{"id":"https://openalex.org/W7117235659","doi":"https://doi.org/10.1109/jbhi.2025.3648589","title":"Parallel Multi-Attention and Gated Fusion for Visual Question Localized Answering in Surgical Scenes","display_name":"Parallel Multi-Attention and Gated Fusion for Visual Question Localized Answering in Surgical Scenes","publication_year":2025,"publication_date":"2025-12-25","ids":{"openalex":"https://openalex.org/W7117235659","doi":"https://doi.org/10.1109/jbhi.2025.3648589","pmid":"https://pubmed.ncbi.nlm.nih.gov/41447493"},"language":"en","primary_location":{"id":"doi:10.1109/jbhi.2025.3648589","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jbhi.2025.3648589","pdf_url":null,"source":{"id":"https://openalex.org/S2495854775","display_name":"IEEE Journal of Biomedical and Health Informatics","issn_l":"2168-2194","issn":["2168-2194","2168-2208"],"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 Journal of Biomedical and Health Informatics","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/A5121285949","display_name":"Zeyu Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210092944","display_name":"Dalian University","ror":"https://ror.org/00g2ypp58","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210092944"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeyu Wang","raw_affiliation_strings":["National and Local Joint Engineering Laboratory of Computer Aided Design, School of Software Engineering, Dalian University, Dalian, China"],"raw_orcid":"https://orcid.org/0009-0008-7794-2027","affiliations":[{"raw_affiliation_string":"National and Local Joint Engineering Laboratory of Computer Aided Design, School of Software Engineering, Dalian University, Dalian, China","institution_ids":["https://openalex.org/I4210092944"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121246241","display_name":"Ming Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156095","display_name":"Aero Engine Corporation of China (China)","ror":"https://ror.org/04pe7qe08","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156095"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Wang","raw_affiliation_strings":["BeiJing Aero-top Hi-tech Company, Ltd., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BeiJing Aero-top Hi-tech Company, Ltd., Beijing, China","institution_ids":["https://openalex.org/I4210156095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070755370","display_name":"Peixi Peng","orcid":"https://orcid.org/0000-0002-7427-8764"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peixi Peng","raw_affiliation_strings":["Institute of Medical Robotics, School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0003-3902-7606","affiliations":[{"raw_affiliation_string":"Institute of Medical Robotics, School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025524501","display_name":"Wanshu Fan","orcid":"https://orcid.org/0000-0001-6299-2795"},"institutions":[{"id":"https://openalex.org/I4210092944","display_name":"Dalian University","ror":"https://ror.org/00g2ypp58","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210092944"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanshu Fan","raw_affiliation_strings":["National and Local Joint Engineering Laboratory of Computer Aided Design, School of Software Engineering, Dalian University, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0001-6299-2795","affiliations":[{"raw_affiliation_string":"National and Local Joint Engineering Laboratory of Computer Aided Design, School of Software Engineering, Dalian University, Dalian, China","institution_ids":["https://openalex.org/I4210092944"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111253251","display_name":"Zhongbin Han","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145090","display_name":"Affiliated Zhongshan Hospital of Dalian University","ror":"https://ror.org/041ts2d40","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210145090"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongbin Han","raw_affiliation_strings":["Department of Surgery, Affiliated Zhongshan Hospital of Dalian University, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Surgery, Affiliated Zhongshan Hospital of Dalian University, Dalian, China","institution_ids":["https://openalex.org/I4210145090"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121277950","display_name":"Xin Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Yang","raw_affiliation_strings":["School of Computer Science and Technology, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0002-8046-722X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101777712","display_name":"Dongsheng Zhou","orcid":"https://orcid.org/0000-0003-0594-0117"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]},{"id":"https://openalex.org/I4210092944","display_name":"Dalian University","ror":"https://ror.org/00g2ypp58","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210092944"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongsheng Zhou","raw_affiliation_strings":["National and Local Joint Engineering Laboratory of Computer Aided Design, School of Software Engineering, Dalian University, School of Computer Science and Technology, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0003-3414-9623","affiliations":[{"raw_affiliation_string":"National and Local Joint Engineering Laboratory of Computer Aided Design, School of Software Engineering, Dalian University, School of Computer Science and Technology, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992","https://openalex.org/I4210092944"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.51198341,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"30","issue":"7","first_page":"5748","last_page":"5760"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9926000237464905,"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":0.9926000237464905,"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":0.00139999995008111,"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/T10028","display_name":"Topic Modeling","score":0.0010999999940395355,"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/task","display_name":"Task (project