{"id":"https://openalex.org/W4415708481","doi":"https://doi.org/10.1109/icme59968.2025.11209525","title":"Open-Scene Understanding-oriented 3D Scene Graph Generation","display_name":"Open-Scene Understanding-oriented 3D Scene Graph Generation","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708481","doi":"https://doi.org/10.1109/icme59968.2025.11209525"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209525","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209525","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":"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/A5059262948","display_name":"Yao Hao","orcid":"https://orcid.org/0000-0002-5277-7271"},"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":true,"raw_author_name":"Yuansu Hao","raw_affiliation_strings":["Harbin Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100420016","display_name":"F. Richard Yu","orcid":"https://orcid.org/0000-0003-1006-7594"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Yu","raw_affiliation_strings":["Zhejiang Lab"],"affiliations":[{"raw_affiliation_string":"Zhejiang Lab","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065488679","display_name":"Yanhao Wang","orcid":"https://orcid.org/0000-0002-7661-3917"},"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":"Yanhao Wang","raw_affiliation_strings":["East China Normal University"],"affiliations":[{"raw_affiliation_string":"East China Normal University","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100721630","display_name":"Yuehua Li","orcid":"https://orcid.org/0000-0003-1000-9247"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuehua Li","raw_affiliation_strings":["Zhejiang Lab"],"affiliations":[{"raw_affiliation_string":"Zhejiang Lab","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001074845","display_name":"Qingxu Deng","orcid":"https://orcid.org/0000-0002-5185-6306"},"institutions":[{"id":"https://openalex.org/I4210137766","display_name":"Institute for Advanced Study","ror":"https://ror.org/03xg85719","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210137766"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Quan Deng","raw_affiliation_strings":["Hangzhou Institute for Advanced Study, UCAS"],"affiliations":[{"raw_affiliation_string":"Hangzhou Institute for Advanced Study, UCAS","institution_ids":["https://openalex.org/I4210137766"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102024383","display_name":"Yu Yuan","orcid":"https://orcid.org/0000-0002-3978-483X"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Yu","raw_affiliation_strings":["Zhejiang Lab"],"affiliations":[{"raw_affiliation_string":"Zhejiang Lab","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083889298","display_name":"Chen Huang","orcid":"https://orcid.org/0000-0002-4978-493X"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Huang","raw_affiliation_strings":["Zhejiang Lab"],"affiliations":[{"raw_affiliation_string":"Zhejiang Lab","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103101143","display_name":"Nan Che","orcid":"https://orcid.org/0000-0001-5771-1856"},"institutions":[{"id":"https://openalex.org/I100188998","display_name":"Harbin University of Science and Technology","ror":"https://ror.org/04e6y1282","country_code":"CN","type":"education","lineage":["https://openalex.org/I100188998"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nan Che","raw_affiliation_strings":["Harbin University of Science and Technology"],"affiliations":[{"raw_affiliation_string":"Harbin University of Science and Technology","institution_ids":["https://openalex.org/I100188998"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5059262948"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33853956,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.9596999883651733,"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":0.9596999883651733,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.005400000140070915,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.004800000227987766,"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/scene-graph","display_name":"Scene graph","score":0.6728000044822693},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.532800018787384},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.5281999707221985},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.43799999356269836},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.43790000677108765},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.3393000066280365},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.328900009393692},{"id":"https://openalex.org/keywords/3d-reconstruction","display_name":"3D