{"id":"https://openalex.org/W4415540810","doi":"https://doi.org/10.1145/3746027.3755626","title":"MESH - Understanding Videos Like Human: Measuring Hallucinations in Large Video Models","display_name":"MESH - Understanding Videos Like Human: Measuring Hallucinations in Large Video Models","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540810","doi":"https://doi.org/10.1145/3746027.3755626"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755626","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755626","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3755626","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Garry Yang","orcid":"https://orcid.org/0009-0000-9534-6765"},"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":"Garry Yang","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0009-0000-9534-6765","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zizhe Chen","orcid":"https://orcid.org/0009-0005-7032-1525"},"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":"Zizhe Chen","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0009-0005-7032-1525","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111959714","display_name":"Man Hon Wong","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":"Man Hon Wong","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0009-0000-8553-6004","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Haoyu Lei","orcid":"https://orcid.org/0009-0009-1393-2273"},"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":"Haoyu Lei","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0009-0009-1393-2273","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100611594","display_name":"Yongqiang Chen","orcid":"https://orcid.org/0000-0003-2485-3529"},"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":"Yongqiang Chen","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0003-2485-3529","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103196797","display_name":"Zhenguo Li","orcid":"https://orcid.org/0000-0002-8492-3069"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenguo Li","raw_affiliation_strings":["Huawei Noah's Ark Lab, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-8492-3069","affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kaiwen Zhou","orcid":"https://orcid.org/0000-0002-3088-8085"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaiwen Zhou","raw_affiliation_strings":["Huawei Noah's Ark Lab, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-3088-8085","affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016082884","display_name":"James Cheng","orcid":"https://orcid.org/0000-0001-6313-6288"},"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":"James Cheng","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-6313-6288","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4827","last_page":"4836"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9861999750137329,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9861999750137329,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9825000166893005,"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/T12859","display_name":"Cell Image Analysis Techniques","score":0.9587000012397766,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6158000230789185},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.6074000000953674},{"id":"https://openalex.org/keywords/visual-hallucination","display_name":"Visual Hallucination","score":0.4113999903202057},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.4036000072956085},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3637999892234802},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.33629998564720154}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7590000033378601},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6158000230789185},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.6074000000953674},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5253999829292297},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4147000014781952},{"id":"https://openalex.org/C2908998935","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Visual Hallucination","level":2,"score":0.4113999903202057},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.4036000072956085},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3637999892234802},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.33629998564720154},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.32749998569488525},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.31200000643730164},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3019999861717224},{"id":"https://openalex.org/C2780760462","wikidata":"https://www.wikidata.org/wiki/Q7927952","display_name":"Video modeling","level":4,"score":0.2703000009059906},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2565000057220459}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755626","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755626","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3746027.3755626","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755626","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1578285471","https://openalex.org/W3034636873","https://openalex.org/W3203774379","https://openalex.org/W3216130706","https://openalex.org/W4309674289","https://openalex.org/W4322718191","https://openalex.org/W4382132560","https://openalex.org/W4386555501","https://openalex.org/W4387929281","https://openalex.org/W4388110348","https://openalex.org/W4388585881","https://openalex.org/W4389157280","https://openalex.org/W4389523832","https://openalex.org/W4390489684","https://openalex.org/W4390873290","https://openalex.org/W4391766565","https://openalex.org/W4392172801","https://openalex.org/W4392972049","https://openalex.org/W4396813518","https://openalex.org/W4397028102","https://openalex.org/W4399318000","https://openalex.org/W4399553980","https://openalex.org/W4399794640","https://openalex.org/W4400023822","https://openalex.org/W4402670320","https://openalex.org/W4402670751","https://openalex.org/W4402716370","https://openalex.org/W4402727142","https://openalex.org/W4402727904","https://openalex.org/W4402754238","https://openalex.org/W4403784016","https://openalex.org/W4404330874","https://openalex.org/W4404570580","https://openalex.org/W4404988057","https://openalex.org/W4405029492"],"related_works":[],"abstract_inverted_index":{"Large":[0,10],"Video":[1],"Models":[2,12],"(LVMs)":[3],"build":[4],"on":[5,46],"the":[6,53],"semantic":[7],"capabilities":[8],"of":[9,49],"Language":[11],"(LLMs)":[13],"and":[14,81,86,100,115,135],"vision":[15],"modules":[16],"by":[17],"integrating":[18],"temporal":[19],"information":[20],"to":[21,33,68,139],"better":[22],"understand":[23],"dynamic":[24],"video":[25,42,50,106,122],"content.":[26],"Despite":[27],"their":[28,137],"progress,":[29],"LVMs":[30,72,129],"are":[31],"prone":[32],"hallucinations-producing":[34],"inaccurate":[35],"or":[36,147],"irrelevant":[37],"descriptions.":[38],"Current":[39],"benchmarks":[40],"for":[41,118],"hallucination":[43],"depend":[44],"heavily":[45],"manual":[47],"categorization":[48],"content,":[51],"neglecting":[52],"perception-based":[54],"processes":[55],"through":[56],"which":[57],"humans":[58],"naturally":[59],"interpret":[60],"videos.":[61,156],"We":[62,108],"introduce":[63],"MESH,":[64],"a":[65,76,91],"benchmark":[66,158],"designed":[67],"evaluate":[69],"hallucinations":[70,120,140],"in":[71,121,154],"systematically.":[73],"MESH":[74,111],"uses":[75],"Question-Answering":[77],"framework":[78],"with":[79,104],"binary":[80],"multi-choice":[82],"formats":[83],"incorporating":[84],"target":[85],"trap":[87],"instances.":[88],"It":[89],"follows":[90],"bottom-up":[92],"approach,":[93],"evaluating":[94],"basic":[95,133],"objects,":[96],"coarse-to-fine":[97],"subject":[98],"features,":[99,136],"subject-action":[101],"pairs,":[102],"aligning":[103,148],"human":[105],"understanding.":[107,123],"demonstrate":[109],"that":[110,127],"offers":[112],"an":[113],"effective":[114],"comprehensive":[116],"approach":[117],"identifying":[119],"Our":[124],"evaluations":[125],"show":[126],"while":[128],"excel":[130],"at":[131,161],"recognizing":[132],"objects":[134],"susceptibility":[138],"increases":[141],"markedly":[142],"when":[143],"handling":[144],"fine":[145],"details":[146],"multiple":[149],"actions":[150],"involving":[151],"various":[152],"subjects":[153],"longer":[155],"The":[157],"is":[159],"available":[160],"MESH-Benchmark.":[162]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}