{"id":"https://openalex.org/W4383108485","doi":"https://doi.org/10.1109/icra48891.2023.10160647","title":"Dynamic Interactive Relation Capturing via Scene Graph Learning for Robotic Surgical Report Generation","display_name":"Dynamic Interactive Relation Capturing via Scene Graph Learning for Robotic Surgical Report Generation","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4383108485","doi":"https://doi.org/10.1109/icra48891.2023.10160647"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10160647","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160647","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","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/A5074311923","display_name":"Hongqiu Wang","orcid":"https://orcid.org/0000-0001-9726-4253"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Hongqiu Wang","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou),Guangzhou,Guangdong,China,511400"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou),Guangzhou,Guangdong,China,511400","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"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/I4210122016","display_name":"Wellcome / EPSRC Centre for Interventional and Surgical Sciences","ror":"https://ror.org/03r42r570","country_code":"GB","type":"facility","lineage":["https://openalex.org/I124357947","https://openalex.org/I1299528221","https://openalex.org/I4210087105","https://openalex.org/I4210122016","https://openalex.org/I45129253","https://openalex.org/I87048295"]},{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yueming Jin","raw_affiliation_strings":["University College London,Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS),Department of Computer Science","Department of Computer Science, Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS), University College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University College London,Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS),Department of Computer Science","institution_ids":["https://openalex.org/I4210122016","https://openalex.org/I45129253"]},{"raw_affiliation_string":"Department of Computer Science, Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS), University College London","institution_ids":["https://openalex.org/I4210122016","https://openalex.org/I45129253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016081925","display_name":"Lei Zhu","orcid":"https://orcid.org/0000-0003-3871-663X"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Lei Zhu","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou),Guangzhou,Guangdong,China,511400","The Hong Kong University of Science and Technology, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou),Guangzhou,Guangdong,China,511400","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]},{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Hong Kong SAR, China","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5074311923"],"corresponding_institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"],"apc_list":null,"apc_paid":null,"fwci":2.3199,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.90379476,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2702","last_page":"2709"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9901000261306763,"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/computer-science","display_name":"Computer science","score":0.7872344255447388},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.551353394985199},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.4842517077922821},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.44110608100891113},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43703240156173706},{"id":"https://openalex.org/keywords/graph-layout","display_name":"Graph Layout","score":0.4138379991054535},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2534152865409851},{"id":"https://openalex.org/keywords/graph-drawing","display_name":"Graph drawing","score":0.21834158897399902},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.18539535999298096},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.0918135941028595}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7872344255447388},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.551353394985199},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.4842517077922821},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.44110608100891113},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43703240156173706},{"id":"https://openalex.org/C2911174283","wikidata":"https://www.wikidata.org/wiki/Q739462","display_name":"Graph Layout","level":4,"score":0.4138379991054535},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2534152865409851},{"id":"https://openalex.org/C112953755","wikidata":"https://www.wikidata.org/wiki/Q739462","display_name":"Graph