{"id":"https://openalex.org/W7166870991","doi":"https://doi.org/10.18653/v1/2026.acl-long.113","title":"MMCLIP: Cross-Modal Attention Masked Modelling for Medical Language-Image Pre-Training","display_name":"MMCLIP: Cross-Modal Attention Masked Modelling for Medical Language-Image Pre-Training","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166870991","doi":"https://doi.org/10.18653/v1/2026.acl-long.113"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.113","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.113","pdf_url":"https://aclanthology.org/2026.acl-long.113.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.113.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139807719","display_name":"Biao Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Biao Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139731089","display_name":"Yutong Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yutong Xie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139784961","display_name":"Zeyu Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeyu Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139836072","display_name":"Vu Minh Hieu Phan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vu Minh Hieu Phan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139747741","display_name":"Qi Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qi Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139850289","display_name":"Ling Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ling Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139735710","display_name":"Qi Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qi Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.8800873,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2440","last_page":"2455"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.4332999885082245,"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":0.4332999885082245,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.05550000071525574,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.044199999421834946,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.24050000309944153},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.23389999568462372},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.22689999639987946},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2249000072479248},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.21629999577999115}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.439300000667572},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3057999908924103},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2773999869823456},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.2485000044107437},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.24050000309944153},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.23389999568462372},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.22689999639987946},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2249000072479248},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.21629999577999115},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.21469999849796295}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.113","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.113","pdf_url":"https://aclanthology.org/2026.acl-long.113.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.113","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.113","pdf_url":"https://aclanthology.org/2026.acl-long.113.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7456895709037781,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166870991.pdf","grobid_xml":"https://content.openalex.org/works/W7166870991.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision-and-language":[0],"pretraining":[1],"(VLP)":[2],"in":[3,76,94],"medicine":[4],"leverages":[5],"contrastive":[6],"learning":[7],"on":[8,32],"image-text":[9],"pairs,":[10],"often":[11],"enhanced":[12],"with":[13,61],"masked":[14],"modeling.However,":[15],"existing":[16],"methods":[17],"face":[18],"two":[19,53],"challenges:":[20],"difficulty":[21],"reconstructing":[22,79],"key":[23,73],"pathological":[24],"features":[25,58],"due":[26],"to":[27,63],"limited":[28],"data,":[29],"and":[30,70,78,96],"reliance":[31],"either":[33],"paired":[34],"or":[35],"image-only":[36],"datasets":[37],"without":[38],"combining":[39],"both.To":[40],"address":[41],"this,":[42],"we":[43],"propose":[44],"MMCLIP":[45,84],"(Masked":[46],"Medical":[47],"Contrastive":[48],"Language-Image":[49],"Pre-training),":[50],"which":[51],"introduces":[52],"modules:":[54],"AttMIM,":[55],"masking":[56,72],"image":[57],"highly":[59],"correlated":[60],"text":[62,77],"improve":[64],"reconstruction":[65],"of":[66],"fine":[67],"medical":[68,74],"details,":[69],"EntMLM,":[71],"entities":[75],"them":[80],"using":[81],"visual":[82],"cues.Furthermore,":[83],"incorporates":[85],"unpaired":[86],"data":[87],"through":[88],"disease-kind":[89],"prompts,":[90],"achieving":[91],"state-of-the-art":[92],"performance":[93],"zero-shot":[95],"fine-tuning":[97],"across":[98],"five":[99],"benchmarks.Code:":[100]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}