{"id":"https://openalex.org/W4415901680","doi":"https://doi.org/10.18653/v1/2026.findings-acl.965","title":"LongInsightBench: A Comprehensive Benchmark for Evaluating Omni-Modal Models on Human-Centric Long-Video Understanding.","display_name":"LongInsightBench: A Comprehensive Benchmark for Evaluating Omni-Modal Models on Human-Centric Long-Video Understanding.","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4415901680","doi":"https://doi.org/10.18653/v1/2026.findings-acl.965"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.965","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.965","pdf_url":"https://aclanthology.org/2026.findings-acl.965.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.965.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"ZhaoYang Han","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"ZhaoYang Han","raw_affiliation_strings":["Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qihan Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qihan Lin","raw_affiliation_strings":["Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101925133","display_name":"Hao Liang","orcid":"https://orcid.org/0000-0002-8097-4707"},"institutions":[{"id":"https://openalex.org/I166382143","display_name":"Moscow State University of Printing Arts","ror":"https://ror.org/02e16wz39","country_code":"RU","type":"education","lineage":["https://openalex.org/I166382143"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN","RU"],"is_corresponding":false,"raw_author_name":"Hao Liang","raw_affiliation_strings":["Peking University","Zhongguancun Academy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Zhongguancun Academy","institution_ids":["https://openalex.org/I166382143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034339449","display_name":"Bowen Chen","orcid":"https://orcid.org/0009-0000-5827-6593"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bowen Chen","raw_affiliation_strings":["Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100712549","display_name":"Zhou Liu","orcid":"https://orcid.org/0000-0002-4651-1370"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou Liu","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008772211","display_name":"Wentao Zhang","orcid":"https://orcid.org/0000-0002-7532-5550"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wentao Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"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":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01389286,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"19332","last_page":"19358"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9492999911308289,"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":0.9492999911308289,"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":0.013399999588727951,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.012600000016391277,"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/benchmark","display_name":"Benchmark (surveying)","score":0.7982000112533569},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.621999979019165},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6169000267982483},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6115000247955322},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5411999821662903},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4072999954223633},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.39640000462532043},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.39100000262260437},{"id":"https://openalex.org/keywords/quality-assurance","display_name":"Quality assurance","score":0.38499999046325684}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7982000112533569},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7741000056266785},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.621999979019165},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6169000267982483},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6115000247955322},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5940999984741211},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5516999959945679},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5411999821662903},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44760000705718994},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4072999954223633},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.39640000462532043},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.39100000262260437},{"id":"https://openalex.org/C106436119","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assurance","level":3,"score":0.38499999046325684},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.36329999566078186},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3562000095844269},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.31279999017715454},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.30820000171661377},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.29980000853538513},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.29330000281333923},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.27649998664855957},{"id":"https://openalex.org/C2982962833","wikidata":"https://www.wikidata.org/wiki/Q17092450","display_name":"Information fusion","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.25940001010894775},{"id":"https://openalex.org/C2780795517","wikidata":"https://www.wikidata.org/wiki/Q6030997","display_name":"Information assurance","level":3,"score":0.25440001487731934},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.2533999979496002}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.965","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.965","pdf_url":"https://aclanthology.org/2026.findings-acl.965.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.17305","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.17305","pdf_url":"https://arxiv.org/pdf/2510.17305","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2510.17305","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.17305","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.965","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.965","pdf_url":"https://aclanthology.org/2026.findings-acl.965.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2981796383","display_name":null,"funder_award_id":"62402016","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4572520933","display_name":null,"funder_award_id":"92470121","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"},{"id":"https://openalex.org/F4320321106","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934"},{"id":"https://openalex.org/F4320324787","display_name":"Peking University","ror":"https://ror.org/02v51f717"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415901680.pdf","grobid_xml":"https://content.openalex.org/works/W4415901680.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,44,83,102],"introduce":[1],"LongInsightBench,":[2,126],"the":[3,114,119,155,166],"first":[4],"benchmark":[5,34],"designed":[6,85,128],"to":[7,11,112],"assess":[8],"models'":[9],"ability":[10],"understand":[12],"long":[13],"videos,":[14],"with":[15],"a":[16,105,129],"focus":[17],"on":[18,55,63,125],"human":[19],"language,":[20],"viewpoints,":[21],"actions,":[22],"and":[23,31,58,68,75,79,93,97,116,122,147],"other":[24],"contextual":[25,76],"elements,":[26],"while":[27],"integrating":[28],"visual,":[29],"audio,":[30],"text":[32],"modalities.Our":[33],"excels":[35],"in":[36,140,158],"three":[37],"key":[38],"areas:":[39],"a)":[40],"Long-Duration,":[41],"Human-Centric":[42],"Videos:":[43],"carefully":[45],"selected":[46],"approximately":[47],"1,000":[48],"videos":[49],"from":[50],"opensource":[51],"datasets":[52],"FineVideo":[53],"based":[54],"duration":[56],"limit":[57],"multi-modal":[59],"information":[60,156],"density,":[61],"focusing":[62],"content":[64],"like":[65],"lectures,":[66],"interviews,":[67],"vlogs,":[69],"which":[70,163],"contain":[71],"rich":[72],"human-centric":[73],"semantic":[74],"attributes.b)":[77],"Diverse":[78],"Challenging":[80],"Task":[81],"Scenarios:":[82],"have":[84,103],"six":[86],"challenging":[87],"task":[88],"scenarios,":[89],"including":[90],"both":[91],"Intra-Event":[92],"Inter-Event":[94],"Tasks.c)":[95],"Rigorous":[96],"Comprehensive":[98],"Quality":[99],"Assurance":[100],"Pipelines:":[101],"developed":[104],"threestep,":[106],"semi-automated":[107],"data":[108],"quality":[109],"assurance":[110],"pipeline":[111],"ensure":[113],"difficulty":[115],"validity":[117],"of":[118,131,161],"synthesized":[120],"questions":[121],"answer":[123],"options.Based":[124],"we":[127,164],"series":[130],"experiments.which":[132],"shows":[133],"that":[134],"Omnimodal":[135],"models(OLMs)":[136],"still":[137],"face":[138],"challenge":[139],"tasks":[141],"requiring":[142],"precise":[143],"temporal":[144],"localization":[145],"(T-Loc)":[146],"long-range":[148],"causal":[149],"inference":[150],"(CE-Caus).Surprisingly,":[151],"extended":[152],"experiments":[153],"reveal":[154],"loss":[157],"modal":[159],"fusion":[160],"OLMs,":[162],"called":[165],"Fusion":[167],"Deficit":[168],"Paradox.":[169],"1":[170],"*":[171],"These":[172],"authors":[173],"contributed":[174],"equally.":[175]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-22T00:00:00"}