{"id":"https://openalex.org/W4387789891","doi":"https://doi.org/10.1109/tmm.2023.3325965","title":"Multi-Task Paired Masking With Alignment Modeling for Medical Vision-Language Pre-Training","display_name":"Multi-Task Paired Masking With Alignment Modeling for Medical Vision-Language Pre-Training","publication_year":2023,"publication_date":"2023-10-19","ids":{"openalex":"https://openalex.org/W4387789891","doi":"https://doi.org/10.1109/tmm.2023.3325965"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2023.3325965","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3325965","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Transactions on Multimedia","raw_type":"journal-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/A5100365746","display_name":"Ke Zhang","orcid":"https://orcid.org/0000-0002-9855-003X"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ke Zhang","raw_affiliation_strings":["Key Laboratory of Complex Systems Modeling and Simulation, School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-9855-003X","affiliations":[{"raw_affiliation_string":"Key Laboratory of Complex Systems Modeling and Simulation, School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029741928","display_name":"Yan Yang","orcid":"https://orcid.org/0000-0001-5598-1692"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Yang","raw_affiliation_strings":["Key Laboratory of Complex Systems Modeling and Simulation, School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-5598-1692","affiliations":[{"raw_affiliation_string":"Key Laboratory of Complex Systems Modeling and Simulation, School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050817770","display_name":"Jun Yu","orcid":"https://orcid.org/0000-0003-1922-7283"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Yu","raw_affiliation_strings":["Key Laboratory of Complex Systems Modeling and Simulation, School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1922-7283","affiliations":[{"raw_affiliation_string":"Key Laboratory of Complex Systems Modeling and Simulation, School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045151493","display_name":"Hanliang Jiang","orcid":"https://orcid.org/0000-0003-0902-882X"},"institutions":[{"id":"https://openalex.org/I2802390878","display_name":"Sir Run Run Shaw Hospital","ror":"https://ror.org/00ka6rp58","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I2802390878"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanliang Jiang","raw_affiliation_strings":["Regional Medical Center for National Institute of Respiratory Diseases, Sir Run Run Shaw Hospital, College of Medicine, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-0902-882X","affiliations":[{"raw_affiliation_string":"Regional Medical Center for National Institute of Respiratory Diseases, Sir Run Run Shaw Hospital, College of Medicine, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I2802390878","https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100728569","display_name":"Jianping Fan","orcid":"https://orcid.org/0000-0003-2290-1785"},"institutions":[{"id":"https://openalex.org/I4210156165","display_name":"Lenovo (China)","ror":"https://ror.org/04srd9d93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156165"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianping Fan","raw_affiliation_strings":["AI Lab at Lenovo Research, China"],"raw_orcid":"https://orcid.org/0000-0003-2290-1785","affiliations":[{"raw_affiliation_string":"AI Lab at Lenovo Research, China","institution_ids":["https://openalex.org/I4210156165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028597017","display_name":"Qingming Huang","orcid":"https://orcid.org/0000-0001-7542-296X"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingming Huang","raw_affiliation_strings":["School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7542-296X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003662438","display_name":"Weidong Han","orcid":"https://orcid.org/0000-0001-7227-3671"},"institutions":[{"id":"https://openalex.org/I135237710","display_name":"Zhejiang Normal University","ror":"https://ror.org/01vevwk45","country_code":"CN","type":"education","lineage":["https://openalex.org/I135237710"]},{"id":"https://openalex.org/I2802390878","display_name":"Sir Run Run Shaw Hospital","ror":"https://ror.org/00ka6rp58","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I2802390878"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weidong Han","raw_affiliation_strings":["Department of Medical Oncology, Sir Run Run Shaw Hospital, College of Medicine, Zhejiang University in Hangzhou, Hangzhou, China","College of Mathematical Medicine, Zhejiang Normal University in Jinhua, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0001-7227-3671","affiliations":[{"raw_affiliation_string":"Department of Medical Oncology, Sir Run Run Shaw Hospital, College of Medicine, Zhejiang University in Hangzhou, Hangzhou, China","institution_ids":["https://openalex.org/I2802390878","https://openalex.org/I76130692"]},{"raw_affiliation_string":"College of Mathematical Medicine, Zhejiang Normal University in Jinhua, Zhejiang, China","institution_ids":["https://openalex.org/I135237710"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100365746"],"corresponding_institution_ids":["https://openalex.org/I50760025"],"apc_list":null,"apc_paid":null,"fwci":4.8276,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.9643575,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"26","issue":null,"first_page":"4706","last_page":"4721"},"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":0.9961000084877014,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9868000149726868,"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/computer-science","display_name":"Computer