{"id":"https://openalex.org/W7128233846","doi":"https://doi.org/10.1109/tip.2026.3659752","title":"Procedure-Aware Hierarchical Alignment for Open Surgery Video-Language Pretraining","display_name":"Procedure-Aware Hierarchical Alignment for Open Surgery Video-Language Pretraining","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7128233846","doi":"https://doi.org/10.1109/tip.2026.3659752","pmid":"https://pubmed.ncbi.nlm.nih.gov/41650402"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2026.3659752","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3659752","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Boqiang Xu","orcid":"https://orcid.org/0000-0003-1465-5553"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Boqiang Xu","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1465-5553","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125308650","display_name":"Jinlin Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinlin Wu","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125310014","display_name":"Jian Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Liang","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3890-1894","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhenan Sun","orcid":"https://orcid.org/0000-0003-4029-9935"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenan Sun","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4029-9935","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125316218","display_name":"Hongbin Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongbin Liu","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4315-7556","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125308923","display_name":"Jiebo Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210147894","display_name":"Institut de Recherche et d\u2019Innovation","ror":"https://ror.org/04nqadf13","country_code":"FR","type":"facility","lineage":["https://openalex.org/I4210147894"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jiebo Luo","raw_affiliation_strings":["Hong Kong Institute of Science and Innovation, Hong Kong, SAR, China"],"raw_orcid":"https://orcid.org/0000-0002-4516-9729","affiliations":[{"raw_affiliation_string":"Hong Kong Institute of Science and Innovation, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I4210147894"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5125302351","display_name":"Zhen Lei","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Lei","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0791-189X","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12830041,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"1966","last_page":"1976"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10916","display_name":"Surgical Simulation and Training","score":0.4684000015258789,"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"}},"topics":[{"id":"https://openalex.org/T10916","display_name":"Surgical Simulation and Training","score":0.4684000015258789,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.3644999861717224,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.04619999974966049,"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/open-surgery","display_name":"Open surgery","score":0.6414999961853027},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4659999907016754},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.44690001010894775},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.43869999051094055},{"id":"https://openalex.org/keywords/learning-curve","display_name":"Learning curve","score":0.43459999561309814},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3352999985218048},{"id":"https://openalex.org/keywords/image-warping","display_name":"Image warping","score":0.33230000734329224},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3100999891757965},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.3077000081539154}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6869000196456909},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6762999892234802},{"id":"https://openalex.org/C3018900477","wikidata":"https://www.wikidata.org/wiki/Q1755504","display_name":"Open surgery","level":2,"score":0.6414999961853027},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4659999907016754},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.44690001010894775},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.43869999051094055},{"id":"https://openalex.org/C34585555","wikidata":"https://www.wikidata.org/wiki/Q1368723","display_name":"Learning curve","level":2,"score":0.43459999561309814},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4174000024795532},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3564999997615814},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3352999985218048},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.33230000734329224},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3100999891757965},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3077000081539154},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.30550000071525574},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.30480000376701355},{"id":"https://openalex.org/C103203806","wikidata":"https://www.wikidata.org/wiki/Q942348","display_name":"Robotic surgery","level":2,"score":0.3021000027656555},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.2987000048160553},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.2921000123023987},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2906000018119812},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C19527891","wikidata":"https://www.wikidata.org/wiki/Q1120908","display_name":"Medical physics","level":1,"score":0.2720000147819519},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C2779370443","wikidata":"https://www.wikidata.org/wiki/Q1776627","display_name":"Surgical planning","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C2778739407","wikidata":"https://www.wikidata.org/wiki/Q165372","display_name":"CLIPS","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2547999918460846},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2538999915122986},{"id":"https://openalex.org/C52672216","wikidata":"https://www.wikidata.org/wiki/Q1749840","display_name":"Depth perception","level":3,"score":0.25369998812675476}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D013514","descriptor_name":"Surgical Procedures, Operative","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013514","descriptor_name":"Surgical Procedures, Operative","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013514","descriptor_name":"Surgical Procedures, Operative","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013514","descriptor_name":"Surgical Procedures, Operative","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D014741","descriptor_name":"Video