{"id":"https://openalex.org/W4413146378","doi":"https://doi.org/10.1109/cvpr52734.2025.01321","title":"Universal Scene Graph Generation","display_name":"Universal Scene Graph Generation","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413146378","doi":"https://doi.org/10.1109/cvpr52734.2025.01321"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.01321","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01321","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5089517967","display_name":"Shengqiong Wu","orcid":"https://orcid.org/0000-0001-6192-1194"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shengqiong Wu","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hao Fei","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hao Fei","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089404640","display_name":"Tat\u2010Seng Chua","orcid":"https://orcid.org/0000-0001-6097-7807"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tat-Seng Chua","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"14158","last_page":"14168"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9918000102043152,"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":0.9918000102043152,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9865000247955322,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9746999740600586,"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/computer-science","display_name":"Computer science","score":0.6439529061317444},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3202044665813446}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6439529061317444},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3202044665813446}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.01321","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01321","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Scene":[0],"graph":[1],"(SG)":[2],"representations":[3,65],"can":[4],"neatly":[5],"and":[6,36,98,119,166,189,197],"efficiently":[7],"describe":[8],"scene":[9,51,69,154,184],"semantics,":[10],"which":[11,109,134],"has":[12],"driven":[13],"sustained":[14],"intensive":[15],"research":[16,45],"in":[17,66,133],"SG":[18,44,64,77],"generation.":[19],"In":[20],"the":[21,54,58,124,142],"real":[22],"world,":[23],"multiple":[24],"modalities":[25],"often":[26],"coexist,":[27],"with":[28,126,168],"different":[29,62],"types,":[30],"such":[31],"as":[32],"images,":[33],"text,":[34],"video,":[35],"3D":[37],"data,":[38],"expressing":[39,183],"distinct":[40],"characteristics.":[41],"Unfortunately,":[42],"current":[43],"is":[46,202],"largely":[47],"confined":[48],"to":[49,140,158],"single-modality":[50],"modeling,":[52],"preventing":[53],"full":[55],"utilization":[56],"of":[57,61,83,93,115],"complementary":[59],"strengths":[60],"modality":[63,94,143],"depicting":[67],"holistic":[68],"semantics.":[70],"To":[71],"this":[72],"end,":[73],"we":[74,102,135,150,174],"introduce":[75],"Universal":[76],"(USG),":[78],"a":[79,104,152,179],"novel":[80],"representation":[81],"capable":[82],"fully":[84],"characterizing":[85],"comprehensive":[86],"semantic":[87],"scenes":[88],"from":[89],"any":[90],"given":[91],"combination":[92],"inputs,":[95],"encompassing":[96],"modality-invariant":[97],"modality-specific":[99],"scenes.":[100],"Further,":[101,149],"tailor":[103],"niche-targeting":[105],"USG":[106,131,177],"parser,":[107],"USG-Par,":[108],"effectively":[110],"addresses":[111],"two":[112],"key":[113],"bottlenecks":[114],"cross-modal":[116,146],"object":[117,138,147],"alignment":[118],"out-of-domain":[120],"challenges.":[121],"We":[122],"design":[123],"USG-Par":[125,193],"modular":[127],"architecture":[128],"for":[129,145,182],"end-to-end":[130],"generation,":[132],"devise":[136],"an":[137],"associator":[139],"relieve":[141],"gap":[144],"alignment.":[148],"propose":[151],"text-centric":[153],"contrasting":[155],"learning":[156],"mechanism":[157],"mitigate":[159],"domain":[160],"imbalances":[161],"by":[162],"aligning":[163],"multimodal":[164],"objects":[165],"relations":[167],"textual":[169],"SGs.":[170],"Through":[171],"extensive":[172],"experiments,":[173],"demonstrate":[175],"that":[176,191],"offers":[178],"stronger":[180],"capability":[181],"semantics":[185],"than":[186],"standalone":[187],"SGs,":[188],"also":[190],"our":[192],"achieves":[194],"higher":[195],"efficacy":[196],"performance.":[198],"The":[199],"project":[200],"page":[201],"https://sqwu.top/USG/.":[203]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":5}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}