{"id":"https://openalex.org/W7138319999","doi":"https://doi.org/10.1609/aaai.v40i7.37435","title":"Multi-view Invariance Learning for 3D Scene Graph Pre-training via Collaborative Cross-Modal Regularization","display_name":"Multi-view Invariance Learning for 3D Scene Graph Pre-training via Collaborative Cross-Modal Regularization","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138319999","doi":"https://doi.org/10.1609/aaai.v40i7.37435"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i7.37435","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i7.37435","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i7.37435","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129727121","display_name":"Yucheng Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yucheng Huang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122050118","display_name":"Luping Ji","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luping Ji","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129668569","display_name":"Ruijie Xiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruijie Xiao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100714106","display_name":"Jiayuan Sun","orcid":"https://orcid.org/0009-0002-9569-131X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiayuan Sun","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5129727121"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.70992366,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"7","first_page":"5203","last_page":"5211"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.8343999981880188,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.8343999981880188,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.07370000332593918,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.012400000356137753,"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/predicate","display_name":"Predicate (mathematical logic)","score":0.5429999828338623},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.5411999821662903},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.5357000231742859},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4717999994754791},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.43619999289512634},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4138999879360199},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.36809998750686646}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6815999746322632},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.567799985408783},{"id":"https://openalex.org/C140146324","wikidata":"https://www.wikidata.org/wiki/Q1144319","display_name":"Predicate (mathematical logic)","level":2,"score":0.5429999828338623},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.5411999821662903},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.5357000231742859},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4717999994754791},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.43619999289512634},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4138999879360199},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.36809998750686646},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.3546000123023987},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3506999909877777},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.35010001063346863},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.33500000834465027},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33059999346733093},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.303600013256073},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.28369998931884766},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.27649998664855957},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.26409998536109924},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.26109999418258667}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i7.37435","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i7.37435","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i7.37435","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i7.37435","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.5874171257019043,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"3D":[0,63,87,172],"scene":[1,9,173],"graph":[2,174],"generation":[3,175],"is":[4,13,151,168],"a":[5,70,97,143],"pivotal":[6],"task":[7],"in":[8,141,170],"understanding.":[10],"Its":[11],"performance":[12],"easy":[14],"to":[15,95,116,153],"be":[16],"constrained":[17],"by":[18,58],"the":[19,26,40,82,108,113,124,133,138,156],"limited":[20],"availability":[21],"of":[22,86,159],"annotated":[23],"data.":[24],"Currently,":[25],"existing":[27],"solutions":[28],"on":[29,35],"point":[30],"cloud":[31],"pre-training":[32],"usually":[33],"emphasize":[34],"object-centric":[36],"representations":[37],"while":[38],"neglecting":[39],"predicate":[41,59,144,157],"feature":[42,102],"learning.":[43,103],"This":[44],"limitation":[45],"significantly":[46],"hinders":[47],"their":[48,90],"relational":[49],"reasoning":[50],"capabilities,":[51],"as":[52],"inter-object":[53],"relationships":[54,92],"are":[55,93],"fundamentally":[56],"governed":[57],"features.":[60],"To":[61,131],"enhance":[62],"Scene":[64],"Graphs":[65],"Pre-training,":[66],"this":[67],"paper":[68],"proposes":[69],"task-specific":[71],"Multi-view":[72],"Invariance":[73],"Learning":[74],"framework":[75,106,167],"with":[76,147],"Collaborative":[77],"Cross-modal":[78],"Regularization.":[79],"In":[80],"detail,":[81],"inherent":[83],"horizontal-rotation":[84],"invariance":[85],"objects":[88],"and":[89],"semantic":[91,125],"leveraged":[94],"construct":[96],"self-supervised":[98],"paradigm":[99],"for":[100],"triplet":[101],"Moreover,":[104],"our":[105,166],"harnesses":[107],"cross-modal":[109],"prior":[110],"knowledge":[111,134,148],"from":[112,137],"vision-language":[114],"model":[115,118,140],"regularize":[117],"optimization.":[119],"It":[120],"could":[121],"further":[122],"achieve":[123],"discrimination":[126],"via":[127],"unsupervised":[128],"deep":[129],"clustering.":[130],"resolve":[132],"discrepancies":[135],"arising":[136],"pre-trained":[139,160],"fine-tuning,":[142],"adapter":[145],"equipped":[146],"filtering":[149],"gate":[150],"devised":[152],"selectively":[154],"aggregate":[155],"features":[158],"model.":[161],"Extensive":[162],"experiments":[163],"demonstrate":[164],"that":[165],"effective":[169],"boosting":[171],"performance,":[176],"surpassing":[177],"state-of-the-art":[178],"ones.":[179]},"counts_by_year":[],"updated_date":"2026-03-18T06:31:55.123368","created_date":"2026-03-18T00:00:00"}