{"id":"https://openalex.org/W4392902791","doi":"https://doi.org/10.1109/icassp48485.2024.10446878","title":"Sam-Guided Enhanced Fine-Grained Encoding with Mixed Semantic Learning for Medical Image Captioning","display_name":"Sam-Guided Enhanced Fine-Grained Encoding with Mixed Semantic Learning for Medical Image Captioning","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902791","doi":"https://doi.org/10.1109/icassp48485.2024.10446878"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446878","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446878","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5043316070","display_name":"Zhenyu Zhang","orcid":"https://orcid.org/0000-0002-7410-4967"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Zhenyu Zhang","raw_affiliation_strings":["Zhejiang University-University of Illinois Urbana-Champaign Institute, Zhejiang University,China","Zhejiang University-University of Illinois Urbana-Champaign Institute, Zhejiang University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University-University of Illinois Urbana-Champaign Institute, Zhejiang University,China","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Zhejiang University-University of Illinois Urbana-Champaign Institute, Zhejiang University, China","institution_ids":["https://openalex.org/I157725225","https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102631454","display_name":"Benlu Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Benlu Wang","raw_affiliation_strings":["Zhejiang University-University of Illinois Urbana-Champaign Institute, Zhejiang University,China","Zhejiang University-University of Illinois Urbana-Champaign Institute, Zhejiang University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University-University of Illinois Urbana-Champaign Institute, Zhejiang University,China","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Zhejiang University-University of Illinois Urbana-Champaign Institute, Zhejiang University, China","institution_ids":["https://openalex.org/I157725225","https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074787984","display_name":"Weijie Liang","orcid":"https://orcid.org/0000-0002-0833-350X"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Weijie Liang","raw_affiliation_strings":["Zhejiang University-University of Illinois Urbana-Champaign Institute, Zhejiang University,China","Zhejiang University-University of Illinois Urbana-Champaign Institute, Zhejiang University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University-University of Illinois Urbana-Champaign Institute, Zhejiang University,China","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Zhejiang University-University of Illinois Urbana-Champaign Institute, Zhejiang University, China","institution_ids":["https://openalex.org/I157725225","https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009722782","display_name":"Yizhi Li","orcid":"https://orcid.org/0000-0003-4049-0385"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Yizhi Li","raw_affiliation_strings":["Zhejiang University-University of Illinois Urbana-Champaign Institute, Zhejiang University,China","Zhejiang University-University of Illinois Urbana-Champaign Institute, Zhejiang University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University-University of Illinois Urbana-Champaign Institute, Zhejiang University,China","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Zhejiang University-University of Illinois Urbana-Champaign Institute, Zhejiang University, China","institution_ids":["https://openalex.org/I157725225","https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018711512","display_name":"Xuechen Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Xuechen Guo","raw_affiliation_strings":["Zhejiang University-University of Illinois Urbana-Champaign Institute, Zhejiang University,China","Zhejiang University-University of Illinois Urbana-Champaign Institute, Zhejiang University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University-University of Illinois Urbana-Champaign Institute, Zhejiang University,China","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Zhejiang University-University of Illinois Urbana-Champaign Institute, Zhejiang University, China","institution_ids":["https://openalex.org/I157725225","https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062245538","display_name":"Guanhong Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Guanhong Wang","raw_affiliation_strings":["Zhejiang University-University of Illinois Urbana-Champaign Institute, Zhejiang University,China","Zhejiang University-University of Illinois Urbana-Champaign Institute, Zhejiang University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University-University of Illinois Urbana-Champaign Institute, Zhejiang University,China","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Zhejiang University-University of Illinois Urbana-Champaign Institute, Zhejiang University, China","institution_ids":["https://openalex.org/I157725225","https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058143402","display_name":"Shiyan Li","orcid":"https://orcid.org/0000-0001-9907-5763"},"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":"Shiyan Li","raw_affiliation_strings":["Sir Run Run Shaw Hospital, Zhejiang University School of Medicine,China","Sir Run Run Shaw Hospital, Zhejiang University School of Medicine, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sir Run Run Shaw Hospital, Zhejiang University School of Medicine,China","institution_ids":["https://openalex.org/I2802390878"]},{"raw_affiliation_string":"Sir Run Run Shaw Hospital, Zhejiang