{"id":"https://openalex.org/W4416105912","doi":"https://doi.org/10.1109/iccv51701.2025.02092","title":"Learnable Retrieval Enhanced Visual-Text Alignment and Fusion for Radiology Report Generation","display_name":"Learnable Retrieval Enhanced Visual-Text Alignment and Fusion for Radiology Report Generation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416105912","doi":"https://doi.org/10.1109/iccv51701.2025.02092"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02092","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02092","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.07568","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022862584","display_name":"Qin Zhou","orcid":"https://orcid.org/0000-0001-5334-7188"},"institutions":[{"id":"https://openalex.org/I143593769","display_name":"East China University of Science and Technology","ror":"https://ror.org/01vyrm377","country_code":"CN","type":"education","lineage":["https://openalex.org/I143593769"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qin Zhou","raw_affiliation_strings":["ECUST,Department of Computer Science and Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ECUST,Department of Computer Science and Engineering,China","institution_ids":["https://openalex.org/I143593769"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047959370","display_name":"Guoyan Liang","orcid":"https://orcid.org/0000-0003-0072-3156"},"institutions":[{"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":"Guoyan Liang","raw_affiliation_strings":["Zhejiang University,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114240949","display_name":"Xiuwen Li","orcid":"https://orcid.org/0009-0009-2250-7148"},"institutions":[{"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":"Xindi Li","raw_affiliation_strings":["Zhejiang University,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009749449","display_name":"Jingyuan Chen","orcid":"https://orcid.org/0000-0003-0415-6937"},"institutions":[{"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":"Jingyuan Chen","raw_affiliation_strings":["Zhejiang University,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100407657","display_name":"Zhe Wang","orcid":"https://orcid.org/0000-0003-1119-1765"},"institutions":[{"id":"https://openalex.org/I143593769","display_name":"East China University of Science and Technology","ror":"https://ror.org/01vyrm377","country_code":"CN","type":"education","lineage":["https://openalex.org/I143593769"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhe Wang","raw_affiliation_strings":["ECUST,Department of Computer Science and Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ECUST,Department of Computer Science and Engineering,China","institution_ids":["https://openalex.org/I143593769"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056066639","display_name":"Chang Yao","orcid":"https://orcid.org/0000-0002-1187-6257"},"institutions":[{"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":"Chang Yao","raw_affiliation_strings":["Zhejiang University,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017672363","display_name":"Sai Wu","orcid":"https://orcid.org/0000-0002-7903-1496"},"institutions":[{"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":"Sai Wu","raw_affiliation_strings":["Zhejiang University,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"22529","last_page":"22538"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8355000019073486,"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":0.8355000019073486,"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/T10028","display_name":"Topic Modeling","score":0.05429999902844429,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.020500000566244125,"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/context","display_name":"Context (archaeology)","score":0.6326000094413757},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5848000049591064},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4706000089645386},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.47029998898506165},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.44909998774528503},{"id":"https://openalex.org/keywords/medical-imaging","display_name":"Medical imaging","score":0.374099999666214}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7081999778747559},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6326000094413757},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5848000049591064},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4706000089645386},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.47029998898506165},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.44909998774528503},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42660000920295715},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.374099999666214},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37049999833106995},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.33390000462532043},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.27129998803138733},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25360000133514404}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02092","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02092","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.07568","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.07568","pdf_url":"https://arxiv.org/pdf/2507.07568","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.07568","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.07568","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.07568","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.07568","pdf_url":"https://arxiv.org/pdf/2507.07568","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6081112666","display_name":null,"funder_award_id":"62201341","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Automated":[0],"radiology":[1,203],"report":[2,58,138,204],"generation":[3,205],"is":[4],"essential":[5],"for":[6,97,118,136],"improving":[7],"diagnostic":[8],"efficiency":[9],"and":[10,28,44,54,78,102,108,147,183],"reducing":[11],"the":[12,38,88,180,186],"workload":[13],"of":[14,177],"medical":[15],"professionals.":[16],"However,":[17],"existing":[18],"methods":[19],"face":[20],"significant":[21],"challenges,":[22],"such":[23],"as":[24],"disease":[25],"class":[26,52,100],"imbalance":[27,53,163],"insufficient":[29],"cross-modal":[30],"fusion.":[31],"To":[32],"address":[33],"these":[34],"issues,":[35],"we":[36],"propose":[37],"learnable":[39],"Retrieval":[40,68],"Enhanced":[41],"Visual-Text":[42],"Alignment":[43],"Fusion":[45],"(REVTAF)":[46],"framework,":[47],"which":[48],"effectively":[49,160],"tackles":[50],"both":[51],"visual-text":[55,106,152],"fusion":[56,109],"in":[57,202],"generation.":[59,139],"REVTAF":[60,149,169],"incorporates":[61],"two":[62],"core":[63],"components:":[64],"(1)":[65],"a":[66,82,104],"Learnable":[67],"Enhancer":[69],"(LRE)":[70],"that":[71,111,168],"utilizes":[72],"semantic":[73],"hierarchies":[74],"from":[75],"hyperbolic":[76],"space":[77],"intra-batch":[79],"context":[80],"through":[81],"ranking-based":[83],"metric.":[84],"LRE":[85],"adaptively":[86],"retrieves":[87],"most":[89],"relevant":[90],"reference":[91],"reports,":[92],"enhancing":[93],"image":[94],"representations,":[95],"particularly":[96],"underrepresented":[98],"(tail)":[99],"inputs;":[101],"(2)":[103],"fine-grained":[105,151],"alignment":[107,146],"strategy":[110],"ensures":[112],"consistency":[113],"across":[114],"multi-source":[115,145],"cross-attention":[116,128],"maps":[117],"precise":[119],"alignment.":[120],"This":[121],"component":[122],"further":[123,198],"employs":[124],"an":[125,174],"optimal":[126],"transport-based":[127],"mechanism":[129],"to":[130],"dynamically":[131],"integrate":[132],"task-relevant":[133],"textual":[134],"knowledge":[135],"improved":[137],"By":[140],"combining":[141],"adaptive":[142],"retrieval":[143],"with":[144,191],"fusion,":[148],"achieves":[150],"integration":[153],"under":[154],"weak":[155],"image-report":[156],"level":[157],"supervision":[158],"while":[159],"mitigating":[161],"data":[162],"issues.":[164],"The":[165],"experiments":[166],"demonstrate":[167],"outperforms":[170],"state-of-the-art":[171],"methods,":[172],"achieving":[173],"average":[175],"improvement":[176],"7.4%":[178],"on":[179,185],"MIMIC-CXR":[181],"dataset":[182],"2.9%":[184],"IU":[187],"X-Ray":[188],"dataset.":[189],"Comparisons":[190],"mainstream":[192],"multimodal":[193],"LLMs":[194],"(e.g.,":[195],"GPT-series":[196],"models),":[197],"highlight":[199],"its":[200],"superiority":[201],"https://github.com/banbooliang/REVTAF-RRG.":[206]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}