{"id":"https://openalex.org/W4383109126","doi":"https://doi.org/10.1109/icra48891.2023.10160403","title":"Surgical-VQLA:Transformer with Gated Vision-Language Embedding for Visual Question Localized-Answering in Robotic Surgery","display_name":"Surgical-VQLA:Transformer with Gated Vision-Language Embedding for Visual Question Localized-Answering in Robotic Surgery","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4383109126","doi":"https://doi.org/10.1109/icra48891.2023.10160403"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10160403","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160403","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":"conference-paper","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/A5101434323","display_name":"Long Bai","orcid":"https://orcid.org/0000-0003-2671-3298"},"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":"Long Bai","raw_affiliation_strings":["The Chinese University of Hong Kong (CUHK),Dept. of Electronic Engineering,Hong Kong,China","Dept. of Electronic Engineering, The Chinese University of Hong Kong (CUHK), Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong (CUHK),Dept. of Electronic Engineering,Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Dept. of Electronic Engineering, The Chinese University of Hong Kong (CUHK), Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066653567","display_name":"Mobarakol Islam","orcid":"https://orcid.org/0000-0002-7162-2822"},"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":"Mobarakol Islam","raw_affiliation_strings":["University College,Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS),London,UK","Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS), University College, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University College,Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS),London,UK","institution_ids":["https://openalex.org/I4210122016"]},{"raw_affiliation_string":"Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS), University College, London, UK","institution_ids":["https://openalex.org/I4210122016","https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040765329","display_name":"Lalithkumar Seenivasan","orcid":"https://orcid.org/0000-0002-0103-1234"},"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":"Lalithkumar Seenivasan","raw_affiliation_strings":["National University of Singapore,Dept. of Biomedical Engineering,Singapore","Dept. of Biomedical Engineering, National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Dept. of Biomedical Engineering,Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Dept. of Biomedical Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032340829","display_name":"Hongliang Ren","orcid":"https://orcid.org/0000-0002-6488-1551"},"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"]},{"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","SG"],"is_corresponding":false,"raw_author_name":"Hongliang Ren","raw_affiliation_strings":["The Chinese University of Hong Kong (CUHK),Dept. of Electronic Engineering,Hong Kong,China","Dept. of Biomedical Engineering, National University of Singapore, Singapore","Dept. of Electronic Engineering, The Chinese University of Hong Kong (CUHK), Hong Kong, China","Shun Hing Institute of Advanced Engineering, The Chinese University of Hong Kong (CUHK), Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong (CUHK),Dept. of Electronic Engineering,Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Dept. of Biomedical Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Dept. of Electronic Engineering, The Chinese University of Hong Kong (CUHK), Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Shun Hing Institute of Advanced Engineering, The Chinese University of Hong Kong (CUHK), Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6859","last_page":"6865"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9987000226974487,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9659000039100647,"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/question-answering","display_name":"Question answering","score":0.8578343987464905},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.780277669429779},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5811176300048828},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.518842339515686},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4364534020423889},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.42803025245666504},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.41071105003356934},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35017484426498413},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3493337035179138},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.34559234976768494},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.1946215033531189}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.8578343987464905},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.780277669429779},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5811176300048828},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.518842339515686},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4364534020423889},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.42803025245666504},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.41071105003356934},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35017484426498413},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3493337035179138},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34559234976768494},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.1946215033531189},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48891.2023.10160403","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160403","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5799999833106995,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G5523909023","display_name":null,"funder_award_id":"CRF