reconstruction","score":0.3165999948978424}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7491999864578247},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.6728000044822693},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6593000292778015},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5863999724388123},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.532800018787384},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.5281999707221985},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.43799999356269836},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.43790000677108765},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3393000066280365},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.328900009393692},{"id":"https://openalex.org/C109950114","wikidata":"https://www.wikidata.org/wiki/Q4464732","display_name":"3D reconstruction","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3138999938964844},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C3019007443","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3d model","level":2,"score":0.3012999892234802},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2831999957561493},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.28060001134872437},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C5134670","wikidata":"https://www.wikidata.org/wiki/Q1626444","display_name":"Cut","level":4,"score":0.2728999853134155},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.2567000091075897}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209525","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209525","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":17,"referenced_works":["https://openalex.org/W2479423890","https://openalex.org/W2579549467","https://openalex.org/W2740924709","https://openalex.org/W2990129662","https://openalex.org/W3035154952","https://openalex.org/W3173271937","https://openalex.org/W3183042936","https://openalex.org/W4312818263","https://openalex.org/W4383108719","https://openalex.org/W4386071707","https://openalex.org/W4386076183","https://openalex.org/W4386083046","https://openalex.org/W4390189960","https://openalex.org/W4401414715","https://openalex.org/W4401415428","https://openalex.org/W4402704531","https://openalex.org/W4402726938"],"related_works":[],"abstract_inverted_index":{"Understanding":[0],"complex":[1],"3D":[2,20,31,38,75,108,126,158],"environments":[3],"is":[4],"essential":[5],"for":[6,37,55,147,181],"many":[7],"computer":[8],"vision":[9],"and":[10,46,52,98,124,140,162,168,189],"robotic":[11],"applications,":[12],"especially":[13],"in":[14,27,61,129],"highly":[15],"dynamic":[16],"open-scene":[17,63,185],"scenarios.":[18],"The":[19,87],"scene":[21,39,127],"graph":[22,40],"plays":[23],"an":[24],"important":[25],"role":[26],"the":[28,62,166,171,179,182],"comprehension":[29],"of":[30,170,184],"environments.":[32],"However,":[33],"most":[34],"existing":[35],"methods":[36],"generation":[41],"depend":[42],"on":[43,155],"pre-specified":[44],"object":[45,109,142],"relationship":[47],"classes":[48],"(i.e.,":[49],"closed":[50],"vocabulary)":[51],"labeled":[53,84],"data":[54,190],"training,":[56],"which":[57],"restricts":[58],"their":[59],"effectiveness":[60,167],"setting.":[64],"To":[65],"address":[66],"this":[67],"issue,":[68],"we":[69,151],"propose":[70],"a":[71,114,130],"novel":[72],"Open-Scene":[73],"Understanding-oriented":[74],"Scene":[76],"Graph":[77],"(OSU-3DSG)":[78],"framework":[79,89],"that":[80],"can":[81],"operate":[82],"without":[83],"training":[85],"data.":[86],"OSU-3DSG":[88,172],"effectively":[90],"extracts":[91],"visual":[92],"features":[93],"from":[94],"RGB-D":[95],"image":[96],"sequences":[97],"fuses":[99],"them":[100],"with":[101],"camera":[102],"pose":[103],"estimates":[104],"to":[105,164,177],"create":[106],"accurate":[107],"maps.":[110],"Then,":[111],"by":[112],"leveraging":[113],"pre-trained":[115],"Vision":[116],"Language":[117],"Model":[118],"(VLM),":[119],"it":[120,135,145],"generates":[121],"relational":[122],"triplets":[123],"constructs":[125],"graphs":[128],"zero-shot":[131],"manner.":[132],"In":[133],"particular,":[134],"excels":[136],"at":[137,193],"adaptively":[138],"recognizing":[139],"interpreting":[141],"relationships,":[143],"making":[144],"suitable":[146],"open-world":[148,157],"applications.":[149],"Finally,":[150],"perform":[152],"extensive":[153],"experiments":[154],"two":[156],"datasets,":[159],"namely":[160],"3DSSG":[161],"Replica,":[163],"evaluate":[165],"adaptability":[169],"framework,":[173],"demonstrating":[174],"its":[175],"potential":[176],"pave":[178],"way":[180],"advancement":[183],"understanding.":[186],"Our":[187],"code":[188],"are":[191],"published":[192],"https://github.com/YuansuHao/OSU-3DSG.":[194]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-30T00:00:00"}
