{"id":"https://openalex.org/W7164906160","doi":"https://doi.org/10.48550/arxiv.2606.15328","title":"SGFormer++: Semantic Graph Transformer for Incremental 3D Scene Graph Generation","display_name":"SGFormer++: Semantic Graph Transformer for Incremental 3D Scene Graph Generation","publication_year":2026,"publication_date":"2026-06-13","ids":{"openalex":"https://openalex.org/W7164906160","doi":"https://doi.org/10.48550/arxiv.2606.15328"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.15328","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.15328","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.15328","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103041611","display_name":"Mengshi Qi","orcid":"https://orcid.org/0000-0002-6955-6635"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qi, Mengshi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040389265","display_name":"Changsheng Lv","orcid":"https://orcid.org/0000-0001-8485-3905"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lv, Changsheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040327990","display_name":"Zijian Fu","orcid":"https://orcid.org/0000-0001-9872-4346"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu, Zijian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138690740","display_name":"Xianlin Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Xianlin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138711216","display_name":"Huadong Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Huadong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5889000296592712,"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":0.5889000296592712,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.13199999928474426,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.07880000025033951,"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/graph","display_name":"Graph","score":0.43529999256134033},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.414000004529953},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.39959999918937683},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3962000012397766},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.3736000061035156},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.37070000171661377},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.3684000074863434},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.3447999954223633},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.34119999408721924}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7369999885559082},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5335000157356262},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.43529999256134033},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4300999939441681},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.414000004529953},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.39959999918937683},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3962000012397766},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.3736000061035156},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.37070000171661377},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3684000074863434},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.3447999954223633},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.34119999408721924},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3400999903678894},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.33809998631477356},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3154999911785126},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.30790001153945923},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.30320000648498535},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29510000348091125},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.29280000925064087},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2599000036716461},{"id":"https://openalex.org/C140146324","wikidata":"https://www.wikidata.org/wiki/Q1144319","display_name":"Predicate (mathematical logic)","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2556000053882599},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C78023250","wikidata":"https://www.wikidata.org/wiki/Q657596","display_name":"Unary operation","level":2,"score":0.2540999948978424}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.15328","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.15328","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.15328","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.15328","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,78,148],"propose":[4],"SGFormer++,":[5],"a":[6,88,104,152,170,206],"novel":[7,153],"Semantic":[8,105],"Graph":[9,89],"Transformer":[10,67],"for":[11,84],"3D":[12,85],"scene":[13,49],"graph":[14,53],"generation":[15],"(SGG),":[16],"which":[17,157],"aims":[18],"to":[19,72,165],"parse":[20],"point":[21],"cloud":[22],"scenes":[23],"into":[24],"semantic":[25,125],"structural":[26],"graphs,":[27],"where":[28,142],"nodes":[29],"denote":[30],"detected":[31],"object":[32],"instances":[33],"and":[34,61,102,120,169,183,201,219],"edges":[35],"encode":[36],"their":[37],"pairwise":[38],"relationships,":[39],"with":[40,98,112,151],"the":[41,135,189,215],"core":[42],"challenge":[43,137],"lying":[44],"in":[45,198,211],"modeling":[46],"complex":[47],"global":[48,74,96],"structure.":[50],"While":[51],"existing":[52],"convolutional":[54],"network":[55],"(GCN)-based":[56],"methods":[57],"suffer":[58],"from":[59,115],"over-smoothing":[60],"limited":[62],"receptive":[63],"fields,":[64],"SGFormer++":[65,150,194],"leverages":[66],"layers":[68],"as":[69],"its":[70],"backbone":[71],"enable":[73],"message":[75],"passing.":[76],"Specifically,":[77],"introduce":[79],"two":[80],"key":[81],"components":[82],"tailored":[83],"SGG:":[86],"(1)":[87],"Embedding":[90],"Layer++":[91,107],"that":[92,108,175,193],"efficiently":[93],"integrates":[94],"edge-aware":[95],"context":[97],"linear":[99],"computational":[100],"complexity,":[101],"(2)":[103],"Injection":[106],"enriches":[109],"visual":[110],"features":[111,160],"linguistic":[113],"priors":[114],"large":[116],"language":[117],"models":[118,122],"(LLMs)":[119],"vision-language":[121],"(VLMs),":[123],"boosting":[124],"representation":[126],"without":[127],"introducing":[128],"extra":[129],"trainable":[130],"parameters.":[131],"To":[132],"further":[133],"address":[134],"practical":[136],"of":[138],"incremental":[139,202,216],"SGG":[140],"(I-SGG),":[141],"new":[143],"relationship":[144],"categories":[145],"arrive":[146],"sequentially,":[147],"equip":[149],"Spatial-guided":[154],"Feature":[155],"Adapter,":[156],"calibrates":[158],"predicate":[159],"using":[161],"subject-object":[162],"spatial":[163],"geometry":[164],"counter":[166],"scale":[167],"variation,":[168],"Cascaded":[171],"Binary":[172],"Prediction":[173],"Head":[174],"mitigates":[176],"catastrophic":[177],"forgetting":[178],"via":[179],"task-incremental":[180],"classifier":[181],"expansion":[182],"logit":[184],"distillation.":[185],"Extensive":[186],"experiments":[187],"on":[188],"3DSSG":[190],"benchmark":[191],"demonstrate":[192],"achieves":[195],"state-of-the-art":[196],"performance":[197],"both":[199],"standard":[200],"settings:":[203],"it":[204],"yields":[205],"significant":[207],"4.49%":[208],"absolute":[209],"improvement":[210],"Predicate":[212],"A@1":[213],"under":[214],"setting.":[217],"Code":[218],"data":[220],"are":[221],"available":[222],"at:":[223],"https://github.com/Andy20178/SGFormer.":[224]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-17T00:00:00"}