{"id":"https://openalex.org/W4413280241","doi":"https://doi.org/10.1007/s44443-025-00203-2","title":"SPIN-SGG: spatial integration for open-vocabulary scene graph generation","display_name":"SPIN-SGG: spatial integration for open-vocabulary scene graph generation","publication_year":2025,"publication_date":"2025-08-18","ids":{"openalex":"https://openalex.org/W4413280241","doi":"https://doi.org/10.1007/s44443-025-00203-2"},"language":"en","primary_location":{"id":"doi:10.1007/s44443-025-00203-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44443-025-00203-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44443-025-00203-2.pdf","source":{"id":"https://openalex.org/S2764955546","display_name":"Journal of King Saud University - Computer and Information Sciences","issn_l":"1319-1578","issn":["1319-1578","2213-1248"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of King Saud University Computer and Information Sciences","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://link.springer.com/content/pdf/10.1007/s44443-025-00203-2.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101319191","display_name":"Nanhao Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I2802624667","display_name":"Hefei Institutes of Physical Science","ror":"https://ror.org/046n57345","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I2802624667"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Nanhao Liang","raw_affiliation_strings":["Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei, P. R. China","University of Science and Technology of China, Hefei, P. R. China"],"affiliations":[{"raw_affiliation_string":"Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei, P. R. China","institution_ids":["https://openalex.org/I2802624667","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101798003","display_name":"Xiaoyuan Yang","orcid":"https://orcid.org/0000-0002-7367-0115"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I2802624667","display_name":"Hefei Institutes of Physical Science","ror":"https://ror.org/046n57345","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I2802624667"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyuan Yang","raw_affiliation_strings":["Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei, P. R. China","University of Science and Technology of China, Hefei, P. R. China"],"affiliations":[{"raw_affiliation_string":"Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei, P. R. China","institution_ids":["https://openalex.org/I2802624667","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101944241","display_name":"Shengyi Wang","orcid":"https://orcid.org/0000-0003-0117-040X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I2802624667","display_name":"Hefei Institutes of Physical Science","ror":"https://ror.org/046n57345","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I2802624667"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengyi Wang","raw_affiliation_strings":["Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei, P. R. China","University of Science and Technology of China, Hefei, P. R. China"],"affiliations":[{"raw_affiliation_string":"Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei, P. R. China","institution_ids":["https://openalex.org/I2802624667","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072988055","display_name":"Yong Liu","orcid":"https://orcid.org/0000-0001-9031-9696"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I2802624667","display_name":"Hefei Institutes of Physical Science","ror":"https://ror.org/046n57345","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I2802624667"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Liu","raw_affiliation_strings":["Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei, P. R. China"],"affiliations":[{"raw_affiliation_string":"Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei, P. R. China","institution_ids":["https://openalex.org/I2802624667","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065705407","display_name":"Yingwei Xia","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I2802624667","display_name":"Hefei Institutes of Physical Science","ror":"https://ror.org/046n57345","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I2802624667"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingwei Xia","raw_affiliation_strings":["Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei, P. R. China"],"affiliations":[{"raw_affiliation_string":"Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei, P. R. China","institution_ids":["https://openalex.org/I2802624667","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101319191"],"corresponding_institution_ids":["https://openalex.org/I126520041","https://openalex.org/I19820366","https://openalex.org/I2802624667"],"apc_list":{"value":1350,"currency":"USD","value_usd":1350},"apc_paid":{"value":1350,"currency":"USD","value_usd":1350},"fwci":1.2134,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.82450923,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"37","issue":"7","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":0.9998000264167786,"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":0.9998000264167786,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9925000071525574,"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":0.9724000096321106,"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/vocabulary","display_name":"Vocabulary","score":0.5888265371322632},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4572429955005646},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.42895767092704773},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.15269649028778076},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12401527166366577}],"concepts":[{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5888265371322632},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4572429955005646},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.42895767092704773},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.15269649028778076},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12401527166366577},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s44443-025-00203-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44443-025-00203-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44443-025-00203-2.pdf","source":{"id":"https://openalex.org/S2764955546","display_name":"Journal