management)","score":0.5389999747276306},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5139999985694885},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.49059998989105225},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.478300005197525},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.45559999346733093},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.424699991941452},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3804999887943268},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.3765000104904175},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.3718999922275543}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8551999926567078},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7242000102996826},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5389999747276306},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5139999985694885},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.49059998989105225},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.478300005197525},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.45559999346733093},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.424699991941452},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3804999887943268},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.3765000104904175},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3718999922275543},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3628000020980835},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.34369999170303345},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.3407000005245209},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3395000100135803},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.3352000117301941},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32339999079704285},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.319599986076355},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.296099990606308},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.27630001306533813},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2662000060081482},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.2551000118255615},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.25209999084472656}],"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":"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":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D013514","descriptor_name":"Surgical Procedures, Operative","qualifier_ui":"Q000193","qualifier_name":"education","is_major_topic":true},{"descriptor_ui":"D013514","descriptor_name":"Surgical Procedures, Operative","qualifier_ui":"Q000193","qualifier_name":"education","is_major_topic":true},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/jbhi.2025.3648589","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jbhi.2025.3648589","pdf_url":null,"source":{"id":"https://openalex.org/S2495854775","display_name":"IEEE Journal of Biomedical and Health Informatics","issn_l":"2168-2194","issn":["2168-2194","2168-2208"],"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 Journal of Biomedical and Health Informatics","raw_type":"journal-article"},{"id":"pmid:41447493","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41447493","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 journal of biomedical and health informatics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8485033512115479,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G3299298849","display_name":null,"funder_award_id":"62502064","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4201996127","display_name":null,"funder_award_id":"D23006","funder_id":"https://openalex.org/F4320336698","funder_display_name":"Overseas Expertise Introduction Center for Discipline Innovation of Food Nutrition and Human Health (111 Center)"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320336698","display_name":"Overseas Expertise Introduction Center for Discipline Innovation of Food Nutrition and Human Health (111 Center)","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2747623286","https://openalex.org/W2752782242","https://openalex.org/W2962766617","https://openalex.org/W2963351448","https://openalex.org/W2963717374","https://openalex.org/W2964072591","https://openalex.org/W2966683369","https://openalex.org/W2990763144","https://openalex.org/W2998249728","https://openalex.org/W3094897602","https://openalex.org/W3094926883","https://openalex.org/W3096609285","https://openalex.org/W4210528082","https://openalex.org/W4221139382","https://openalex.org/W4249477935","https://openalex.org/W4283368635","https://openalex.org/W4289752563","https://openalex.org/W4383109126","https://openalex.org/W4385245566","https://openalex.org/W4387211845","https://openalex.org/W4387211892","https://openalex.org/W4387225896","https://openalex.org/W4391092744","https://openalex.org/W4391486420","https://openalex.org/W4399666152","https://openalex.org/W4401044130","https://openalex.org/W4402351525","https://openalex.org/W4402727538","https://openalex.org/W4403063149","https://openalex.org/W4407450063","https://openalex.org/W7131800420"],"related_works":[],"abstract_inverted_index":{"Surgical":[0],"Visual":[1],"Question":[2],"Localized":[3],"Answering":[4],"(Surgical-VQLA)":[5],"is":[6],"an":[7],"emerging":[8],"task":[9,31],"that":[10,66],"supports":[11],"surgical":[12],"education":[13],"by":[14,160,171],"generating":[15],"accurate":[16],"answers":[17],"and":[18,27,36,53,73,133,138,146,165,170,176,193],"localizing":[19],"relevant":[20],"anatomical":[21,94,195],"regions":[22],"based":[23],"on":[24,143,168,179],"visual":[25,88,111],"content":[26],"textual":[28],"queries.":[29],"This":[30],"requires":[32],"precise":[33,194],"spatial":[34,51,139],"reasoning":[35],"tight":[37],"semantic":[38,55,108],"alignment":[39],"across":[40],"modalities,":[41],"which":[42],"remain":[43],"challenging":[44],"for":[45],"current":[46],"models":[47],"due":[48],"to":[49,85,105,128],"limited":[50],"sensitivity":[52],"insufficient":[54],"integration.":[56],"Mitigating":[57],"these":[58],"limitations,":[59],"we":[60,77,121],"propose":[61],"EndoVisLoc,":[62,154],"a":[63,79,99,123],"dedicated":[64],"framework":[65],"enhances":[67],"visual-textual":[68],"interaction":[69],"through":[70],"structured":[71],"attention":[72],"gated":[74,114],"fusion.":[75,119],"Specifically,":[76],"design":[78],"Parallel":[80],"Multi":[81],"Attention":[82],"Module":[83,103],"(PMAM)":[84],"capture":[86],"different":[87],"features,":[89],"improving":[90],"the":[91,130,144,150,156,184],"perception":[92],"of":[93,153,187],"structures.":[95],"We":[96],"further":[97],"develop":[98],"Dynamic":[100],"Gated":[101],"Fusion":[102],"(DGFM)":[104],"adaptively":[106],"inject":[107],"priors":[109],"into":[110],"features":[112],"via":[113],"control,":[115],"facilitating":[116],"robust":[117],"cross-modal":[118],"Finally,":[120],"introduce":[122],"Hierarchical":[124],"Classifier":[125],"Head":[126],"(HCH)":[127],"refine":[129],"fused":[131],"representations":[132],"jointly":[134],"optimize":[135],"answer":[136,191],"prediction":[137],"localization.":[140,196],"Extensive":[141],"experiments":[142],"EndoVis-18-VQLA":[145,169],"EndoVis-17-VQLA":[147],"datasets":[148],"demonstrate":[149],"superior":[151],"performance":[152],"surpassing":[155],"state-of-the-art":[157],"OTAS":[158],"model":[159],"+5.72%":[161],"ACC,":[162,173],"+5.73%":[163],"F-score,":[164,175],"+1.82%":[166],"mIoU":[167,178],"+1.59%":[172],"+2.48%":[174],"+0.33%":[177],"EndoVis-17-VQLA.":[180],"These":[181],"results":[182],"confirm":[183],"consistent":[185],"advantage":[186],"EndoVisLoc":[188],"in":[189],"both":[190],"accuracy":[192]},"counts_by_year":[],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-12-25T00:00:00"}
