{"id":"https://openalex.org/W7138071363","doi":"https://doi.org/10.1609/aaai.v40i8.37593","title":"SurgPub-Video: A Comprehensive Surgical Video Framework for Enhanced Surgical Intelligence in Vision-Language Model","display_name":"SurgPub-Video: A Comprehensive Surgical Video Framework for Enhanced Surgical Intelligence in Vision-Language Model","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138071363","doi":"https://doi.org/10.1609/aaai.v40i8.37593"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i8.37593","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i8.37593","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37593/41555","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37593/41555","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070831420","display_name":"Yaoqian Li","orcid":"https://orcid.org/0000-0002-5189-8151"},"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":"Yaoqian Li","raw_affiliation_strings":["Department of Computer Science and Engineering, The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046094203","display_name":"Xikai Yang","orcid":"https://orcid.org/0000-0003-1762-9684"},"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":"Xikai Yang","raw_affiliation_strings":["Department of Computer Science and Engineering, The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101204537","display_name":"Dunyuan Xu","orcid":"https://orcid.org/0000-0001-7600-9384"},"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":"Dunyuan Xu","raw_affiliation_strings":["Department of Computer Science and Engineering, The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129646568","display_name":"Yang YU","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":"Yang YU","raw_affiliation_strings":["Department of Computer Science and Engineering, The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129699883","display_name":"Litao Zhao","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":"Litao Zhao","raw_affiliation_strings":["Department of Computer Science and Engineering, The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129667972","display_name":"Xiaowei Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaowei Hu","raw_affiliation_strings":["School of Future Technology, South China University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Future Technology, South China University of Technology","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129749810","display_name":"Jinpeng li","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":"Jinpeng Li","raw_affiliation_strings":["Department of Computer Science and Engineering, The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129649200","display_name":"Pheng-Ann Heng","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":"Pheng-Ann Heng","raw_affiliation_strings":["Department of Computer Science and Engineering, The Chinese University of Hong Kong\nInstitute of Medical Intelligence and XR, The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Chinese University of Hong Kong\nInstitute of Medical Intelligence and XR, The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32407407,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"8","first_page":"6628","last_page":"6635"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8205000162124634,"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":0.8205000162124634,"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/T10916","display_name":"Surgical Simulation and Training","score":0.06319999694824219,"subfield":{"id":"https://openalex.org/subfields/2746","display_name":"Surgery"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.021199999377131462,"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/surgical-procedures","display_name":"Surgical procedures","score":0.5315999984741211},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5037999749183655},{"id":"https://openalex.org/keywords/surgical-planning","display_name":"Surgical planning","score":0.42089998722076416},{"id":"https://openalex.org/keywords/surgical-instrument","display_name":"Surgical instrument","score":0.4036000072956085},{"id":"https://openalex.org/keywords/surgical-simulation","display_name":"Surgical simulation","score":0.37549999356269836},{"id":"https://openalex.org/keywords/surgical-robot","display_name":"Surgical robot","score":0.33959999680519104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6017000079154968},{"id":"https://openalex.org/C3019611579","wikidata":"https://www.wikidata.org/wiki/Q6641956","display_name":"Surgical procedures","level":2,"score":0.5315999984741211},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5037999749183655},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4235999882221222},{"id":"https://openalex.org/C2779370443","wikidata":"https://www.wikidata.org/wiki/Q1776627","display_name":"Surgical planning","level":2,"score":0.42089998722076416},{"id":"https://openalex.org/C2778181360","wikidata":"https://www.wikidata.org/wiki/Q1074814","display_name":"Surgical instrument","level":2,"score":0.4036000072956085},{"id":"https://openalex.org/C3018608816","wikidata":"https://www.wikidata.org/wiki/Q195818","display_name":"Surgical simulation","level":2,"score":0.37549999356269836},{"id":"https://openalex.org/C3017684034","wikidata":"https://www.wikidata.org/wiki/Q942348","display_name":"Surgical robot","level":3,"score":0.33959999680519104},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3310000002384186},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.31130000948905945},{"id":"https://openalex.org/C2988634675","wikidata":"https://www.wikidata.org/wiki/Q34508","display_name":"Video recording","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C19527891","wikidata":"https://www.wikidata.org/wiki/Q1120908","display_name":"Medical physics","level":1,"score":0.30410000681877136},{"id":"https://openalex.org/C3020562746","wikidata":"https://www.wikidata.org/wiki/Q7446275","display_name":"Surgical resection","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2694000005722046},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.25209999084472656},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i8.37593","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i8.37593","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37593/41555","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/37593","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37593","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i8.37593","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i8.37593","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37593/41555","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7531156539916992,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320323059","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138071363.pdf","grobid_xml":"https://content.openalex.org/works/W7138071363.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision-Language":[0],"Models":[1],"(VLMs)":[2],"have":[3],"shown":[4],"significant":[5],"potential":[6],"in":[7],"surgical":[8,26,45,66,85,94,112],"scene":[9],"analysis,":[10],"yet":[11],"existing":[12],"models":[13],"are":[14],"limited":[15],"by":[16],"frame-level":[17,79],"datasets":[18],"and":[19,47,78,81,100,109,119,129],"lack":[20],"high-quality":[21],"video":[22,67],"data":[23],"with":[24,132],"procedural":[25],"knowledge.":[27],"To":[28],"address":[29],"these":[30],"challenges,":[31],"we":[32],"make":[33],"the":[34,71,106],"following":[35],"contributions:":[36],"(i)":[37],"SurgPub-Video,":[38],"a":[39,62,83],"comprehensive":[40],"dataset":[41],"of":[42],"over":[43],"3,000":[44],"videos":[46],"25":[48],"million":[49],"annotated":[50],"frames":[51],"across":[52],"11":[53,93],"specialities,":[54,95],"sourced":[55],"from":[56],"peer-reviewed":[57],"clinical":[58],"journals,":[59],"(ii)":[60],"SurgLLaVA-Video,":[61],"specialized":[63],"VLM":[64],"for":[65],"understanding,":[68],"built":[69],"upon":[70],"TinyLLaVA-Video":[72],"architecture":[73],"that":[74,123],"supports":[75],"both":[76,127],"video-level":[77,84],"inputs,":[80],"(iii)":[82],"Visual":[86],"Question":[87],"Answering":[88],"(VQA)":[89],"benchmark,":[90],"covering":[91],"diverse":[92],"such":[96],"as":[97],"vascular,":[98],"cardiology,":[99],"thoracic.":[101],"Extensive":[102],"experiments,":[103],"conducted":[104],"on":[105],"proposed":[107],"benchmark":[108],"three":[110,134],"additional":[111],"downstream":[113],"tasks":[114],"(action":[115],"recognition,":[116],"skill":[117],"assessment,":[118],"triplet":[120],"recognition),":[121],"show":[122],"SurgLLaVA-Video":[124],"significantly":[125],"outperforms":[126],"general-purpose":[128],"surgical-specific":[130],"VLMs":[131],"only":[133],"billion":[135],"parameters.":[136]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-18T00:00:00"}