science","score":0.8670731782913208},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6563758850097656},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.634666919708252},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5909557938575745},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.5223016738891602},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4902072548866272},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.47012412548065186},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.4301174283027649},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.40206238627433777},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35133975744247437},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34335100650787354}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8670731782913208},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6563758850097656},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.634666919708252},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5909557938575745},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.5223016738891602},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4902072548866272},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.47012412548065186},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4301174283027649},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40206238627433777},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35133975744247437},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34335100650787354},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2023.3325965","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3325965","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G6151690139","display_name":null,"funder_award_id":"62020106007","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6570941292","display_name":null,"funder_award_id":"62125201","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7252885093","display_name":null,"funder_award_id":"62176230","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W1889081078","https://openalex.org/W1895577753","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2152772232","https://openalex.org/W2525778437","https://openalex.org/W2526377930","https://openalex.org/W2563032747","https://openalex.org/W2575842049","https://openalex.org/W2617576589","https://openalex.org/W2786273134","https://openalex.org/W2896457183","https://openalex.org/W2897980926","https://openalex.org/W2901466771","https://openalex.org/W2903721568","https://openalex.org/W2914203365","https://openalex.org/W2962858109","https://openalex.org/W2962974137","https://openalex.org/W2963084599","https://openalex.org/W2963466845","https://openalex.org/W2963954913","https://openalex.org/W2979525559","https://openalex.org/W2995225687","https://openalex.org/W3094950914","https://openalex.org/W3104609094","https://openalex.org/W3108512475","https://openalex.org/W3164670515","https://openalex.org/W3173688449","https://openalex.org/W3174148569","https://openalex.org/W3181252431","https://openalex.org/W3198570286","https://openalex.org/W3198817488","https://openalex.org/W3201906559","https://openalex.org/W3203255640","https://openalex.org/W3212203927","https://openalex.org/W3213233983","https://openalex.org/W3213610319","https://openalex.org/W4205403018","https://openalex.org/W4229027955","https://openalex.org/W4283258232","https://openalex.org/W4283821415","https://openalex.org/W4285108627","https://openalex.org/W4285531589","https://openalex.org/W4295917908","https://openalex.org/W4312533035","https://openalex.org/W4313156423","https://openalex.org/W4322718191","https://openalex.org/W4375802394","https://openalex.org/W4385245566","https://openalex.org/W4385573131","https://openalex.org/W4390872699","https://openalex.org/W6639432524","https://openalex.org/W6678262379","https://openalex.org/W6682631176","https://openalex.org/W6727690538","https://openalex.org/W6736057607","https://openalex.org/W6751711410","https://openalex.org/W6752083267","https://openalex.org/W6757817989","https://openalex.org/W6775383885","https://openalex.org/W6784185929","https://openalex.org/W6791353385","https://openalex.org/W6845921028","https://openalex.org/W6846055702","https://openalex.org/W6849714168","https://openalex.org/W6850625674"],"related_works":["https://openalex.org/W3000097931","https://openalex.org/W2354322770","https://openalex.org/W4237547500","https://openalex.org/W1570848052","https://openalex.org/W2373192430","https://openalex.org/W4239268388","https://openalex.org/W4243305035","https://openalex.org/W1537496349","https://openalex.org/W2379407973","https://openalex.org/W2350267540"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"the":[3,49,83,88,141,149],"growing":[4],"demand":[5],"for":[6],"medical":[7,33],"imaging":[8],"diagnosis":[9],"has":[10],"placed":[11],"a":[12,18,69,100,124],"significant":[13],"burden":[14],"on":[15,74],"radiologists.":[16],"As":[17],"solution,":[19],"Medical":[20],"Vision-Language":[21],"Pre-training":[22],"(Med-VLP)":[23],"methods":[24,46,155],"have":[25,47],"been":[26],"proposed":[27,150],"to":[28,81,93,109,130,135],"learn":[29],"universal":[30],"representations":[31,116,143],"from":[32],"images":[34],"and":[35,102,139,163],"reports,":[36],"benefiting":[37],"downstream":[38,158],"tasks":[39],"without":[40],"requiring":[41],"fine-grained":[42],"annotations.":[43],"However,":[44],"existing":[45],"overlooked":[48],"importance":[50],"of":[51],"cross-modal":[52,61,84,97],"alignment":[53,85],"in":[54,59,113,156],"joint":[55,89],"image-text":[56,90],"reconstruction,":[57],"resulting":[58],"insufficient":[60],"interaction.":[62],"To":[63],"address":[64],"this":[65],"limitation,":[66],"we":[67,122],"propose":[68],"unified":[70,151],"Med-VLP":[71],"framework":[72,92],"based":[73],"Multi-task":[75],"Paired":[76],"Masking":[77],"with":[78,117],"Alignment":[79,104],"(MPMA)":[80],"integrate":[82,132],"task":[86],"into":[87],"reconstruction":[91,138],"achieve":[94],"more":[95],"comprehensive":[96],"interaction,":[98],"while":[99],"Global":[101],"Local":[103],"(GLA)":[105],"module":[106,129],"is":[107],"designed":[108],"assist":[110,136],"self-supervised":[111],"paradigm":[112],"obtaining":[114],"semantic":[115],"rich":[118],"domain":[119],"knowledge.":[120],"Furthermore,":[121],"introduce":[123],"Memory-Augmented":[125],"Cross-Modal":[126],"Fusion":[127],"(MA-CMF)":[128],"fully":[131],"visual":[133],"information":[134],"report":[137],"fuse":[140],"multi-modal":[142,164],"adequately.":[144],"Experimental":[145],"results":[146],"demonstrate":[147],"that":[148],"approach":[152],"outperforms":[153],"previous":[154],"all":[157],"tasks,":[159],"including":[160],"uni-modal,":[161],"cross-modal,":[162],"tasks.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":28},{"year":2024,"cited_by_count":11}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2023-10-20T00:00:00"}
