{"id":"https://openalex.org/W4401608390","doi":"https://doi.org/10.1109/tmi.2024.3444279","title":"S\u00b2Former-OR: Single-Stage Bi-Modal Transformer for Scene Graph Generation in OR","display_name":"S\u00b2Former-OR: Single-Stage Bi-Modal Transformer for Scene Graph Generation in OR","publication_year":2024,"publication_date":"2024-08-15","ids":{"openalex":"https://openalex.org/W4401608390","doi":"https://doi.org/10.1109/tmi.2024.3444279","pmid":"https://pubmed.ncbi.nlm.nih.gov/39146166"},"language":"en","primary_location":{"id":"doi:10.1109/tmi.2024.3444279","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmi.2024.3444279","pdf_url":null,"source":{"id":"https://openalex.org/S58069681","display_name":"IEEE Transactions on Medical Imaging","issn_l":"0278-0062","issn":["0278-0062","1558-254X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Medical Imaging","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5082263233","display_name":"Jialun Pei","orcid":"https://orcid.org/0000-0002-2630-2838"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Jialun Pei","raw_affiliation_strings":["Department of Computer Science and Engineering and the Institute of Medical Intelligence and XR, The Chinese University of Hong Kong, Hong Kong, SAR, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering and the Institute of Medical Intelligence and XR, The Chinese University of Hong Kong, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104248359","display_name":"Diandian Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Diandian Guo","raw_affiliation_strings":["Institute of Medical Intelligence and XR, The Chinese University of Hong Kong, Hong Kong, SAR, China"],"affiliations":[{"raw_affiliation_string":"Institute of Medical Intelligence and XR, The Chinese University of Hong Kong, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063092287","display_name":"Jingyang Zhang","orcid":"https://orcid.org/0000-0002-1788-6501"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jingyang Zhang","raw_affiliation_strings":["Institute of Medical Intelligence and XR, The Chinese University of Hong Kong, Hong Kong, SAR, China"],"affiliations":[{"raw_affiliation_string":"Institute of Medical Intelligence and XR, The Chinese University of Hong Kong, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015803667","display_name":"Manxi Lin","orcid":"https://orcid.org/0000-0003-3399-8682"},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Manxi Lin","raw_affiliation_strings":["Department of Applied Mathematics and Computer Science, Technical University of Denmark, Lyngby, Denmark"],"affiliations":[{"raw_affiliation_string":"Department of Applied Mathematics and Computer Science, Technical University of Denmark, Lyngby, Denmark","institution_ids":["https://openalex.org/I96673099"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050163233","display_name":"Yueming Jin","orcid":"https://orcid.org/0000-0003-3775-3877"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yueming Jin","raw_affiliation_strings":["Department of Biomedical Engineering and the Department of Electrical and Computer Engineering, National University of Singapore (NUS), Queenstown, Singapore"],"affiliations":[{"raw_affiliation_string":"Department of Biomedical Engineering and the Department of Electrical and Computer Engineering, National University of Singapore (NUS), Queenstown, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032708386","display_name":"Pheng\u2010Ann Heng","orcid":"https://orcid.org/0000-0003-3055-5034"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Pheng-Ann Heng","raw_affiliation_strings":["Department of Computer Science and Engineering and the Institute of Medical Intelligence and XR, The Chinese University of Hong Kong, Hong Kong, SAR, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering and the Institute of Medical Intelligence and XR, The Chinese University of Hong Kong, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5082263233"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":0.9708,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.76401162,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"44","issue":"1","first_page":"361","last_page":"372"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9968000054359436,"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":0.9968000054359436,"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":0.9865000247955322,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9835000038146973,"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/modal","display_name":"Modal","score":0.5710196495056152},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.44916659593582153},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.44767534732818604},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4434027075767517},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.36275339126586914},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3502737879753113},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3257138729095459},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.2116374373435974},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.20573610067367554},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.14201924204826355}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5710196495056152},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44916659593582153},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.44767534732818604},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4434027075767517},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.36275339126586914},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3502737879753113},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3257138729095459},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.2116374373435974},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.20573610067367554},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.14201924204826355},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D009873","descriptor_name":"Operating Rooms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009873","descriptor_name":"Operating Rooms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009873","descriptor_name":"Operating Rooms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009873","descriptor_name":"Operating