{"id":"https://openalex.org/W7126078465","doi":"https://doi.org/10.1109/bibm66473.2025.11356041","title":"Multi-Scale Visual Prompting for Robust Visual Question Answering in Medical Imaging","display_name":"Multi-Scale Visual Prompting for Robust Visual Question Answering in Medical Imaging","publication_year":2025,"publication_date":"2025-12-15","ids":{"openalex":"https://openalex.org/W7126078465","doi":"https://doi.org/10.1109/bibm66473.2025.11356041"},"language":null,"primary_location":{"id":"doi:10.1109/bibm66473.2025.11356041","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm66473.2025.11356041","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","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/A5101875456","display_name":"Yang Ma","orcid":"https://orcid.org/0000-0003-3719-3195"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Yang Ma","raw_affiliation_strings":["School of Computer Science, The University of Sydney,Sydney,Australia"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, The University of Sydney,Sydney,Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068623236","display_name":"Dongang Wang","orcid":"https://orcid.org/0000-0001-5805-0244"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Dongang Wang","raw_affiliation_strings":["Brain and Mind Centre, The University of Sydney,Sydney,Australia"],"affiliations":[{"raw_affiliation_string":"Brain and Mind Centre, The University of Sydney,Sydney,Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124236704","display_name":"Peilin Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Peilin Liu","raw_affiliation_strings":["School of Mathematics, The University of Sydney,Sydney,Australia"],"affiliations":[{"raw_affiliation_string":"School of Mathematics, The University of Sydney,Sydney,Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124183450","display_name":"Michael Barnett","orcid":null},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Michael Barnett","raw_affiliation_strings":["Brain and Mind Centre, The University of Sydney,Sydney,Australia"],"affiliations":[{"raw_affiliation_string":"Brain and Mind Centre, The University of Sydney,Sydney,Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124272001","display_name":"Dingxuan Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Dingxuan Zhou","raw_affiliation_strings":["School of Mathematics, The University of Sydney,Sydney,Australia"],"affiliations":[{"raw_affiliation_string":"School of Mathematics, The University of Sydney,Sydney,Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101923761","display_name":"Weidong Cai","orcid":"https://orcid.org/0000-0001-9581-7774"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Weidong Cai","raw_affiliation_strings":["School of Computer Science, The University of Sydney,Sydney,Australia"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, The University of Sydney,Sydney,Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100385862","display_name":"Chenyu Wang","orcid":"https://orcid.org/0000-0001-7135-7662"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Chenyu Wang","raw_affiliation_strings":["School of Computer Science, The University of Sydney,Sydney,Australia"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, The University of Sydney,Sydney,Australia","institution_ids":["https://openalex.org/I129604602"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5101875456"],"corresponding_institution_ids":["https://openalex.org/I129604602"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.72414171,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3921","last_page":"3925"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.987500011920929,"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":0.987500011920929,"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":0.0035000001080334187,"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":0.0027000000700354576,"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/interpretability","display_name":"Interpretability","score":0.8693000078201294},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6481000185012817},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6148999929428101},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5946999788284302},{"id":"https://openalex.org/keywords/medical-imaging","display_name":"Medical imaging","score":0.5745999813079834},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.5309000015258789},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5253000259399414},{"id":"https://openalex.org/keywords/spatial-contextual-awareness","display_name":"Spatial contextual awareness","score":0.37299999594688416}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8693000078201294},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.732200026512146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6672000288963318},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6481000185012817},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6148999929428101},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5946999788284302},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.5745999813079834},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.5309000015258789},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5253000259399414},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43050000071525574},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.37299999594688416},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.3440999984741211},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.33169999718666077},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32820001244544983},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3149999976158142},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.3077999949455261},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.28029999136924744},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C3019150057","wikidata":"https://www.wikidata.org/wiki/Q92779279","display_name":"Medical information","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.2578999996185303}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm66473.2025.11356041","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm66473.2025.11356041","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7515286207199097,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2901466771","https://openalex.org/W3138516171","https://openalex.org/W3165058054","https://openalex.org/W3203255640","https://openalex.org/W4294691359","https://openalex.org/W4295917908","https://openalex.org/W4304092130","https://openalex.org/W4318263203","https://openalex.org/W4386352883","https://openalex.org/W4386882992","https://openalex.org/W4387211791","https://openalex.org/W4409048398","https://openalex.org/W4414349717"],"related_works":[],"abstract_inverted_index":{"Medical":[0],"imaging":[1],"inherently":[2],"exhibits":[3],"multi-scale":[4,118],"characteristics,":[5],"encompassing":[6],"both":[7,125],"global":[8,32],"anatomical":[9],"structures":[10],"and":[11,68,113,120,127,151],"localized":[12],"pathological":[13],"details.":[14],"However,":[15],"most":[16],"existing":[17],"multimodal":[18,155],"large":[19],"language":[20],"models":[21],"(MLLMs)":[22],"for":[23,148],"medical":[24,129,156],"visual":[25,119,146],"question":[26],"answering":[27],"(VQA)":[28],"rely":[29],"mainly":[30],"on":[31,102],"features,":[33],"limiting":[34],"fine-grained":[35],"reasoning":[36,153],"across":[37,57],"spatial":[38,80],"levels.":[39],"To":[40],"address":[41],"this,":[42],"we":[43],"propose":[44],"MSFormer":[45,60,115,135],"(Multi-Scale":[46],"Transformer),":[47],"a":[48,65,72],"vision-language":[49],"architecture":[50],"that":[51,134],"dynamically":[52],"integrates":[53],"hierarchical":[54],"image":[55],"features":[56,96],"multiple":[58],"scales.":[59],"extracts":[61],"multi-resolution":[62],"embeddings":[63],"via":[64],"vision":[66],"backbone":[67],"refines":[69],"them":[70],"using":[71],"Multi-Scale":[73,84],"Positional":[74],"Embedding":[75],"(MSPE)":[76],"module":[77],"to":[78,92,95,105],"maintain":[79],"alignment.":[81],"Its":[82],"core":[83],"Grouped":[85],"Attention":[86],"(MSGA)":[87],"mechanism":[88],"enables":[89],"learnable":[90],"queries":[91],"jointly":[93],"attend":[94],"from":[97],"different":[98],"scales,":[99],"adaptively":[100],"focusing":[101],"context":[103],"relevant":[104],"each":[106],"question.":[107],"Through":[108],"contrastive":[109],"pretraining,":[110],"instruction":[111],"tuning,":[112],"fine-tuning,":[114],"effectively":[116],"aligns":[117],"textual":[121],"representations,":[122],"substantially":[123],"improving":[124],"open-":[126],"closed-ended":[128],"VQA.":[130],"Extensive":[131],"experiments":[132],"show":[133],"consistently":[136],"surpasses":[137],"prior":[138],"state-of-the-art":[139],"models,":[140],"underscoring":[141],"the":[142],"value":[143],"of":[144],"scale-aware":[145],"prompting":[147],"enhanced":[149],"interpretability":[150],"clinical":[152],"in":[154],"AI.":[157]},"counts_by_year":[],"updated_date":"2026-02-01T03:34:12.195049","created_date":"2026-01-30T00:00:00"}