Recording","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D014741","descriptor_name":"Video Recording","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D014741","descriptor_name":"Video Recording","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D014741","descriptor_name":"Video Recording","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D014741","descriptor_name":"Video Recording","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D014741","descriptor_name":"Video Recording","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D025321","descriptor_name":"Surgery, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D025321","descriptor_name":"Surgery, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D025321","descriptor_name":"Surgery, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D025321","descriptor_name":"Surgery, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D065287","descriptor_name":"Robotic Surgical Procedures","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D065287","descriptor_name":"Robotic Surgical Procedures","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D065287","descriptor_name":"Robotic Surgical Procedures","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D065287","descriptor_name":"Robotic Surgical Procedures","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D065287","descriptor_name":"Robotic Surgical Procedures","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D065287","descriptor_name":"Robotic Surgical Procedures","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2026.3659752","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3659752","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:41650402","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41650402","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4103426291","display_name":null,"funder_award_id":"U2441251","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8525382974","display_name":null,"funder_award_id":"U1836217","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":45,"referenced_works":["https://openalex.org/W129606432","https://openalex.org/W2000694776","https://openalex.org/W2080628940","https://openalex.org/W2139106564","https://openalex.org/W2194775991","https://openalex.org/W2398889210","https://openalex.org/W2765685204","https://openalex.org/W2766183047","https://openalex.org/W2777273430","https://openalex.org/W2927739223","https://openalex.org/W2963524571","https://openalex.org/W2990503944","https://openalex.org/W2995394235","https://openalex.org/W2996495478","https://openalex.org/W3034572008","https://openalex.org/W3045648360","https://openalex.org/W3090913119","https://openalex.org/W3092562667","https://openalex.org/W3112106476","https://openalex.org/W3120894151","https://openalex.org/W3150630416","https://openalex.org/W3155656997","https://openalex.org/W3176463841","https://openalex.org/W3177098672","https://openalex.org/W3198379050","https://openalex.org/W3201659970","https://openalex.org/W3203204495","https://openalex.org/W3203711169","https://openalex.org/W3204588463","https://openalex.org/W3209142733","https://openalex.org/W4296054452","https://openalex.org/W4312508181","https://openalex.org/W4312614039","https://openalex.org/W4383108447","https://openalex.org/W4385245566","https://openalex.org/W4386065554","https://openalex.org/W4386076085","https://openalex.org/W4387225898","https://openalex.org/W4387705768","https://openalex.org/W4389377137","https://openalex.org/W4402951547","https://openalex.org/W4403002315","https://openalex.org/W4411040306","https://openalex.org/W4412584687","https://openalex.org/W4415795548"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1,242],"in":[2,16,22,118,134,243],"surgical":[3,39,107],"robotics":[4],"and":[5,14,24,53,73,86,102,125,149,156,187,196,231],"computer":[6],"vision":[7],"have":[8],"greatly":[9],"improved":[10],"intelligent":[11],"systems'":[12],"autonomy":[13],"perception":[15],"the":[17,35,54,69,163],"operating":[18],"room":[19],"(OR),":[20],"especially":[21],"endoscopic":[23],"minimally":[25],"invasive":[26],"surgeries.":[27],"However,":[28],"for":[29,76,97,114,176,240],"open":[30,77,94,119,177,244],"surgery,":[31],"which":[32],"is":[33,110,136],"still":[34],"predominant":[36],"form":[37],"of":[38,56,82,90,146,209],"intervention":[40],"worldwide,":[41],"there":[42],"has":[43],"been":[44],"relatively":[45],"limited":[46],"exploration":[47],"due":[48],"to":[49,151,170,204],"its":[50,237],"inherent":[51],"complexity":[52],"lack":[55],"large-scale,":[57],"diverse":[58],"datasets.":[59],"To":[60],"close":[61],"this":[62],"gap,":[63],"we":[64,161],"present":[65],"OpenSurgery,":[66],"by":[67,139,191],"far":[68],"largest":[70],"video-text":[71],"pretraining":[72],"evaluation":[74],"dataset":[75,113],"surgery":[78,95,120,178,245],"understanding.":[79,179,246],"OpenSurgery":[80,135],"consists":[81,89],"two":[83],"subsets:":[84],"OpenSurgery-Pretrain":[85,88],"OpenSurgery-EVAL.":[87],"843":[91],"publicly":[92],"available":[93],"videos":[96],"pretraining,":[98],"spanning":[99],"102":[100],"hours":[101],"encompassing":[103],"over":[104],"20":[105],"distinct":[106],"types.":[108],"OpenSurgery-EVAL":[109],"a":[111,182,198],"benchmark":[112],"evaluating":[115],"model":[116],"performance":[117,219],"understanding,":[121],"comprising":[122],"280":[123],"training":[124],"120":[126],"test":[127],"videos,":[128],"totaling":[129],"49":[130],"hours.":[131],"Each":[132],"video":[133],"meticulously":[137],"annotated":[138],"expert":[140],"surgeons":[141],"at":[142],"three":[143],"hierarchical":[144],"levels":[145],"video,":[147],"operation,":[148],"frame":[150],"ensure":[152],"both":[153],"high":[154],"quality":[155],"strong":[157,238],"clinical":[158],"applicability.":[159],"Next,":[160],"propose":[162],"Hierarchical":[164],"Surgical":[165],"Knowledge":[166],"Pretraining":[167],"(HierSKP)":[168],"framework":[169],"facilitate":[171],"large-scale":[172],"multimodal":[173],"representation":[174],"learning":[175,185],"HierSKP":[180,216],"leverages":[181],"granularity-aware":[183],"contrastive":[184],"strategy":[186],"enhances":[188],"procedural":[189],"comprehension":[190],"constructing":[192],"hard":[193],"negative":[194],"samples":[195],"incorporating":[197],"Dynamic":[199],"Time":[200],"Warping":[201],"(DTW)-based":[202],"loss":[203],"capture":[205],"fine-grained":[206],"temporal":[207,228],"alignment":[208],"visual":[210],"semantics.":[211],"Extensive":[212],"experiments":[213],"show":[214],"that":[215],"achieves":[217],"state-of-the-art":[218],"on":[220],"OpenSurgegy-EVAL":[221],"across":[222],"multiple":[223],"tasks,":[224],"including":[225],"operation":[226],"recognition,":[227],"action":[229],"localization,":[230],"zero-shot":[232],"cross-modal":[233],"retrieval.":[234],"This":[235],"demonstrates":[236],"generalizability":[239],"further":[241]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-02-08T00:00:00"}