University School of Medicine, China","institution_ids":["https://openalex.org/I2802390878","https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089410490","display_name":"Gaoang Wang","orcid":"https://orcid.org/0000-0002-8403-1538"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Gaoang Wang","raw_affiliation_strings":["Zhejiang University-University of Illinois Urbana-Champaign Institute, Zhejiang University,China","Zhejiang University-University of Illinois Urbana-Champaign Institute, Zhejiang University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University-University of Illinois Urbana-Champaign Institute, Zhejiang University,China","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Zhejiang University-University of Illinois Urbana-Champaign Institute, Zhejiang University, China","institution_ids":["https://openalex.org/I157725225","https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.2809,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.93072201,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1731","last_page":"1735"},"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/T10028","display_name":"Topic Modeling","score":0.9911999702453613,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9732000231742859,"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/closed-captioning","display_name":"Closed captioning","score":0.9776074886322021},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8390474319458008},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.7431763410568237},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6144195199012756},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5932574272155762},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5821124911308289},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5558997988700867},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5063620805740356},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.43431556224823},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33809998631477356}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9776074886322021},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8390474319458008},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.7431763410568237},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6144195199012756},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5932574272155762},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5821124911308289},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5558997988700867},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5063620805740356},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.43431556224823},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33809998631477356},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446878","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446878","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G6473221358","display_name":null,"funder_award_id":"62106219","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":29,"referenced_works":["https://openalex.org/W1490960179","https://openalex.org/W1861492603","https://openalex.org/W1956340063","https://openalex.org/W2154652894","https://openalex.org/W2600463316","https://openalex.org/W2897980926","https://openalex.org/W3035252911","https://openalex.org/W3104050923","https://openalex.org/W3135367836","https://openalex.org/W3166396011","https://openalex.org/W3176456866","https://openalex.org/W3184735396","https://openalex.org/W4226182655","https://openalex.org/W4229005866","https://openalex.org/W4313156423","https://openalex.org/W4318718936","https://openalex.org/W4385063184","https://openalex.org/W4385573131","https://openalex.org/W4390872699","https://openalex.org/W4390874575","https://openalex.org/W6678262379","https://openalex.org/W6682631176","https://openalex.org/W6761205521","https://openalex.org/W6784185929","https://openalex.org/W6798805250","https://openalex.org/W6811013733","https://openalex.org/W6811340617","https://openalex.org/W6849177959","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4289422896"],"abstract_inverted_index":{"With":[0],"the":[1,9,18,61,94,105,113],"development":[2],"of":[3,107,124],"multimodality":[4],"and":[5,29,73,97],"large":[6],"language":[7],"models,":[8],"deep":[10],"learning-based":[11],"technique":[12],"for":[13,121],"medical":[14,46,55,101,125],"image":[15,30,56],"captioning":[16,57],"holds":[17],"potential":[19],"to":[20,41,66,90],"offer":[21],"valuable":[22],"diagnostic":[23],"recommendations.":[24],"However,":[25],"current":[26],"generic":[27],"text":[28],"pre-trained":[31,114],"models":[32],"do":[33],"not":[34],"yield":[35],"satisfactory":[36],"results":[37],"when":[38],"it":[39,111],"comes":[40],"describing":[42],"intricate":[43],"details":[44,99],"within":[45,100],"images.":[47,102,126],"In":[48,77],"this":[49,108],"paper,":[50],"we":[51],"present":[52],"a":[53,82],"novel":[54],"method":[58],"guided":[59],"by":[60],"segment":[62],"anything":[63],"model":[64,116],"(SAM)":[65],"enable":[67],"enhanced":[68],"encoding":[69],"with":[70,86],"both":[71,93],"general":[72],"detailed":[74],"feature":[75],"extraction.":[76],"addition,":[78],"our":[79],"approach":[80],"employs":[81],"distinctive":[83],"pre-training":[84],"strategy":[85],"mixed":[87],"semantic":[88],"learning":[89],"simultaneously":[91],"capture":[92],"overall":[95],"information":[96],"finer":[98],"We":[103],"demonstrate":[104],"effectiveness":[106],"approach,":[109],"as":[110],"outperforms":[112],"BLIP2":[115],"on":[117],"various":[118],"evaluation":[119],"metrics":[120],"generating":[122],"descriptions":[123]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
