{"id":"https://openalex.org/W7160257380","doi":"https://doi.org/10.1109/wacv61042.2026.00162","title":"Multimodal Medical Image Binding via Shared Text Embeddings","display_name":"Multimodal Medical Image Binding via Shared Text Embeddings","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160257380","doi":"https://doi.org/10.1109/wacv61042.2026.00162"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00162","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00162","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","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/A5124219396","display_name":"Yunhao Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yunhao Liu","raw_affiliation_strings":["The Hong Kong Polytechnic University,Department of Data Science and Artificial Intelligence,Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Department of Data Science and Artificial Intelligence,Hong Kong,China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109240337","display_name":"Suyang Xi","orcid":"https://orcid.org/0009-0004-8662-0354"},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suyang Xi","raw_affiliation_strings":["Emory University,Atlanta,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Emory University,Atlanta,USA","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135305750","display_name":"Shiqi Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I165488957","display_name":"Lingnan University","ror":"https://ror.org/0563pg902","country_code":"HK","type":"education","lineage":["https://openalex.org/I165488957"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Shiqi Liu","raw_affiliation_strings":["Hong Kong Lingnan University,Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong Lingnan University,Hong Kong,China","institution_ids":["https://openalex.org/I165488957"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002921938","display_name":"Hong Ding","orcid":"https://orcid.org/0000-0003-4422-9248"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hong Ding","raw_affiliation_strings":["University of Illinois Chicago,Chicago,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Chicago,Chicago,USA","institution_ids":["https://openalex.org/I39422238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135399997","display_name":"Chicheng Jin","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chicheng Jin","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135314766","display_name":"Chong Zhong","orcid":null},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chong Zhong","raw_affiliation_strings":["The Hong Kong Polytechnic University,Department of Data Science and Artificial Intelligence,Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Department of Data Science and Artificial Intelligence,Hong Kong,China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135362706","display_name":"Junjun He","orcid":null},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junjun He","raw_affiliation_strings":["Shanghai AI Laboratory,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory,China","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128652875","display_name":"Catherine C. Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Catherine C. Liu","raw_affiliation_strings":["The Hong Kong Polytechnic University,Department of Data Science and Artificial Intelligence,Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Department of Data Science and Artificial Intelligence,Hong Kong,China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101725213","display_name":"Ye Shen","orcid":"https://orcid.org/0000-0002-6833-765X"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiqing Shen","raw_affiliation_strings":["Johns Hopkins University,Baltimore,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Baltimore,USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":21.6816,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.989501,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1610","last_page":"1620"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.33390000462532043,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.33390000462532043,"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/T10388","display_name":"Advanced Steganography and Watermarking Techniques","score":0.06199999898672104,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.05290000140666962,"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/image","display_name":"Image (mathematics)","score":0.4756999909877777},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.32109999656677246},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.3073999881744385},{"id":"https://openalex.org/keywords/medical-imaging","display_name":"Medical