153],"description":[154],"pairs":[155],"constructed.":[157],"Utilize":[158],"rich":[159],"knowledge":[160],"powerful":[162],"multi-turn":[163],"conversation":[164],"capabilities":[165,191],"multi-modal":[167],"large":[168],"language":[169],"models,":[170],"proposed":[172],"can":[174],"not":[175],"only":[176],"better":[178],"semantic":[179],"understanding":[180],"relational":[182,189],"modeling,":[183],"but":[184],"seamlessly":[186],"integrating":[187],"its":[188],"modeling":[190],"enhance":[193],"visual-language":[194,237],"Extensive":[196],"experimental":[197],"results":[198,224],"demonstrate":[199],"our":[201],"method":[202],"constructs":[203],"an":[204],"effective":[205],"representation,":[207],"outperforming":[208],"state-of-the-art":[210],"by":[211],"3.35%":[212],"recall":[214],"generating":[216],"significantly":[217,234],"fewer":[218],"average":[219],"triplets":[220],"8.7vs.":[221],"9.2.":[222],"tasks":[227],"indicate":[229],"contributes":[235],"interactive":[238],"reasoning.":[239]},"counts_by_year":[],"updated_date":"2026-07-04T06:09:54.619538","created_date":"2026-02-17T00:00:00"}