{"id":"https://openalex.org/W7161809552","doi":"https://doi.org/10.1109/isbi61048.2026.11515743","title":"Evidence-Grounded Temporal Reasoning in Operating Room Long Video Understanding","display_name":"Evidence-Grounded Temporal Reasoning in Operating Room Long Video Understanding","publication_year":2026,"publication_date":"2026-04-08","ids":{"openalex":"https://openalex.org/W7161809552","doi":"https://doi.org/10.1109/isbi61048.2026.11515743"},"language":null,"primary_location":{"id":"doi:10.1109/isbi61048.2026.11515743","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isbi61048.2026.11515743","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE 23rd 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/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":["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/A5089926157","display_name":"J J 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":["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/A5136556566","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":["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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.61360151,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.4650000035762787,"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":0.4650000035762787,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.061500001698732376,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.0560000017285347,"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/key","display_name":"Key (lock)","score":0.2777999937534332},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.27730000019073486},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.23270000517368317},{"id":"https://openalex.org/keywords/window","display_name":"Window (computing)","score":0.21729999780654907},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.21459999680519104}],"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/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4887999892234802},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35740000009536743},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2484000027179718},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.23270000517368317},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.21729999780654907},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.21459999680519104},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.21410000324249268}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isbi61048.2026.11515743","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isbi61048.2026.11515743","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE 23rd International Symposium on Biomedical Imaging (ISBI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W4296195896","https://openalex.org/W4387321091","https://openalex.org/W4402713111","https://openalex.org/W4403725941","https://openalex.org/W4410369527","https://openalex.org/W4413156101","https://openalex.org/W4414379518","https://openalex.org/W7155652131","https://openalex.org/W7160173378"],"related_works":[],"abstract_inverted_index":{"Operating":[0],"rooms":[1],"(OR)":[2],"are":[3],"complex,":[4],"high-risk":[5],"environments":[6],"that":[7,104],"demand":[8],"long-horizon":[9],"video":[10,152],"understanding":[11,78],"for":[12,76,147],"intelligent":[13],"surgical":[14,65],"assistance":[15],"and":[16,23,60,85,100,108,140,145],"quality":[17],"assurance.":[18],"Existing":[19],"domainspecific":[20],"OR":[21],"models":[22,47],"datasets":[24],"mainly":[25],"address":[26],"short-clip":[27],"or":[28],"frame-level":[29],"analysis,":[30],"lacking":[31],"the":[32,57,115,124],"ability":[33],"to":[34,55,64],"reason":[35],"across":[36],"extended":[37],"temporal":[38,51,97],"contexts.":[39],"In":[40],"contrast,":[41],"general":[42],"long-video":[43,77],"multimodal":[44],"large":[45],"language":[46],"(MLLMs)":[48],"exhibit":[49],"strong":[50],"reasoning":[52,92,102,117,138],"but":[53],"fail":[54],"capture":[56],"structured":[58,149],"interactions":[59],"clinical":[61],"semantics":[62],"unique":[63],"workflows.":[66],"To":[67],"bridge":[68],"this":[69],"gap,":[70],"we":[71],"introduce":[72],"OR-LongVQA,":[73],"a":[74,91],"benchmark":[75],"in":[79,136],"operating":[80,150],"rooms,":[81],"covering":[82],"diverse":[83],"factors":[84],"causality-centered":[86],"questions.":[87],"We":[88,113],"further":[89],"propose":[90],"retrieval":[93],"framework":[94,118],"based":[95],"on":[96,123],"scene":[98],"graph":[99],"evidence-grounded":[101],"modules":[103],"retrieve":[105],"relevant":[106],"subgraphs":[107],"perform":[109],"interpretable":[110],"step-by-step":[111],"inference.":[112],"compare":[114],"proposed":[116],"with":[119],"existing":[120],"state-of-the-art":[121],"methods":[122,131],"OR-LongVQA":[125],"benchmark.":[126],"Our":[127],"approach":[128],"outperforms":[129],"prior":[130],"by":[132],"achieving":[133],"significant":[134],"improvements":[135],"longhorizon":[137],"accuracy":[139],"interpretability,":[141],"demonstrating":[142],"its":[143],"effectiveness":[144],"reliability":[146],"clinically-oriented,":[148],"room":[151],"understanding.":[153]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-05-21T00:00:00"}