{"id":"https://openalex.org/W4415707786","doi":"https://doi.org/10.1109/icme59968.2025.11209357","title":"Universal Scene Graph Generation via Semantic Feature Alignment","display_name":"Universal Scene Graph Generation via Semantic Feature Alignment","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415707786","doi":"https://doi.org/10.1109/icme59968.2025.11209357"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209357","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209357","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5058416717","display_name":"Xiangyu Zhang","orcid":"https://orcid.org/0000-0003-1297-6951"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyu Zhang","raw_affiliation_strings":["Harbin Institute of Technology,College of Computer Science and Technology,Shenzhen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,College of Computer Science and Technology,Shenzhen","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Guoxi Qiu","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoxi Qiu","raw_affiliation_strings":["Harbin Institute of Technology,College of Computer Science and Technology,Shenzhen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,College of Computer Science and Technology,Shenzhen","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100625519","display_name":"Yong Xu","orcid":"https://orcid.org/0000-0002-2525-7086"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Xu","raw_affiliation_strings":["Harbin Institute of Technology,College of Computer Science and Technology,Shenzhen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,College of Computer Science and Technology,Shenzhen","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100449050","display_name":"Jinghua Wang","orcid":"https://orcid.org/0009-0007-3879-874X"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinghua Wang","raw_affiliation_strings":["Harbin Institute of Technology,College of Computer Science and Technology,Shenzhen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,College of Computer Science and Technology,Shenzhen","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9923999905586243,"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":0.9923999905586243,"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":0.0017999999690800905,"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":0.0010999999940395355,"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/relation","display_name":"Relation (database)","score":0.7195000052452087},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.6189000010490417},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5454000234603882},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5450000166893005},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5388000011444092},{"id":"https://openalex.org/keywords/spatial-relation","display_name":"Spatial relation","score":0.5094000101089478},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.48350000381469727},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.45320001244544983}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7440000176429749},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7321000099182129},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.7195000052452087},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.6189000010490417},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5454000234603882},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5450000166893005},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5388000011444092},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.5094000101089478},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.48350000381469727},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.45320001244544983},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.44909998774528503},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.42969998717308044},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.40619999170303345},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.38760000467300415},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.36890000104904175},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3434999883174896},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3427000045776367},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3301999866962433},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3231000006198883},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2824999988079071},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.271699994802475}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209357","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209357","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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":27,"referenced_works":["https://openalex.org/W2250378130","https://openalex.org/W2579549467","https://openalex.org/W2963184176","https://openalex.org/W2963514444","https://openalex.org/W2963536419","https://openalex.org/W2963938081","https://openalex.org/W2992478697","https://openalex.org/W3034538190","https://openalex.org/W3035017890","https://openalex.org/W3119206490","https://openalex.org/W3138516171","https://openalex.org/W3171162797","https://openalex.org/W3171270868","https://openalex.org/W3181556077","https://openalex.org/W3195129957","https://openalex.org/W3198299822","https://openalex.org/W4304092470","https://openalex.org/W4312744661","https://openalex.org/W4312747482","https://openalex.org/W4312873085","https://openalex.org/W4312956471","https://openalex.org/W4386066484","https://openalex.org/W4386071767","https://openalex.org/W4402727824","https://openalex.org/W4403277953","https://openalex.org/W4404612908","https://openalex.org/W4404792503"],"related_works":[],"abstract_inverted_index":{"Scene":[0],"Graph":[1],"Generation":[2],"(SGG)":[3],"offers":[4],"a":[5,48,92],"valuable":[6],"structured":[7],"representation":[8],"for":[9],"various":[10],"computer":[11],"vision":[12],"applications.":[13],"With":[14],"advancements":[15],"in":[16,127],"visual":[17,103],"and":[18,33,62,78,104,111,146,155,176],"textual":[19,105],"alignment,":[20],"researchers":[21],"are":[22],"exploring":[23],"both":[24,58,144],"open-vocabulary":[25,34],"object":[26,31,60,145,154],"detection":[27,36],"to":[28,37,132],"address":[29,43,82],"unseen":[30,39,59,63,69,83],"categories":[32,61,142],"relation":[35,40,64,88,137,156],"manage":[38],"categories.":[41,65],"To":[42,80,117],"real-world":[44],"applications,":[45],"we":[46,85,130,158],"propose":[47,131],"new":[49],"universal":[50,161],"scene":[51,162],"graph":[52,163],"generation":[53],"framework":[54],"(U-SGG)":[55],"that":[56],"handles":[57],"Our":[66],"method":[67],"detects":[68],"objects":[70],"by":[71],"leveraging":[72],"the":[73,87,102,109,115,119,141,169,174,179],"aligned":[74],"representations":[75],"of":[76,114,121,124,143,178],"images":[77],"text.":[79],"effectively":[81],"relations,":[84],"build":[86],"prediction":[89],"head":[90],"using":[91],"Visual":[93,170],"Language":[94],"Transformer,":[95],"which":[96],"takes":[97],"into":[98,136],"consideration":[99],"not":[100],"only":[101],"features,":[106],"but":[107],"also":[108],"attribute":[110],"spatial":[112],"features":[113],"objects.":[116],"alleviate":[118],"problem":[120],"insufficient":[122],"quantity":[123],"training":[125],"data":[126,151],"SGG":[128],"tasks,":[129],"parse":[133],"image":[134,149],"captions":[135],"triples,":[138],"thereby":[139],"enriching":[140],"relation.":[147],"Using":[148],"caption":[150],"with":[152],"diverse":[153],"categories,":[157],"successfully":[159],"achieve":[160],"generation.":[164],"Comprehensive":[165],"experimental":[166],"results":[167],"on":[168],"Genome":[171],"benchmark":[172],"demonstrate":[173],"effectiveness":[175],"superiority":[177],"proposed":[180],"method.":[181]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-30T00:00:00"}