{"id":"https://openalex.org/W4382762629","doi":"https://doi.org/10.48550/arxiv.2306.16741","title":"Foundation Model for Endoscopy Video Analysis via Large-scale Self-supervised Pre-train","display_name":"Foundation Model for Endoscopy Video Analysis via Large-scale Self-supervised Pre-train","publication_year":2023,"publication_date":"2023-06-29","ids":{"openalex":"https://openalex.org/W4382762629","doi":"https://doi.org/10.48550/arxiv.2306.16741"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2306.16741","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2306.16741","pdf_url":"https://arxiv.org/pdf/2306.16741","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2306.16741","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100434562","display_name":"Zhao Wang","orcid":"https://orcid.org/0000-0003-1067-4589"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wang, Zhao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100785985","display_name":"Chang Liu","orcid":"https://orcid.org/0000-0002-0219-959X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Chang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066553616","display_name":"Shaoting Zhang","orcid":"https://orcid.org/0000-0002-8719-448X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Shaoting","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5090516040","display_name":"Qi Dou","orcid":"https://orcid.org/0000-0002-3416-9950"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dou, Qi","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100434562"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10552","display_name":"Colorectal Cancer Screening and Detection","score":0.9864000082015991,"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":0.9864000082015991,"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":0.7342321276664734},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7313539385795593},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6387916803359985},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6347434520721436},{"id":"https://openalex.org/keywords/dice","display_name":"Dice","score":0.5366603136062622},{"id":"https://openalex.org/keywords/f1-score","display_name":"F1 score","score":0.5003888607025146},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4836038649082184},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44431987404823303},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3813651204109192}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7342321276664734},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7313539385795593},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6387916803359985},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6347434520721436},{"id":"https://openalex.org/C22029948","wikidata":"https://www.wikidata.org/wiki/Q45089","display_name":"Dice","level":2,"score":0.5366603136062622},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.5003888607025146},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4836038649082184},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44431987404823303},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3813651204109192},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2306.16741","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2306.16741","pdf_url":"https://arxiv.org/pdf/2306.16741","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},{"id":"doi:10.48550/arxiv.2306.16741","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2306.16741","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2306.16741","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2306.16741","pdf_url":"https://arxiv.org/pdf/2306.16741","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.5400000214576721},{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.41999998688697815}],"awards":[{"id":"https://openalex.org/G5341622981","display_name":null,"funder_award_id":"HZQB-KCZYB-20200089","funder_id":"https://openalex.org/F4320326705","funder_display_name":"Science, Technology and Innovation Commission of Shenzhen Municipality"}],"funders":[{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"},{"id":"https://openalex.org/F4320321920","display_name":"Innovation and Technology Commission","ror":"https://ror.org/04vf9tr09"},{"id":"https://openalex.org/F4320326705","display_name":"Science, Technology and Innovation Commission of Shenzhen Municipality","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3104750253","https://openalex.org/W3021239166","https://openalex.org/W2586273397","https://openalex.org/W4366341510","https://openalex.org/W2390936256","https://openalex.org/W2483429559","https://openalex.org/W2016385589","https://openalex.org/W2009559548","https://openalex.org/W4287854475","https://openalex.org/W3186737058"],"abstract_inverted_index":{"Foundation":[0],"models":[1,230],"have":[2],"exhibited":[3],"remarkable":[4],"success":[5],"in":[6,121],"various":[7,140],"applications,":[8],"such":[9,198],"as":[10,163,199],"disease":[11,145],"diagnosis":[12],"and":[13,55,61,72,87,110,144,178,189,205,211,213,219,225,229],"text":[14],"report":[15],"generation.":[16],"To":[17,92],"date,":[18],"a":[19,35,48,76,99,111,155,195],"foundation":[20,36,95],"model":[21,37,69],"for":[22,154,208,222],"endoscopic":[23,42],"video":[24,43,49,102,131],"analysis":[25],"is":[26],"still":[27],"lacking.":[28],"In":[29],"this":[30],"paper,":[31],"we":[32,46,65,97],"propose":[33],"Endo-FM,":[34],"specifically":[38],"developed":[39],"using":[40,70],"massive":[41],"data.":[44],"First,":[45],"build":[47],"transformer,":[50],"which":[51],"captures":[52],"both":[53],"local":[54,73],"global":[56,71],"long-range":[57],"dependencies":[58],"across":[59,89],"spatial":[60],"temporal":[62],"dimensions.":[63],"Second,":[64],"pre-train":[66],"our":[67,180],"transformer":[68],"views":[74],"via":[75,159],"self-supervised":[77,187],"manner,":[78],"aiming":[79],"to":[80,84,135],"make":[81],"it":[82],"robust":[83],"spatial-temporal":[85],"variations":[86],"discriminative":[88],"different":[90,170],"scenes.":[91],"develop":[93],"the":[94,164,183],"model,":[96],"construct":[98],"large-scale":[100],"endoscopy":[101],"dataset":[103,114,125],"by":[104,161,194],"combining":[105],"9":[106],"publicly":[107],"available":[108],"datasets":[109],"privately":[112],"collected":[113],"from":[115],"Baoshan":[116],"Branch":[117],"of":[118,128,172],"Renji":[119],"Hospital":[120],"Shanghai,":[122],"China.":[123],"Our":[124,147],"overall":[126],"consists":[127],"over":[129],"33K":[130],"clips":[132],"with":[133],"up":[134],"5":[136],"million":[137],"frames,":[138],"encompassing":[139],"protocols,":[141],"target":[142],"organs,":[143],"types.":[146],"pre-trained":[148],"Endo-FM":[149,181],"can":[150],"be":[151],"easily":[152],"adopted":[153],"given":[156],"downstream":[157,173],"task":[158],"fine-tuning":[160],"serving":[162],"backbone.":[165],"With":[166],"experiments":[167],"on":[168],"3":[169],"types":[171],"tasks,":[174],"including":[175],"classification,":[176,209,223],"segmentation,":[177,210,224],"detection,":[179],"surpasses":[182],"current":[184],"state-of-the-art":[185],"(SOTA)":[186],"pre-training":[188],"adapter-based":[190],"transfer":[191],"learning":[192],"methods":[193],"significant":[196],"margin,":[197],"VCL":[200],"(3.1%":[201],"F1,":[202,216],"4.8%":[203],"Dice,":[204,218],"5.5%":[206],"F1":[207,221],"detection)":[212],"ST-Adapter":[214],"(5.9%":[215],"9.6%":[217],"9.9%":[220],"detection).":[226],"Code,":[227],"datasets,":[228],"are":[231],"released":[232],"at":[233],"https://github.com/med-air/Endo-FM.":[234]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}