{"id":"https://openalex.org/W4304092130","doi":"https://doi.org/10.1145/3503161.3548122","title":"Caption-Aware Medical VQA via Semantic Focusing and Progressive Cross-Modality Comprehension","display_name":"Caption-Aware Medical VQA via Semantic Focusing and Progressive Cross-Modality Comprehension","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304092130","doi":"https://doi.org/10.1145/3503161.3548122"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548122","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548122","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","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/A5085073312","display_name":"Fuze Cong","orcid":"https://orcid.org/0000-0002-0947-2392"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuze Cong","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011919230","display_name":"Shibiao Xu","orcid":"https://orcid.org/0000-0003-4037-9900"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shibiao Xu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100675165","display_name":"Li Guo","orcid":"https://orcid.org/0000-0002-9723-3294"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Guo","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088568072","display_name":"Yinbing Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinbing Tian","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":2.7738,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.93643801,"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":"3569","last_page":"3577"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9889000058174133,"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":0.9768999814987183,"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/closed-captioning","display_name":"Closed captioning","score":0.935904860496521},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8057974576950073},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6699180006980896},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6017885208129883},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5763375163078308},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.5611168742179871},{"id":"https://openalex.org/keywords/medical-diagnosis","display_name":"Medical diagnosis","score":0.5322425365447998},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5236113667488098},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.5199066996574402},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.4973588287830353},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.47302982211112976},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4445365071296692},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3739238381385803}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.935904860496521},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8057974576950073},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6699180006980896},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6017885208129883},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5763375163078308},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.5611168742179871},{"id":"https://openalex.org/C534262118","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Medical diagnosis","level":2,"score":0.5322425365447998},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5236113667488098},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.5199066996574402},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.4973588287830353},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.47302982211112976},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4445365071296692},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3739238381385803},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3548122","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548122","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6499999761581421,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G4189301930","display_name":null,"funder_award_id":"2019YFB1406500","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1641498739","https://openalex.org/W2064675550","https://openalex.org/W2108598243","https://openalex.org/W2157331557","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2770165365","https://openalex.org/W2895902247","https://openalex.org/W2901466771","https://openalex.org/W2911489562","https://openalex.org/W2913340405","https://openalex.org/W2963150162","https://openalex.org/W2963954913","https://openalex.org/W2970971581","https://openalex.org/W2979525559","https://openalex.org/W2981694290","https://openalex.org/W2997591391","https://openalex.org/W3011651912","https://openalex.org/W3011797839","https://openalex.org/W3015965768","https://openalex.org/W3083376569","https://openalex.org/W3091588028","https://openalex.org/W3094950914","https://openalex.org/W3095473065","https://openalex.org/W3098325931","https://openalex.org/W3165058054","https://openalex.org/W3203247393","https://openalex.org/W3203255640","https://openalex.org/W4212774754","https://openalex.org/W4283723743","https://openalex.org/W4295312788"],"related_works":["https://openalex.org/W4288115461","https://openalex.org/W2951590222","https://openalex.org/W2745461083","https://openalex.org/W2295744208","https://openalex.org/W2972206754","https://openalex.org/W4386380747","https://openalex.org/W2952322859","https://openalex.org/W207304934","https://openalex.org/W4385572364","https://openalex.org/W4385805088"],"abstract_inverted_index":{"Medical":[0],"Visual":[1],"Question":[2],"Answering":[3],"as":[4],"a":[5,66,162,184],"specific-domain":[6],"task":[7],"requires":[8],"substantive":[9],"prior":[10],"knowledge":[11],"of":[12,21,28,76,84,100,198],"medicine.":[13],"However,":[14],"deep":[15],"learning":[16],"techniques":[17],"encounter":[18],"severe":[19],"problems":[20],"limited":[22],"supervision":[23],"due":[24],"to":[25,37,48,58,112,127,144,151,168,203],"the":[26,39,53,73,89,116,129,141,147,153,157,173,196,199,204],"scarcity":[27],"well-annotated":[29],"large-scale":[30],"medical":[31,85,90,193],"VQA":[32,68],"datasets.":[33],"As":[34],"an":[35],"alternative":[36],"facing":[38],"data":[40],"limitation":[41],"problem,":[42],"image":[43,77,121,134],"captioning":[44,135],"can":[45,71],"be":[46],"introduced":[47],"learn":[49],"summary":[50,74],"information":[51,75],"about":[52],"picture,":[54],"which":[55],"is":[56,125],"beneficial":[57],"question":[59,91,175],"answering.":[60],"To":[61],"this":[62],"end,":[63],"we":[64,160],"propose":[65,161],"caption-aware":[67],"method":[69,98],"that":[70],"read":[72],"content":[78,109,155],"and":[79,87,107,114,139,176,188],"clinic":[80],"diagnoses":[81],"from":[82,133],"plenty":[83],"images":[86],"answer":[88],"with":[92],"richer":[93],"multimodality":[94],"features.":[95],"The":[96],"proposed":[97,200],"consists":[99],"two":[101],"novel":[102],"components":[103],"emphasizing":[104],"semantic":[105,108,117,154],"locations":[106,118],"respectively.":[110],"Firstly,":[111],"extract":[113],"leverage":[115],"implied":[119],"in":[120,156,183],"captioning,":[122],"similarity":[123],"analysis":[124],"designed":[126],"summarize":[128],"attention":[130,182],"maps":[131],"generated":[132,158],"by":[136,179],"their":[137],"relevance":[138],"guide":[140],"visual":[142],"model":[143],"focus":[145],"on":[146,191],"semantic-rich":[148],"regions.":[149],"Besides,":[150],"combine":[152],"captions,":[159],"Progressive":[163],"Compact":[164],"Bilinear":[165],"Interactions":[166],"structure":[167],"achieve":[169],"cross-modality":[170],"comprehension":[171],"over":[172],"image,":[174],"caption":[177],"features":[178],"performing":[180],"bilinear":[181],"gradual":[185],"manner.":[186],"Qualitative":[187],"quantitative":[189],"experiments":[190],"various":[192],"datasets":[194],"exhibit":[195],"superiority":[197],"approach":[201],"compared":[202],"state-of-the-art":[205],"methods.":[206]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":7}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}