{"id":"https://openalex.org/W4412695717","doi":"https://doi.org/10.1109/tpami.2025.3592831","title":"WildVideo: Benchmarking LMMs for Understanding Video-Language Interaction","display_name":"WildVideo: Benchmarking LMMs for Understanding Video-Language Interaction","publication_year":2025,"publication_date":"2025-07-25","ids":{"openalex":"https://openalex.org/W4412695717","doi":"https://doi.org/10.1109/tpami.2025.3592831","pmid":"https://pubmed.ncbi.nlm.nih.gov/40711895"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3592831","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3592831","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Songyuan Yang","orcid":"https://orcid.org/0009-0009-0170-3377"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Songyuan Yang","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology, Changsha, Hunan, China"],"raw_orcid":"https://orcid.org/0009-0009-0170-3377","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055989750","display_name":"Weijiang Yu","orcid":"https://orcid.org/0000-0002-7449-3093"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]},{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weijiang Yu","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong, China","College of Computer Science and Technology, National University of Defense Technology, Changsha, Hunan, China"],"raw_orcid":"https://orcid.org/0000-0002-7449-3093","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wenjing Yang","orcid":"https://orcid.org/0000-0002-6997-0406"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]},{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjing Yang","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology, Changsha, Hunan, China","School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0002-6997-0406","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xinwang Liu","orcid":"https://orcid.org/0000-0001-9066-1475"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinwang Liu","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology, Changsha, Hunan, China"],"raw_orcid":"https://orcid.org/0000-0001-9066-1475","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Huibin Tan","orcid":"https://orcid.org/0000-0003-4060-8793"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huibin Tan","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology, Changsha, Hunan, China"],"raw_orcid":"https://orcid.org/0000-0003-4060-8793","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060251766","display_name":"Long Lan","orcid":"https://orcid.org/0000-0002-4238-8985"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long Lan","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology, Changsha, Hunan, China"],"raw_orcid":"https://orcid.org/0000-0002-4238-8985","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":null,"display_name":"Nong Xiao","orcid":"https://orcid.org/0000-0002-2166-977X"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nong Xiao","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0002-2166-977X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15592415,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"47","issue":"10","first_page":"9330","last_page":"9344"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.983299970626831,"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":0.983299970626831,"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/T13629","display_name":"Text Readability and Simplification","score":0.9807999730110168,"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/T10028","display_name":"Topic Modeling","score":0.9714999794960022,"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/computer-science","display_name":"Computer science","score":0.6470898389816284},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.636738121509552},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.6295212507247925},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5730161070823669},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5526509881019592},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.5271249413490295},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.48843446373939514},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46368709206581116},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37170419096946716},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.19923344254493713}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6470898389816284},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.636738121509552},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.6295212507247925},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5730161070823669},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5526509881019592},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.5271249413490295},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.48843446373939514},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46368709206581116},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37170419096946716},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.19923344254493713},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D014741","descriptor_name":"Video Recording","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D014741","descriptor_name":"Video Recording","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019985","descriptor_name":"Benchmarking","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019985","descriptor_name":"Benchmarking","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D032882","descriptor_name":"Comprehension","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D032882","descriptor_name":"Comprehension","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2025.3592831","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3592831","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:40711895","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40711895","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2466138076","display_name":null,"funder_award_id":"62376282","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2337252826","https://openalex.org/W2799067027","https://openalex.org/W4309674289","https://openalex.org/W4389519254","https://openalex.org/W4389519587","https://openalex.org/W4399803256","https://openalex.org/W4401043863","https://openalex.org/W4402670037","https://openalex.org/W4402670320","https://openalex.org/W4402671735","https://openalex.org/W4402713111","https://openalex.org/W4402726948","https://openalex.org/W4402727142","https://openalex.org/W4402772286","https://openalex.org/W4403081466","https://openalex.org/W4404534210","https://openalex.org/W4404544862","https://openalex.org/W4404781340","https://openalex.org/W4404781930","https://openalex.org/W4404784276","https://openalex.org/W4405595839","https://openalex.org/W4405596328","https://openalex.org/W4411892026","https://openalex.org/W4413146669","https://openalex.org/W4413156626"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699","https://openalex.org/W1993948687","https://openalex.org/W2000169967","https://openalex.org/W4399363378"],"abstract_inverted_index":{"We":[0,61,117],"introduce":[1],"WildVideo,":[2,123],"an":[3],"open-world":[4],"benchmark":[5,96],"dataset":[6],"designed":[7],"to":[8,11,114],"address":[9],"how":[10],"assess":[12],"hallucination":[13,36,126],"of":[14,37,98,128],"Large":[15],"Multi-modal":[16],"Models":[17],"(LMMs)":[18],"for":[19],"understanding":[20],"video-language":[21],"interaction":[22],"in":[23,134],"the":[24,30],"wild.":[25],"Our":[26],"WildVideo":[27],"comprehensively":[28],"tests":[29],"perceptual,":[31],"cognitive,":[32],"and":[33,42,58,75,85,109],"contextual":[34,87,91],"comprehension":[35,88],"LMMs":[38,68,121],"through":[39],"both":[40],"single-turn":[41,106],"multi-turn":[43,111],"open-ended":[44],"question-answering":[45],"(QA)":[46],"tasks":[47,65,72,80,89],"on":[48,122],"videos":[49],"captured":[50],"from":[51],"two":[52],"human":[53],"perspectives":[54],"(i.e.":[55],"first-person":[56],"view":[57],"third-person":[59],"view).":[60],"define":[62],"9":[63],"distinct":[64],"that":[66],"challenge":[67],"across":[69],"multi-level":[70],"perceptual":[71],"(e.g.,":[73,81,90],"static":[74],"dynamic":[76],"perception),":[77],"multi-aspect":[78],"cognitive":[79],"commonsense,":[82],"world":[83],"knowledge),":[84],"multi-faceted":[86],"ellipsis,":[92],"cross-turn":[93],"retrieval).":[94],"The":[95],"consists":[97],"1,318":[99],"meticulously":[100],"curated":[101],"videos,":[102],"supplemented":[103],"with":[104],"13,704":[105],"QA":[107],"pairs":[108],"1,585":[110],"dialogues":[112],"(up":[113],"5":[115],"turns).":[116],"evaluated":[118],"14":[119],"commonly-used":[120],"revealing":[124],"significant":[125],"issues":[127],"current":[129,136],"LMMs,":[130],"highlighting":[131],"substantial":[132],"gaps":[133],"their":[135],"capabilities.":[137]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
