{"id":"https://openalex.org/W4387846261","doi":"https://doi.org/10.1145/3583780.3614961","title":"Harnessing the Power of Pre-trained Vision-Language Models for Efficient Medical Report Generation","display_name":"Harnessing the Power of Pre-trained Vision-Language Models for Efficient Medical Report Generation","publication_year":2023,"publication_date":"2023-10-21","ids":{"openalex":"https://openalex.org/W4387846261","doi":"https://doi.org/10.1145/3583780.3614961"},"language":"en","primary_location":{"id":"doi:10.1145/3583780.3614961","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3583780.3614961","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Information and Knowledge Management","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/A5101433872","display_name":"Qi Li","orcid":"https://orcid.org/0009-0009-6125-0488"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qi Li","raw_affiliation_strings":["Tsinghua University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5101433872"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":1.2299,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.81962541,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1308","last_page":"1317"},"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":0.9983000159263611,"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":0.9937000274658203,"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/computer-science","display_name":"Computer science","score":0.8111650943756104},{"id":"https://openalex.org/keywords/inefficiency","display_name":"Inefficiency","score":0.6890861988067627},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5812780261039734},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5557034015655518},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.518376886844635},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.489255428314209},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.45515936613082886},{"id":"https://openalex.org/keywords/medical-imaging","display_name":"Medical imaging","score":0.4306100606918335}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8111650943756104},{"id":"https://openalex.org/C2778869765","wikidata":"https://www.wikidata.org/wiki/Q6028363","display_name":"Inefficiency","level":2,"score":0.6890861988067627},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5812780261039734},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5557034015655518},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.518376886844635},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.489255428314209},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.45515936613082886},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.4306100606918335},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3583780.3614961","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3583780.3614961","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1593271688","https://openalex.org/W1773149199","https://openalex.org/W1956340063","https://openalex.org/W2152772232","https://openalex.org/W2562153041","https://openalex.org/W2575842049","https://openalex.org/W2890888035","https://openalex.org/W2914203365","https://openalex.org/W2946580620","https://openalex.org/W2963084599","https://openalex.org/W2964187781","https://openalex.org/W2979861699","https://openalex.org/W2997704374","https://openalex.org/W2999905431","https://openalex.org/W3034655362","https://openalex.org/W3104609094","https://openalex.org/W3109931228","https://openalex.org/W3173688449","https://openalex.org/W3182683290","https://openalex.org/W4229027955","https://openalex.org/W4297828572","https://openalex.org/W6600195515","https://openalex.org/W6600234944","https://openalex.org/W6600339457","https://openalex.org/W6600553734","https://openalex.org/W6703106053"],"related_works":["https://openalex.org/W2264067234","https://openalex.org/W3124243301","https://openalex.org/W1571502335","https://openalex.org/W1589409554","https://openalex.org/W2759038785","https://openalex.org/W2172232600","https://openalex.org/W3123876860","https://openalex.org/W4379801084","https://openalex.org/W3093339210","https://openalex.org/W3015037427"],"abstract_inverted_index":{"Medical":[0,25],"images":[1],"are":[2],"commonly":[3],"used":[4],"in":[5,66,125],"clinical":[6],"practice.":[7],"But":[8],"the":[9,20,33,67,77,90,165],"need":[10,78],"for":[11,79,106,119,144],"diagnosis":[12],"and":[13,89,128,136,175],"reporting":[14],"from":[15,56],"image-based":[16],"examinations":[17],"far":[18],"excels":[19],"current":[21],"medical":[22,68],"capacity.":[23],"Automatic":[24],"Report":[26],"Generation":[27],"(MRG)":[28],"can":[29,54,109],"help":[30],"to":[31,73,122,134],"ease":[32],"burden":[34],"of":[35,92,152],"radiologists.":[36],"Vision-Language":[37],"Pre-training":[38],"(VLP)":[39],"has":[40],"received":[41],"tremendous":[42],"success":[43],"on":[44],"various":[45],"tasks,":[46],"therefore":[47],"it":[48],"is":[49,70],"naturally":[50],"expected":[51],"that":[52,108,158],"MRG":[53,107],"harvest":[55],"this":[57],"rapid":[58],"advancement.":[59],"However,":[60],"directly":[61],"applying":[62],"existing":[63],"VLP":[64,120],"models":[65],"domain":[69],"impracticable":[71],"due":[72],"their":[74],"data-hungry":[75],"nature,":[76],"aligning":[80],"different":[81],"modalities,":[82],"prohibitive":[83],"training":[84,180],"time,":[85],"exorbitant":[86],"hardware":[87],"barrier,":[88],"challenge":[91],"open-ended":[93],"text":[94,143],"generation.":[95],"To":[96],"address":[97],"these":[98],"problems,":[99],"we":[100,159],"propose":[101],"MedEPT,":[102],"a":[103,149,161],"parameter-efficient":[104,116],"approach":[105],"utilize":[110],"ever-ignored":[111],"image-only":[112,145],"datasets.":[113,146],"It":[114],"employs":[115,132],"tuning":[117],"(PET)":[118],"adaption":[121,138],"mitigate":[123],"inefficiency":[124],"fine-tuning":[126],"time":[127,181],"hardware.":[129],"MedEPT":[130],"also":[131],"MRGPID":[133],"augment":[135],"expand":[137],"datasets":[139],"by":[140],"synthesizing":[141],"meaningful":[142],"We":[147],"perform":[148],"systematic":[150],"evaluation":[151],"our":[153],"method.":[154],"Empirical":[155],"results":[156],"show":[157],"obtain":[160],"better":[162],"performance":[163],"than":[164,171,178,182],"state-of-the-art":[166],"method":[167],"while":[168],"using":[169],"less":[170],"10%":[172],"trainable":[173],"parameters":[174],"not":[176],"more":[177],"30%":[179],"ever":[183],"before.":[184]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}