{"id":"https://openalex.org/W4408352617","doi":"https://doi.org/10.1109/icassp49660.2025.10890310","title":"GCS-M3VLT: Guided Context Self-Attention based Multi-modal Medical Vision Language Transformer for Retinal Image Captioning","display_name":"GCS-M3VLT: Guided Context Self-Attention based Multi-modal Medical Vision Language Transformer for Retinal Image Captioning","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352617","doi":"https://doi.org/10.1109/icassp49660.2025.10890310"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890310","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890310","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5015473698","display_name":"Teja Krishna Cherukuri","orcid":"https://orcid.org/0000-0002-4952-728X"},"institutions":[{"id":"https://openalex.org/I181565077","display_name":"Georgia State University","ror":"https://ror.org/03qt6ba18","country_code":"US","type":"education","lineage":["https://openalex.org/I181565077"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Teja Krishna Cherukuri","raw_affiliation_strings":["Georgia State University,Department of Computer Science,Atlanta,GA,USA"],"affiliations":[{"raw_affiliation_string":"Georgia State University,Department of Computer Science,Atlanta,GA,USA","institution_ids":["https://openalex.org/I181565077"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027212073","display_name":"Nagur Shareef Shaik","orcid":"https://orcid.org/0000-0002-2432-7409"},"institutions":[{"id":"https://openalex.org/I181565077","display_name":"Georgia State University","ror":"https://ror.org/03qt6ba18","country_code":"US","type":"education","lineage":["https://openalex.org/I181565077"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nagur Shareef Shaik","raw_affiliation_strings":["Georgia State University,Department of Computer Science,Atlanta,GA,USA"],"affiliations":[{"raw_affiliation_string":"Georgia State University,Department of Computer Science,Atlanta,GA,USA","institution_ids":["https://openalex.org/I181565077"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019753026","display_name":"Jyostna Devi Bodapati","orcid":"https://orcid.org/0000-0002-5185-882X"},"institutions":[{"id":"https://openalex.org/I149313025","display_name":"Vignan's Foundation for Science, Technology & Research","ror":"https://ror.org/03bzf1g85","country_code":"IN","type":"education","lineage":["https://openalex.org/I149313025"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Jyostna Devi Bodapati","raw_affiliation_strings":["Technology &amp; Reserach University,Vignan&#x2019;s Foundation for Science,Guntur,Andhra Pradesh,India"],"affiliations":[{"raw_affiliation_string":"Technology &amp; Reserach University,Vignan&#x2019;s Foundation for Science,Guntur,Andhra Pradesh,India","institution_ids":["https://openalex.org/I149313025"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068927047","display_name":"Dong Hye Ye","orcid":"https://orcid.org/0000-0002-9186-4095"},"institutions":[{"id":"https://openalex.org/I181565077","display_name":"Georgia State University","ror":"https://ror.org/03qt6ba18","country_code":"US","type":"education","lineage":["https://openalex.org/I181565077"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Hye Ye","raw_affiliation_strings":["Georgia State University,Department of Computer Science,Atlanta,GA,USA"],"affiliations":[{"raw_affiliation_string":"Georgia State University,Department of Computer Science,Atlanta,GA,USA","institution_ids":["https://openalex.org/I181565077"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5015473698"],"corresponding_institution_ids":["https://openalex.org/I181565077"],"apc_list":null,"apc_paid":null,"fwci":5.4224,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.952235,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9991999864578247,"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":0.9991999864578247,"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/T11438","display_name":"Retinal Imaging and Analysis","score":0.9679999947547913,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9646000266075134,"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/closed-captioning","display_name":"Closed captioning","score":0.7631487846374512},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7518665790557861},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.658478856086731},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.48118263483047485},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.42873457074165344},{"id":"https://openalex.org/keywords/retinal","display_name":"Retinal","score":0.4250972867012024},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42238807678222656},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4018971025943756},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33831876516342163},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11533334851264954},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.11280450224876404},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.10870197415351868},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.0829443633556366},{"id":"https://openalex.org/keywords/ophthalmology","display_name":"Ophthalmology","score":0.07997626066207886}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7631487846374512},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7518665790557861},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.658478856086731},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.48118263483047485},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42873457074165344},{"id":"https://openalex.org/C2780827179","wikidata":"https://www.wikidata.org/wiki/Q422001","display_name":"Retinal","level":2,"score":0.4250972867012024},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42238807678222656},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4018971025943756},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33831876516342163},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11533334851264954},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.11280450224876404},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.10870197415351868},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0829443633556366},{"id":"https://openalex.org/C118487528","wikidata":"https://www.wikidata.org/wiki/Q161437","display_name":"Ophthalmology","level":1,"score":0.07997626066207886},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890310","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890310","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2016795705","https://openalex.org/W2058579223","https://openalex.org/W2072175453","https://openalex.org/W2302086703","https://openalex.org/W2962858109","https://openalex.org/W3119639728","https://openalex.org/W3194346615","https://openalex.org/W3196479518","https://openalex.org/W4213210229","https://openalex.org/W4220862900","https://openalex.org/W4319300591","https://openalex.org/W4382240685","https://openalex.org/W4386076360","https://openalex.org/W4386076536","https://openalex.org/W4391873005","https://openalex.org/W4392902791","https://openalex.org/W4402915501","https://openalex.org/W4402915770","https://openalex.org/W4403071606","https://openalex.org/W6739901393","https://openalex.org/W6793164127","https://openalex.org/W6851592950","https://openalex.org/W6853469104","https://openalex.org/W6862611975"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W2963177403","https://openalex.org/W4310447809","https://openalex.org/W4200243030","https://openalex.org/W2800782462","https://openalex.org/W3209117276","https://openalex.org/W4388184981","https://openalex.org/W4323777661"],"abstract_inverted_index":{"Retinal":[0],"image":[1,24,56],"analysis":[2],"is":[3],"crucial":[4],"for":[5,54],"diagnosing":[6],"and":[7,26,40,61,76],"treating":[8],"eye":[9],"diseases,":[10],"yet":[11],"generating":[12,108],"accurate":[13],"medical":[14,110],"reports":[15],"from":[16],"images":[17],"remains":[18],"challenging":[19],"due":[20],"to":[21,37],"variability":[22],"in":[23,82,107],"quality":[25],"pathology,":[27],"especially":[28],"with":[29,97],"limited":[30,44],"labeled":[31],"data.":[32],"Previous":[33],"Transformer-based":[34],"models":[35],"struggled":[36],"integrate":[38],"visual":[39,60],"textual":[41,62],"information":[42],"under":[43],"supervision.":[45],"In":[46],"response,":[47],"we":[48],"propose":[49],"a":[50,65,92],"novel":[51],"vision-language":[52],"model":[53,106],"retinal":[55],"captioning":[57],"that":[58],"combines":[59],"features":[63],"through":[64],"guided":[66],"context":[67],"self-attention":[68],"mechanism.":[69],"This":[70],"approach":[71],"captures":[72],"both":[73],"intricate":[74],"details":[75],"the":[77,88,102],"global":[78],"clinical":[79],"context,":[80],"even":[81],"data-scarce":[83],"scenarios.":[84],"Extensive":[85],"experiments":[86],"on":[87],"DeepEyeNet":[89],"dataset":[90],"demonstrate":[91],"0.023":[93],"BLEU@4":[94],"improvement,":[95],"along":[96],"significant":[98],"qualitative":[99],"advancements,":[100],"highlighting":[101],"effectiveness":[103],"of":[104],"our":[105],"comprehensive":[109],"captions.":[111]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-17T09:09:15.849793","created_date":"2025-10-10T00:00:00"}