imaging","score":0.299699991941452},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.2870999872684479}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6248999834060669},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5295000076293945},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4756999909877777},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4041000008583069},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.32109999656677246},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3073999881744385},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.299699991941452},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.29190000891685486},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00162","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00162","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321920","display_name":"Innovation and Technology Commission","ror":"https://ror.org/04vf9tr09"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1969496006","https://openalex.org/W2001193723","https://openalex.org/W2033973189","https://openalex.org/W2052295501","https://openalex.org/W2096380898","https://openalex.org/W2195401421","https://openalex.org/W2530952499","https://openalex.org/W2547569497","https://openalex.org/W2806857275","https://openalex.org/W2888456553","https://openalex.org/W2963466845","https://openalex.org/W2963716420","https://openalex.org/W2970242971","https://openalex.org/W2997006708","https://openalex.org/W3005931683","https://openalex.org/W3027572331","https://openalex.org/W3038704997","https://openalex.org/W3105966348","https://openalex.org/W3201906559","https://openalex.org/W4281640569","https://openalex.org/W4311027007","https://openalex.org/W4312671791","https://openalex.org/W4312956471","https://openalex.org/W4382460199","https://openalex.org/W4385948838","https://openalex.org/W4386071707","https://openalex.org/W4386075997","https://openalex.org/W4386076084","https://openalex.org/W4388065766","https://openalex.org/W4390872745","https://openalex.org/W4390872786","https://openalex.org/W4390873744","https://openalex.org/W4402753899","https://openalex.org/W4402772638","https://openalex.org/W4403015917","https://openalex.org/W4403619348","https://openalex.org/W4405669265","https://openalex.org/W4408733250","https://openalex.org/W4409263233","https://openalex.org/W4409363896","https://openalex.org/W7133220107"],"related_works":[],"abstract_inverted_index":{"Medical":[0,77],"image":[1,111],"analysis":[2],"increasingly":[3],"relies":[4],"on":[5,115,198,206],"the":[6,72,116,178,192,195],"integration":[7],"of":[8,91,180,194],"multiple":[9,92,207],"imaging":[10,94],"modalities":[11,33,95],"to":[12,65,140,191,228],"capture":[13],"complementary":[14],"anatomical":[15],"and":[16,23,46,186,203,223],"functional":[17],"information,":[18],"enabling":[19],"more":[20],"accurate":[21],"diagnosis":[22],"treatment":[24],"planning.":[25],"Achieving":[26],"aligned":[27],"feature":[28],"representations":[29],"across":[30],"these":[31,156],"diverse":[32],"is":[34,63,172,183],"therefore":[35],"important":[36],"for":[37,241],"effective":[38],"multimodal":[39],"analysis.":[40,243],"While":[41],"contrastive":[42],"language-image":[43],"pre-training":[44,85],"(CLIP)":[45],"its":[47,229],"variant":[48],"have":[49],"enabled":[50],"image-text":[51,131,151],"alignments,":[52],"they":[53],"require":[54],"explicitly":[55],"paired":[56,105],"data":[57,106],"between":[58,107],"arbitrary":[59],"two":[60,109],"modalities,":[61,139],"which":[62,133,177],"difficult":[64],"acquire":[66],"in":[67,176,219,237],"medical":[68,93,110,138,242],"contexts.":[69],"To":[70],"address":[71],"gap,":[73],"we":[74,154],"present":[75],"Multimodal":[76],"Image":[78],"Binding":[79],"with":[80,124],"Text":[81],"(M3Bind),":[82],"a":[83,97,161,165,173],"novel":[84],"framework":[86,175],"that":[87,118,211],"enables":[88],"seamless":[89],"alignment":[90,240],"through":[96],"shared":[98,166],"text":[99,144,158,167],"representation":[100],"space":[101,146],"without":[102],"requiring":[103],"explicit":[104],"any":[108],"modalities.":[112],"Specifically,":[113],"based":[114],"insight":[117],"different":[119,137],"images":[120,205],"can":[121,187],"naturally":[122],"bind":[123],"text,":[125],"M3Bind":[126,171,212],"first":[127],"fine-tunes":[128],"pre-trained":[129],"CLIP-like":[130,181,230],"models,":[132],"are":[134],"derived":[135],"from":[136],"align":[141],"their":[142,149],"modality-specific":[143,157],"embedding":[145,168],"while":[147],"preserving":[148],"original":[150],"alignments.":[152],"Subsequently,":[153],"distill":[155],"encoders":[159],"into":[160],"unified":[162],"model,":[163],"creating":[164],"space.":[169],"Notably,":[170],"flexible":[174],"selection":[179],"models":[182],"not":[184],"fixed":[185],"be":[188],"adapted":[189],"according":[190],"requirements":[193],"task.":[196],"Experiments":[197],"X-ray,":[199],"CT,":[200],"retina,":[201],"ECG,":[202],"pathological":[204],"downstream":[208],"tasks":[209,226],"demonstrate":[210],"achieves":[213],"competitive":[214],"or":[215],"even":[216],"superior":[217],"performance":[218],"zero-shot,":[220],"few-shot":[221],"classification":[222],"cross-modal":[224],"retrieval":[225],"compared":[227],"counterparts.":[231],"These":[232],"results":[233],"validate":[234],"M3Bind's":[235],"effectiveness":[236],"achieving":[238],"cross-image-modal":[239]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-05-06T00:00:00"}