{"id":"https://openalex.org/W4417517005","doi":"https://doi.org/10.48550/arxiv.2505.07449","title":"Ophora: A Large-Scale Data-Driven Text-Guided Ophthalmic Surgical Video Generation Model","display_name":"Ophora: A Large-Scale Data-Driven Text-Guided Ophthalmic Surgical Video Generation Model","publication_year":2025,"publication_date":"2025-05-12","ids":{"openalex":"https://openalex.org/W4417517005","doi":"https://doi.org/10.48550/arxiv.2505.07449"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2505.07449","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.07449","pdf_url":"https://arxiv.org/pdf/2505.07449","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.07449","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100318395","display_name":"Wei Li","orcid":"https://orcid.org/0000-0003-2091-8188"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Li, Wei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002996984","display_name":"Ming Hu","orcid":"https://orcid.org/0000-0003-0987-2916"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Ming","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101966262","display_name":"Guoan Wang","orcid":"https://orcid.org/0000-0002-4890-8638"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Guoan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085516582","display_name":"Lihao Liu","orcid":"https://orcid.org/0000-0002-8983-2342"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Lihao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024265110","display_name":"Kaijing Zhou","orcid":"https://orcid.org/0000-0002-6989-4255"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Kaijing","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101263879","display_name":"Junzhi Ning","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ning, Junzhi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033578694","display_name":"Xin Guo","orcid":"https://orcid.org/0000-0002-5563-6060"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Xin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005014252","display_name":"Zongyuan Ge","orcid":"https://orcid.org/0000-0002-5880-8673"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ge, Zongyuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048833501","display_name":"L. M. Gu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gu, Lixu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5056327997","display_name":"Junjun He","orcid":"https://orcid.org/0000-0002-1813-1784"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Junjun","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5100318395"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8981000185012817,"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":0.8981000185012817,"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":0.01899999938905239,"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/T10916","display_name":"Surgical Simulation and Training","score":0.01140000019222498,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.6802999973297119},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5767999887466431},{"id":"https://openalex.org/keywords/ophthalmic-surgery","display_name":"Ophthalmic surgery","score":0.5022000074386597},{"id":"https://openalex.org/keywords/video-recording","display_name":"Video recording","score":0.39649999141693115},{"id":"https://openalex.org/keywords/surgical-procedures","display_name":"Surgical procedures","score":0.3529999852180481},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.3434000015258789}],"concepts":[{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6802999973297119},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5767999887466431},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5072000026702881},{"id":"https://openalex.org/C2994218517","wikidata":"https://www.wikidata.org/wiki/Q760348","display_name":"Ophthalmic surgery","level":2,"score":0.5022000074386597},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.4339999854564667},{"id":"https://openalex.org/C2988634675","wikidata":"https://www.wikidata.org/wiki/Q34508","display_name":"Video recording","level":2,"score":0.39649999141693115},{"id":"https://openalex.org/C3019611579","wikidata":"https://www.wikidata.org/wiki/Q6641956","display_name":"Surgical procedures","level":2,"score":0.3529999852180481},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.3434000015258789},{"id":"https://openalex.org/C2778181360","wikidata":"https://www.wikidata.org/wiki/Q1074814","display_name":"Surgical instrument","level":2,"score":0.322299987077713},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3061000108718872},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.29809999465942383},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.28760001063346863},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C19527891","wikidata":"https://www.wikidata.org/wiki/Q1120908","display_name":"Medical physics","level":1,"score":0.25699999928474426},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2505.07449","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.07449","pdf_url":"https://arxiv.org/pdf/2505.07449","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.07449","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.07449","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:2505.07449","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.07449","pdf_url":"https://arxiv.org/pdf/2505.07449","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0,58],"ophthalmic":[1,18,51,70,91,129,155,174],"surgery,":[2],"developing":[3],"an":[4],"AI":[5],"system":[6],"capable":[7],"of":[8,167,173],"interpreting":[9],"surgical":[10,19,52,71,92,130,156,175],"videos":[11,20,53,72,93,157],"and":[12,33,144,153],"predicting":[13],"subsequent":[14],"operations":[15],"requires":[16],"numerous":[17],"with":[21],"high-quality":[22,97],"annotations,":[23],"which":[24],"are":[25],"difficult":[26],"to":[27,30,45,88,113],"collect":[28],"due":[29],"privacy":[31],"concerns":[32],"labor":[34],"consumption.":[35],"Text-guided":[36],"video":[37,131,138],"generation":[38,132],"(T2V)":[39],"emerges":[40],"as":[41],"a":[42,64,83,95,108,119],"promising":[43],"solution":[44],"overcome":[46],"this":[47,59],"issue":[48],"by":[49],"generating":[50],"based":[54,133,158],"on":[55,123,134,137,159],"surgeon":[56,160],"instructions.":[57,76,161],"paper,":[60],"we":[61,80,106],"present":[62],"Ophora,":[63,79],"pioneering":[65],"model":[66,121],"that":[67,148],"can":[68,150],"generate":[69,151],"following":[73],"natural":[74,124],"language":[75],"To":[77],"construct":[78],"first":[81],"propose":[82,107],"Comprehensive":[84],"Data":[85],"Curation":[86],"pipeline":[87],"convert":[89],"narrative":[90],"into":[94],"large-scale,":[96],"dataset":[98],"comprising":[99],"over":[100],"160K":[101],"video-instruction":[102],"pairs,":[103],"Ophora-160K.":[104,135],"Then,":[105],"Progressive":[109],"Video-Instruction":[110],"Tuning":[111],"scheme":[112],"transfer":[114],"rich":[115],"spatial-temporal":[116],"knowledge":[117],"from":[118],"T2V":[120],"pre-trained":[122],"video-text":[125],"datasets":[126],"for":[127,169],"privacy-preserved":[128],"Experiments":[136],"quality":[139],"evaluation":[140],"via":[141],"quantitative":[142],"analysis":[143],"ophthalmologist":[145],"feedback":[146],"demonstrate":[147],"Ophora":[149,168],"realistic":[152],"reliable":[154],"We":[162],"also":[163],"validate":[164],"the":[165],"capability":[166],"empowering":[170],"downstream":[171],"tasks":[172],"workflow":[176],"understanding.":[177],"Code":[178],"is":[179],"available":[180],"at":[181],"https://github.com/uni-medical/Ophora.":[182]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}