Rooms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D021621","descriptor_name":"Imaging, Three-Dimensional","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D021621","descriptor_name":"Imaging, Three-Dimensional","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D021621","descriptor_name":"Imaging, Three-Dimensional","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D021621","descriptor_name":"Imaging, Three-Dimensional","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1109/tmi.2024.3444279","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmi.2024.3444279","pdf_url":null,"source":{"id":"https://openalex.org/S58069681","display_name":"IEEE Transactions on Medical Imaging","issn_l":"0278-0062","issn":["0278-0062","1558-254X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Medical Imaging","raw_type":"journal-article"},{"id":"pmid:39146166","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39146166","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on medical imaging","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4893727646","display_name":null,"funder_award_id":"T45-401/22-N","funder_id":"https://openalex.org/F4320321592","funder_display_name":"Research Grants Council, University Grants Committee"},{"id":"https://openalex.org/G5826875047","display_name":null,"funder_award_id":"GHP/060/21GD","funder_id":"https://openalex.org/F4320324196","funder_display_name":"Innovation and Technology Commission - Hong Kong"},{"id":"https://openalex.org/G5851636306","display_name":null,"funder_award_id":"A-8001267-01-00","funder_id":"https://openalex.org/F4320311687","funder_display_name":"Ministry of Education"}],"funders":[{"id":"https://openalex.org/F4320311687","display_name":"Ministry of Education","ror":"https://ror.org/03m01yf64"},{"id":"https://openalex.org/F4320321592","display_name":"Research Grants Council, University Grants Committee","ror":"https://ror.org/00djwmt25"},{"id":"https://openalex.org/F4320324196","display_name":"Innovation and Technology Commission - Hong Kong","ror":"https://ror.org/04vf9tr09"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1903029394","https://openalex.org/W2016545368","https://openalex.org/W2194775991","https://openalex.org/W2580456502","https://openalex.org/W2591644541","https://openalex.org/W2962766617","https://openalex.org/W2963088785","https://openalex.org/W2963351448","https://openalex.org/W2963902384","https://openalex.org/W3034538190","https://openalex.org/W3035017890","https://openalex.org/W3035154952","https://openalex.org/W3092562667","https://openalex.org/W3096609285","https://openalex.org/W3101560663","https://openalex.org/W3110266995","https://openalex.org/W3128248230","https://openalex.org/W3173181410","https://openalex.org/W3174293538","https://openalex.org/W3174480456","https://openalex.org/W3181556077","https://openalex.org/W3183042936","https://openalex.org/W3201861986","https://openalex.org/W4200498145","https://openalex.org/W4214526701","https://openalex.org/W4221148496","https://openalex.org/W4288083516","https://openalex.org/W4296195896","https://openalex.org/W4312563197","https://openalex.org/W4312578903","https://openalex.org/W4312770707","https://openalex.org/W4312815172","https://openalex.org/W4312960102","https://openalex.org/W4353007189","https://openalex.org/W4366352717","https://openalex.org/W4385245566","https://openalex.org/W4386083046","https://openalex.org/W4387211779","https://openalex.org/W6739778489","https://openalex.org/W6802823847","https://openalex.org/W6804049574","https://openalex.org/W6804131122"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Scene":[0],"graph":[1,159],"generation":[2,160],"(SGG)":[3],"of":[4,51,155,176],"surgical":[5],"procedures":[6],"is":[7,114],"crucial":[8],"in":[9,14,73,91,195],"enhancing":[10],"holistically":[11],"cognitive":[12],"intelligence":[13],"the":[15,29,49,57,74,118,131,152,168],"operating":[16],"room":[17],"(OR).":[18],"However,":[19],"previous":[20],"works":[21],"have":[22,166],"primarily":[23],"relied":[24],"on":[25,35,130,178],"multi-stage":[26],"learning,":[27],"where":[28],"generated":[30],"semantic":[31,121],"scene":[32],"graphs":[33],"depend":[34],"intermediate":[36,162],"processes":[37],"with":[38,182,203,208,215],"pose":[39],"estimation":[40],"and":[41,85,146,172,192],"object":[42],"detection.":[43],"This":[44],"pipeline":[45],"may":[46],"potentially":[47],"compromise":[48],"flexibility":[50],"learning":[52],"multimodal":[53],"representations,":[54],"consequently":[55],"constraining":[56],"overall":[58],"effectiveness.":[59],"In":[60],"this":[61],"study,":[62],"we":[63,134],"introduce":[64],"a":[65,99,110,136,212],"novel":[66,137],"single-stage":[67,205],"bi-modal":[68],"transformer":[69,139],"framework":[70],"for":[71,89,158,211],"SGG":[72,90,170,206],"OR,":[75],"termed":[76],"S2Former-OR,":[77],"aimed":[78],"to":[79,103,116],"complementally":[80],"leverage":[81],"multi-view":[82,105],"2D":[83,120],"scenes":[84],"3D":[86,124],"point":[87,125],"clouds":[88],"an":[92],"end-to-end":[93],"manner.":[94],"Concretely,":[95],"our":[96,201],"model":[97,196],"embraces":[98],"View-Sync":[100],"Transfusion":[101],"scheme":[102],"encourage":[104],"visual":[106],"information":[107],"interaction.":[108],"Concurrently,":[109],"Geometry-Visual":[111],"Cohesion":[112],"operation":[113],"designed":[115],"integrate":[117],"synergic":[119],"features":[122],"into":[123],"cloud":[126],"features.":[127],"Moreover,":[128],"based":[129],"augmented":[132],"feature,":[133],"propose":[135],"relation-sensitive":[138],"decoder":[140],"that":[141],"embeds":[142],"dynamic":[143],"entity-pair":[144,156],"queries":[145],"relational":[147],"trait":[148],"priors,":[149],"which":[150],"enables":[151],"direct":[153],"prediction":[154],"relations":[157],"without":[161],"steps.":[163],"Extensive":[164],"experiments":[165],"validated":[167],"superior":[169],"performance":[171,218],"lower":[173],"computational":[174],"cost":[175],"S2Former-OR":[177],"4D-OR":[179],"benchmark,":[180],"compared":[181,200],"current":[183],"OR-SGG":[184],"methods,":[185],"e.g.,":[186],"3":[187],"percentage":[188],"points":[189],"Precision":[190],"increase":[191],"24.2M":[193],"reduction":[194],"parameters.":[197],"We":[198],"further":[199],"method":[202],"generic":[204],"methods":[207],"broader":[209],"metrics":[210],"comprehensive":[213],"evaluation,":[214],"consistently":[216],"better":[217],"achieved.":[219],"Our":[220],"source":[221],"code":[222],"can":[223],"be":[224],"made":[225],"available":[226],"at:":[227],"https://github.com/PJLallen/S2Former-OR.":[228]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2024-08-16T00:00:00"}