of King Saud University - Computer and Information Sciences","issn_l":"1319-1578","issn":["1319-1578","2213-1248"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of King Saud University Computer and Information Sciences","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:b42f33e9e8844ee78e7fdbdb92c8208d","is_oa":true,"landing_page_url":"https://doaj.org/article/b42f33e9e8844ee78e7fdbdb92c8208d","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of King Saud University: Computer and Information Sciences, Vol 37, Iss 7, Pp 1-14 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s44443-025-00203-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44443-025-00203-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44443-025-00203-2.pdf","source":{"id":"https://openalex.org/S2764955546","display_name":"Journal of King Saud University - Computer and Information Sciences","issn_l":"1319-1578","issn":["1319-1578","2213-1248"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of King Saud University Computer and Information Sciences","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5400000214576721,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320335774","display_name":"Key Technologies Research and Development Program","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413280241.pdf","grobid_xml":"https://content.openalex.org/works/W4413280241.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W1514151998","https://openalex.org/W1933349210","https://openalex.org/W2002827932","https://openalex.org/W2124907686","https://openalex.org/W2125310925","https://openalex.org/W2479423890","https://openalex.org/W2519683295","https://openalex.org/W2579549467","https://openalex.org/W2745461083","https://openalex.org/W2776212699","https://openalex.org/W2810482788","https://openalex.org/W2886970679","https://openalex.org/W2890531016","https://openalex.org/W2962785943","https://openalex.org/W2963101956","https://openalex.org/W2963115613","https://openalex.org/W2963649796","https://openalex.org/W2963902384","https://openalex.org/W3034984754","https://openalex.org/W3109428934","https://openalex.org/W3172610252","https://openalex.org/W4214520160","https://openalex.org/W4226094317","https://openalex.org/W4312651322","https://openalex.org/W4312936847","https://openalex.org/W4390357571","https://openalex.org/W4390871795","https://openalex.org/W4392904155","https://openalex.org/W4399938885","https://openalex.org/W4402713111","https://openalex.org/W4402716288","https://openalex.org/W4403725720","https://openalex.org/W4404612908","https://openalex.org/W4405595839","https://openalex.org/W4409262174","https://openalex.org/W4409365924","https://openalex.org/W6600002382","https://openalex.org/W6600008909","https://openalex.org/W6600829110","https://openalex.org/W6601205648","https://openalex.org/W6603527449"],"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],"Generation":[2],"(SGG)":[3],"aims":[4],"to":[5],"represent":[6],"visual":[7],"scenes":[8],"as":[9,20,141],"structured":[10],"graphs,":[11],"where":[12],"objects":[13],"and":[14,42,68,99,103,135,144,157,172,195,204],"their":[15],"pairwise":[16],"relationships":[17],"are":[18],"modeled":[19],"relational":[21],"triples.":[22],"However,":[23],"conventional":[24],"SGG":[25,73,185],"methods":[26],"often":[27],"struggle":[28],"with":[29,129,187],"two":[30],"crucial":[31],"limitations:":[32],"inadequate":[33],"modeling":[34],"of":[35,189],"rich":[36],"spatial":[37,62,113,137,150,206],"relations":[38],"beyond":[39],"2D":[40],"layouts,":[41],"poor":[43],"generalization":[44],"in":[45,161,191],"open-vocabulary":[46,72,184],"scenarios.":[47],"To":[48,147],"address":[49],"these":[50],"limitations,":[51],"we":[52,88,121,153],"propose":[53,122],"SPIN-SGG,":[54],"a":[55,84,105,123,173],"novel":[56],"framework":[57],"that":[58,110,179],"explicitly":[59],"integrates":[60],"multi-dimensional":[61],"information\u2014including":[63],"planar":[64],"geometry,":[65],"relative":[66],"depth,":[67],"topological":[69],"structure\u2014into":[70],"an":[71],"pipeline,":[74],"without":[75],"requiring":[76],"ground-truth":[77],"3D":[78],"annotations.":[79],"Our":[80],"approach":[81],"builds":[82],"upon":[83],"two-stage":[85],"design.":[86],"First,":[87],"generate":[89],"pseudo-3D":[90],"scene":[91,132,163],"reconstructions":[92],"from":[93],"monocular":[94],"images":[95],"using":[96],"multi-view":[97],"synthesis":[98],"point":[100],"cloud":[101],"estimation,":[102],"construct":[104],"spatially":[106,124],"enriched":[107],"instruction-tuning":[108],"dataset":[109,177],"includes":[111],"fine-grained":[112],"predicates":[114],"(e.g.,":[115],"left":[116],"of,":[117],"above,":[118],"inside).":[119],"Second,":[120],"aware":[125],"visual-language":[126],"model,":[127],"trained":[128],"both":[130],"static":[131],"graph":[133],"descriptions":[134],"dynamic":[136],"reasoning":[138,207],"tasks":[139],"such":[140],"question":[142],"answering":[143],"multi-turn":[145],"dialogue.":[146],"further":[148],"enhance":[149],"layout":[151],"consistency,":[152],"incorporate":[154],"layer-aware":[155],"clustering":[156],"object-level":[158],"depth":[159],"anchoring":[160],"the":[162,169],"parsing":[164],"module.":[165],"Extensive":[166],"experiments":[167],"on":[168,193,199],"PSG":[170,194],"benchmark":[171],"newly":[174],"curated":[175],"SpatialSGG":[176],"demonstrate":[178],"SPIN-SGG":[180],"significantly":[181],"outperforms":[182],"previous":[183],"methods,":[186],"improvements":[188],"+1.3%":[190],"mR@50":[192],"+2.7%":[196],"QA":[197],"accuracy":[198],"SpatialSGG,":[200],"showcasing":[201],"its":[202],"robust":[203],"comprehensive":[205],"capabilities.":[208]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