drawing","level":3,"score":0.21834158897399902},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.18539535999298096},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.0918135941028595}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icra48891.2023.10160647","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160647","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-130386","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-130386","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3777282796","display_name":null,"funder_award_id":"61902275","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2116341502","https://openalex.org/W2134178143","https://openalex.org/W2154652894","https://openalex.org/W2160899683","https://openalex.org/W2194775991","https://openalex.org/W2600463316","https://openalex.org/W2770165365","https://openalex.org/W2803259101","https://openalex.org/W2803411968","https://openalex.org/W2888096830","https://openalex.org/W2907279673","https://openalex.org/W2907492528","https://openalex.org/W2963175158","https://openalex.org/W2963486920","https://openalex.org/W2963964898","https://openalex.org/W2990818246","https://openalex.org/W3003209274","https://openalex.org/W3034655362","https://openalex.org/W3036848992","https://openalex.org/W3098325931","https://openalex.org/W3123909522","https://openalex.org/W3152893301","https://openalex.org/W3202563726","https://openalex.org/W3207523613","https://openalex.org/W3207576362","https://openalex.org/W3210586215","https://openalex.org/W4283813460","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6678262379","https://openalex.org/W6682631176","https://openalex.org/W6739901393","https://openalex.org/W6751711410","https://openalex.org/W6773996751"],"related_works":["https://openalex.org/W4234874385","https://openalex.org/W2323648130","https://openalex.org/W2157140558","https://openalex.org/W2378782423","https://openalex.org/W4233308809","https://openalex.org/W4387129494","https://openalex.org/W1555430809","https://openalex.org/W1593721195","https://openalex.org/W4387183640","https://openalex.org/W2100388549"],"abstract_inverted_index":{"For":[0],"robot-assisted":[1],"surgery,":[2],"an":[3,115],"accurate":[4],"surgical":[5,40,44,81,93,245,273],"report":[6,45,70,82,274],"reflects":[7],"clinical":[8],"operations":[9],"during":[10],"surgery":[11,258],"and":[12,19,31,36,64,92,114,141,234,261,279,284],"helps":[13],"document":[14],"entry":[15],"tasks,":[16],"post-operative":[17],"analysis":[18],"follow-up":[20],"treatment.":[21],"It":[22],"is":[23],"a":[24,76,101,135,162,198,239,255],"challenging":[25],"task":[26],"due":[27],"to":[28,79,106,120,139,166,183,202],"many":[29],"complex":[30],"diverse":[32],"interactions":[33],"between":[34,62,90],"instruments":[35],"tissues":[37,63,91],"in":[38,125],"the":[39,59,69,87,108,122,147,158,168,171,175,179,185,189,206,215,219,243,249],"scene.":[41],"Although":[42],"existing":[43,271],"generation":[46,71,83,275],"methods":[47,276],"based":[48],"on":[49,174,254],"deep":[50],"learning":[51,124,187],"have":[52],"achieved":[53],"large":[54],"success,":[55],"they":[56],"often":[57],"ignore":[58],"interactive":[60,88,109,172],"relation":[61,89,110,173,208],"instrumental":[65],"tools,":[66],"thereby":[67],"degrading":[68],"performance.":[72],"This":[73],"paper":[74],"presents":[75],"neural":[77],"network":[78,267],"boost":[80],"by":[84],"explicitly":[85],"exploring":[86],"instruments.":[94],"To":[95],"do":[96],"so,":[97],"we":[98,132,224],"first":[99,133],"devise":[100,134],"relational":[102],"exploration":[103],"(RE)":[104],"module":[105,119,160,196,233],"model":[107,165,201],"via":[111],"graph":[112,123,144,186,211,216,229],"learning,":[113],"interaction":[116,207],"perception":[117],"(IP)":[118],"assist":[121],"RE":[126,155,220,232],"module.":[127,156,221],"In":[128],"our":[129,194,252,266],"IP":[130,159,195],"module,":[131],"node":[136,212],"tracking":[137],"system":[138],"identify":[140,205],"append":[142],"missing":[143],"nodes":[145,230],"of":[146,170,178,209,227,231,251],"current":[148,180,190],"video":[149,181,191],"frame":[150,182],"for":[151,213,241,282],"constructing":[152],"graphs":[153],"at":[154,188,218],"Moreover,":[157],"generates":[161],"global":[163],"attention":[164,200],"indicate":[167],"existence":[169],"whole":[176],"scene":[177],"eliminate":[184],"frame.":[192],"Furthermore,":[193],"predicts":[197],"local":[199],"more":[203],"accurately":[204],"each":[210],"assisting":[214],"updating":[217],"After":[222],"that,":[223],"concatenate":[225],"features":[226,237],"all":[228],"pass":[235],"concatenated":[236],"into":[238],"transformer":[240],"generating":[242],"output":[244],"report.":[246],"We":[247],"validate":[248],"effectiveness":[250],"method":[253],"widely-used":[256],"robotic":[257],"benchmark":[259],"dataset,":[260],"experimental":[262],"results":[263],"show":[264],"that":[265],"can":[268],"significantly":[269],"outperform":[270],"state-of-the-art":[272],"(e.g.,":[277],"7.48%":[278],"5.43%":[280],"higher":[281],"BLEU-1":[283],"ROUGE).":[285]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":8}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2023-07-05T00:00:00"}