{"id":"https://openalex.org/W4410296305","doi":"https://doi.org/10.1109/isbi60581.2025.10981310","title":"LLAMA-VG: A Video Vision LLaMA-Based Model for Endoscopy Video Generation","display_name":"LLAMA-VG: A Video Vision LLaMA-Based Model for Endoscopy Video Generation","publication_year":2025,"publication_date":"2025-04-14","ids":{"openalex":"https://openalex.org/W4410296305","doi":"https://doi.org/10.1109/isbi60581.2025.10981310"},"language":"en","primary_location":{"id":"doi:10.1109/isbi60581.2025.10981310","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isbi60581.2025.10981310","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 22nd International Symposium on Biomedical Imaging (ISBI)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5015740069","display_name":"Yueyao Chen","orcid":"https://orcid.org/0009-0008-3084-4032"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yueyao Chen","raw_affiliation_strings":["The Chinese University of Hong Kong,Department of Computer Science and Engineering,Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Department of Computer Science and Engineering,Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107956076","display_name":"Zheng Han","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zheng Han","raw_affiliation_strings":["The Chinese University of Hong Kong,Department of Computer Science and Engineering,Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Department of Computer Science and Engineering,Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090516040","display_name":"Qi Dou","orcid":"https://orcid.org/0000-0002-3416-9950"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Qi Dou","raw_affiliation_strings":["The Chinese University of Hong Kong,Department of Computer Science and Engineering,Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Department of Computer Science and Engineering,Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T10552","display_name":"Colorectal Cancer Screening and Detection","score":0.8575999736785889,"subfield":{"id":"https://openalex.org/subfields/2730","display_name":"Oncology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10552","display_name":"Colorectal Cancer Screening and Detection","score":0.8575999736785889,"subfield":{"id":"https://openalex.org/subfields/2730","display_name":"Oncology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6178445816040039},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5784686207771301},{"id":"https://openalex.org/keywords/video-recording","display_name":"Video recording","score":0.5129351615905762},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5069601535797119},{"id":"https://openalex.org/keywords/endoscopy","display_name":"Endoscopy","score":0.4537615180015564},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.4140758514404297},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.23327061533927917},{"id":"https://openalex.org/keywords/surgery","display_name":"Surgery","score":0.14532500505447388}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6178445816040039},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5784686207771301},{"id":"https://openalex.org/C2988634675","wikidata":"https://www.wikidata.org/wiki/Q34508","display_name":"Video recording","level":2,"score":0.5129351615905762},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5069601535797119},{"id":"https://openalex.org/C2778451229","wikidata":"https://www.wikidata.org/wiki/Q212809","display_name":"Endoscopy","level":2,"score":0.4537615180015564},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.4140758514404297},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.23327061533927917},{"id":"https://openalex.org/C141071460","wikidata":"https://www.wikidata.org/wiki/Q40821","display_name":"Surgery","level":1,"score":0.14532500505447388}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isbi60581.2025.10981310","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isbi60581.2025.10981310","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 22nd International Symposium on Biomedical Imaging (ISBI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G818396220","display_name":null,"funder_award_id":"62322318","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2332757643","https://openalex.org/W3082604781","https://openalex.org/W3102722996","https://openalex.org/W3120341153","https://openalex.org/W3196792983","https://openalex.org/W3203467945","https://openalex.org/W4214612132","https://openalex.org/W4226428874","https://openalex.org/W4312114943","https://openalex.org/W4312423208","https://openalex.org/W4386075896","https://openalex.org/W4387845481","https://openalex.org/W4401612088","https://openalex.org/W4402727645","https://openalex.org/W4403062908","https://openalex.org/W6846959760","https://openalex.org/W6860724318","https://openalex.org/W6862149836"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Endoscopy":[0],"video":[1,66],"data":[2],"is":[3,186],"essential":[4],"for":[5,78],"advancing":[6],"intelligent":[7],"endoscopic":[8],"surgery,":[9],"while":[10],"constraints":[11],"arising":[12],"from":[13,87],"privacy":[14],"regulations":[15],"and":[16,36,75,102,114,148,170],"institutional":[17],"policies":[18],"significantly":[19],"limit":[20],"its":[21],"collection,":[22],"hindering":[23],"the":[24,93,97,112,119,160,181],"development":[25],"of":[26,108,178],"large-scale":[27],"pub-lic":[28],"datasets.":[29],"Video":[30,133],"generation":[31,67],"methods,":[32],"such":[33],"as":[34],"GANs":[35],"diffusion":[37,94],"models,":[38],"hold":[39],"promise":[40],"in":[41,53,117,180],"addressing":[42],"this":[43],"is-sue":[44],"by":[45,136,144,152],"generating":[46],"synthetic":[47],"endoscopy":[48,65],"videos,":[49],"but":[50],"their":[51],"capacity":[52],"modeling":[54],"complex":[55],"spatiotemporal":[56,76],"correlations":[57],"remains":[58],"limited.":[59],"Accordingly,":[60],"we":[61,83],"propose":[62],"a":[63],"novel":[64],"framework":[68],"LLaMA-VG":[69,110,130],"to":[70,91,138,146,155,163],"incorporate":[71],"ro-tary":[72],"positional":[73],"embeddings":[74],"transformations":[77],"long-range":[79],"temporal":[80,168],"reasoning.":[81],"Besides,":[82],"ap-ply":[84],"multimodal":[85],"knowledge":[86],"pretrained":[88],"Vision":[89],"LLaMA":[90],"guide":[92],"process,":[95],"retaining":[96],"context":[98],"sim-ilarity":[99],"between":[100],"generated":[101,182],"real":[103],"videos.":[104],"We":[105],"conducted":[106],"evaluations":[107],"our":[109],"on":[111],"Colonoscopic":[113],"Kvasir-Capsule":[115],"datasets,":[116],"which":[118],"model":[120],"demonstrated":[121],"considerable":[122],"improvements":[123],"over":[124],"existing":[125],"state-of-the-art":[126],"approaches.":[127],"In":[128],"particular,":[129],"improves":[131],"Fr\u00e9chet":[132,140],"Distance":[134,142],"(FVD)":[135],"19.69%":[137],"22.29%,":[139],"In-ception":[141],"(FID)":[143],"7.08%":[145],"27.94%,":[147],"Inception":[149],"Score":[150],"(IS)":[151],"2.31":[153],"%":[154],"4.69%.":[156],"These":[157],"results":[158],"underscore":[159],"model's":[161],"ability":[162],"generate":[164],"videos":[165],"with":[166],"im-proved":[167],"coherence":[169],"spatial":[171],"fidelity,":[172],"simulta-neously":[173],"maintaining":[174],"an":[175],"adequate":[176],"level":[177],"diversity":[179],"content.":[183],"The":[184],"code":[185],"available":[187],"at:":[188],"h":[189],"t":[190,191],"p":[192],"s:":[193],"//github.com/YueyaoChenCYY/LLaMA-VG<sup":[194],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[195],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}