C4026-21GF,CRF C4063-18G","funder_id":"https://openalex.org/F4320321592","funder_display_name":"Research Grants Council, University Grants Committee"},{"id":"https://openalex.org/G552850756","display_name":null,"funder_award_id":"BME-pl-21/8115064","funder_id":"https://openalex.org/F4320335138","funder_display_name":"Shun Hing Institute of Advanced Engineering"},{"id":"https://openalex.org/G6558814693","display_name":null,"funder_award_id":"EP/W00805X/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320321592","display_name":"Research Grants Council, University Grants Committee","ror":"https://ror.org/00djwmt25"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"},{"id":"https://openalex.org/F4320335138","display_name":"Shun Hing Institute of Advanced Engineering","ror":"https://ror.org/00t33hh48"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1522301498","https://openalex.org/W2097540174","https://openalex.org/W2108598243","https://openalex.org/W2164587673","https://openalex.org/W2194775991","https://openalex.org/W2525778437","https://openalex.org/W2768297392","https://openalex.org/W2809600803","https://openalex.org/W2896457183","https://openalex.org/W2951529591","https://openalex.org/W2962766617","https://openalex.org/W2968124245","https://openalex.org/W3003209274","https://openalex.org/W3094502228","https://openalex.org/W3094897602","https://openalex.org/W3094926883","https://openalex.org/W3141200244","https://openalex.org/W3163465952","https://openalex.org/W3171312896","https://openalex.org/W3193402170","https://openalex.org/W3198730297","https://openalex.org/W3200936534","https://openalex.org/W3201068857","https://openalex.org/W4210528082","https://openalex.org/W4283368635","https://openalex.org/W4288574670","https://openalex.org/W4385245566","https://openalex.org/W6606244218","https://openalex.org/W6620707391","https://openalex.org/W6631190155","https://openalex.org/W6727690538","https://openalex.org/W6733328719","https://openalex.org/W6752789745","https://openalex.org/W6755207826","https://openalex.org/W6758742486","https://openalex.org/W6767279747","https://openalex.org/W6773996751","https://openalex.org/W6796729313","https://openalex.org/W6800139874"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W2185469136","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2199184806","https://openalex.org/W127837312","https://openalex.org/W2922283411","https://openalex.org/W4384789578","https://openalex.org/W4387421317"],"abstract_inverted_index":{"Despite":[0],"the":[1,62,86,90,127,153,158,164,167,181,188,195,201,205,222,225,245,257,262,267,281],"availability":[2],"of":[3,9,61,89,109,117,166,204,224,232,244],"computer-aided":[4],"simulators":[5],"and":[6,31,34,54,73,82,107,122,242,260],"recorded":[7,58],"videos":[8,239],"surgical":[10,46,52,97,137,155,238,258],"procedures,":[11],"junior":[12],"residents":[13],"still":[14],"heavily":[15],"rely":[16],"on":[17],"experts":[18],"to":[19,49,78,104,151,176,186,216,266],"answer":[20,93,159],"their":[21,36],"queries.":[22],"However,":[23,95],"expert":[24],"surgeons":[25],"are":[26],"often":[27],"overloaded":[28],"with":[29,85,163,200],"clinical":[30],"academic":[32],"workloads":[33],"limit":[35],"time":[37],"in":[38,135,147,198],"answering.":[39],"For":[40],"this":[41,140],"purpose,":[42],"we":[43,142,170,193],"develop":[44],"a":[45],"question-answering":[47,226],"system":[48],"facilitate":[50],"robot-assisted":[51],"scene":[53,259],"activity":[55],"understanding":[56],"from":[57,240],"videos.":[59],"Most":[60],"existing":[63,282],"visual":[64,80],"question":[65,91],"answering":[66,129],"(VQA)":[67],"methods":[68],"require":[69],"an":[70,271],"object":[71,98],"detector":[72],"regions":[74],"based":[75],"feature":[76],"extractor":[77],"extract":[79],"features":[81],"fuse":[83],"them":[84],"embedded":[87],"text":[88,121],"for":[92,180],"generation.":[94],"(i)":[96],"detection":[99,196],"model":[100],"is":[101,124,130,133],"scarce":[102],"due":[103],"smaller":[105],"datasets":[106,231],"lack":[108],"bounding":[110],"box":[111],"annotation;":[112],"(ii)":[113],"current":[114],"fusion":[115,165],"strategy":[116],"heterogeneous":[118,168],"modalities":[119],"like":[120],"image":[123],"naive;":[125],"(iii)":[126],"localized":[128,261],"missing,":[131],"which":[132],"crucial":[134],"complex":[136],"scenarios.":[138],"In":[139],"paper,":[141],"propose":[143],"Visual":[144],"Question":[145],"Localized-Answering":[146],"Robotic":[148],"Surgery":[149],"(Surgical-VQLA)":[150],"localize":[152],"specific":[154,263],"area":[156,264],"during":[157],"prediction.":[160],"To":[161,190],"deal":[162],"modalities,":[169],"design":[171],"gated":[172],"vision-language":[173],"embedding":[174,274],"(GVLE)":[175],"build":[177],"input":[178],"patches":[179],"Language":[182],"Vision":[183],"Transformer":[184],"(LViT)":[185],"predict":[187],"answer.":[189],"get":[191],"localization,":[192],"add":[194],"head":[197,203],"parallel":[199],"prediction":[202],"LViT.":[206],"We":[207,228],"also":[208],"integrate":[209],"generalized":[210],"intersection":[211],"over":[212,280],"union":[213],"(GIoU)":[214],"loss":[215],"boost":[217],"localization":[218],"performance":[219,279],"by":[220,234,276],"preserving":[221],"accuracy":[223],"model.":[227],"annotate":[229],"two":[230],"VQLA":[233],"utilizing":[235],"publicly":[236],"available":[237],"EndoVis-17":[241],"18":[243],"MICCAI":[246],"challenges.":[247],"Our":[248],"validation":[249],"results":[250],"suggest":[251],"that":[252],"Surgical-VQLA":[253],"can":[254],"better":[255],"understand":[256],"related":[265],"question-answering.":[268],"GVLE":[269],"presents":[270],"efficient":[272],"language-vision":[273],"technique":[275],"showing":[277],"superior":[278],"benchmarks.":[283]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}