{"id":"https://openalex.org/W4406261752","doi":"https://doi.org/10.1109/bibm62325.2024.10821918","title":"Leveraging Convolutional Models as Backbone for Medical Visual Question Answering","display_name":"Leveraging Convolutional Models as Backbone for Medical Visual Question Answering","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406261752","doi":"https://doi.org/10.1109/bibm62325.2024.10821918"},"language":"en","primary_location":{"id":"doi:10.1109/bibm62325.2024.10821918","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm62325.2024.10821918","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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/A5100349464","display_name":"Lei Liu","orcid":"https://orcid.org/0000-0001-5063-2864"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lei Liu","raw_affiliation_strings":["College of Computer Science Inner Mongolia University,National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian,Hohhot,China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science Inner Mongolia University,National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100830970","display_name":"Xiangdong Su","orcid":null},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangdong Su","raw_affiliation_strings":["College of Computer Science Inner Mongolia University,National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian,Hohhot,China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science Inner Mongolia University,National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076174513","display_name":"Guanglai Gao","orcid":"https://orcid.org/0009-0005-5513-1192"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanglai Gao","raw_affiliation_strings":["College of Computer Science Inner Mongolia University,National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian,Hohhot,China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science Inner Mongolia University,National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100349464"],"corresponding_institution_ids":["https://openalex.org/I2722730"],"apc_list":null,"apc_paid":null,"fwci":0.2624,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.58567781,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"2177","last_page":"2182"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9772999882698059,"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":0.9772999882698059,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9531000256538391,"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":0.7934430837631226},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7528113126754761},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.46052441000938416},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3761756718158722},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3281756639480591}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7934430837631226},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7528113126754761},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.46052441000938416},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3761756718158722},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3281756639480591}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm62325.2024.10821918","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm62325.2024.10821918","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320241","display_name":"Academy of Medical Sciences","ror":"https://ror.org/00c489v88"},{"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":34,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2883780447","https://openalex.org/W2901466771","https://openalex.org/W2963125010","https://openalex.org/W2963150162","https://openalex.org/W2963163009","https://openalex.org/W2963446712","https://openalex.org/W2963954913","https://openalex.org/W2979525559","https://openalex.org/W3034429256","https://openalex.org/W3035414587","https://openalex.org/W3094950914","https://openalex.org/W3164670515","https://openalex.org/W3165058054","https://openalex.org/W3203255640","https://openalex.org/W3203635737","https://openalex.org/W4246193833","https://openalex.org/W4283075937","https://openalex.org/W4283258232","https://openalex.org/W4284667763","https://openalex.org/W4295917908","https://openalex.org/W4312715257","https://openalex.org/W4313452817","https://openalex.org/W4320036918","https://openalex.org/W4385245566","https://openalex.org/W6637373629","https://openalex.org/W6638667902","https://openalex.org/W6737664043","https://openalex.org/W6752083267","https://openalex.org/W6760184523","https://openalex.org/W6775041699","https://openalex.org/W6793164127"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Convolutional":[0],"neural":[1],"networks":[2],"(CNNs)":[3],"have":[4],"made":[5],"significant":[6],"contributions":[7],"to":[8,66,120,185],"computer":[9],"vision":[10],"and":[11,19,51,85,107,123,204],"offer":[12],"the":[13,27,54,113,117,157,161,174,201,207],"advantages":[14],"of":[15,176,198],"higher":[16],"training":[17],"efficiency":[18],"lower":[20],"model":[21,130,150,169],"complexity.":[22],"However,":[23],"their":[24],"application":[25],"as":[26,53],"backbone":[28],"in":[29,73],"medical":[30],"visual":[31,77,122],"question":[32,78],"answering":[33,79],"(MedVQA)":[34],"remains":[35],"an":[36,195],"open":[37],"question.":[38],"To":[39,89,127],"address":[40],"this":[41,91],"issue,":[42],"we":[43,93,111,132,193],"employ":[44],"popular":[45],"convolutional":[46,182],"models,":[47,183],"including":[48],"ResNet,":[49],"DenseNet,":[50],"ShuffleNet,":[52],"foundation":[55],"for":[56,76,141,163],"MedVQA,":[57],"achieving":[58],"outstanding":[59,186],"performance.":[60,170],"Different":[61],"backbones":[62],"can":[63],"be":[64],"tailored":[65],"diverse":[67],"real-world":[68],"scenarios.":[69],"The":[70],"central":[71],"challenge":[72],"utilizing":[74],"CNNs":[75],"is":[80],"effectively":[81],"managing":[82],"textual":[83,124],"features":[84],"integrating":[86],"multi-modal":[87,136],"information.":[88],"overcome":[90],"challenge,":[92],"design":[94],"a":[95,134],"novel":[96,135],"global":[97],"interaction":[98],"attention":[99],"(GIA)":[100],"that":[101],"facilitates":[102],"efficient":[103],"interactions":[104],"between":[105],"text":[106],"image":[108],"features.":[109],"Additionally,":[110],"utilize":[112],"dot":[114],"product":[115],"before":[116],"classifier":[118],"output":[119],"enhance":[121,129],"modal":[125],"fusions.":[126],"further":[128,167],"performance,":[131],"propose":[133],"hidden":[137,147],"mixup":[138],"(MHidMix)":[139],"technique":[140,155],"data":[142,153],"augmentation,":[143],"which":[144],"involves":[145],"interpolating":[146],"states":[148],"during":[149],"training.":[151],"This":[152],"augmentation":[154],"smoothes":[156],"decision":[158],"boundary":[159],"without":[160],"need":[162],"complex":[164],"sample":[165],"selection,":[166],"improving":[168],"Experimental":[171],"results":[172],"underscore":[173],"versatility":[175],"our":[177],"proposed":[178],"framework":[179],"across":[180],"various":[181],"leading":[184],"performance":[187],"on":[188,200,206],"four":[189],"MedVQA":[190],"datasets.":[191],"Notably,":[192],"achieved":[194],"accuracy":[196],"increase":[197],"9.4%":[199],"PathVQA":[202],"dataset":[203],"4.5%":[205],"OVQA":[208],"dataset.":[209]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}