{"id":"https://openalex.org/W4417054529","doi":"https://doi.org/10.48550/arxiv.2503.24008","title":"H2VU-Benchmark: A Comprehensive Benchmark for Hierarchical Holistic Video Understanding","display_name":"H2VU-Benchmark: A Comprehensive Benchmark for Hierarchical Holistic Video Understanding","publication_year":2025,"publication_date":"2025-03-31","ids":{"openalex":"https://openalex.org/W4417054529","doi":"https://doi.org/10.48550/arxiv.2503.24008"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2503.24008","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.24008","pdf_url":"https://arxiv.org/pdf/2503.24008","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/2503.24008","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038194678","display_name":"Qilin Wu","orcid":"https://orcid.org/0000-0002-7625-8919"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wu, Qi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038810646","display_name":"Quanlong Zheng","orcid":"https://orcid.org/0000-0001-5059-0078"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Quanlong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5118216947","display_name":"Yanhao Zhang","orcid":"https://orcid.org/0000-0002-6239-8953"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yanhao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014208479","display_name":"Junlin Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Junlin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001147139","display_name":"Jinguo Luo","orcid":"https://orcid.org/0009-0007-4069-1984"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Jinguo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073712729","display_name":"Kuo Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Kuo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120779458","display_name":"Peng Liu","orcid":"https://orcid.org/0009-0004-4104-8067"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Peng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102359689","display_name":"Qingsong Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Qingsong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051667993","display_name":"Ru Zhen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhen, Ru","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047923133","display_name":"Zhenyu Yang","orcid":"https://orcid.org/0009-0000-0006-8214"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Zhenyu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5007720098","display_name":"H. Lu","orcid":"https://orcid.org/0000-0001-6332-2785"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Haonan","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5038194678"],"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":0.8924000263214111,"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":0.8924000263214111,"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":0.02419999986886978,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.01769999973475933,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7138000130653381},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.6169000267982483},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5342000126838684},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5059999823570251},{"id":"https://openalex.org/keywords/pace","display_name":"Pace","score":0.48179998993873596},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.38690000772476196},{"id":"https://openalex.org/keywords/clips","display_name":"CLIPS","score":0.3788999915122986},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.33640000224113464}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8095999956130981},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7138000130653381},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.6169000267982483},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5342000126838684},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5059999823570251},{"id":"https://openalex.org/C2777526511","wikidata":"https://www.wikidata.org/wiki/Q691543","display_name":"Pace","level":2,"score":0.48179998993873596},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.40860000252723694},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4065999984741211},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.38690000772476196},{"id":"https://openalex.org/C2778739407","wikidata":"https://www.wikidata.org/wiki/Q165372","display_name":"CLIPS","level":2,"score":0.3788999915122986},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.33640000224113464},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.33320000767707825},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.33090001344680786},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.323199987411499},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3118000030517578},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.31029999256134033},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.30250000953674316},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.29809999465942383},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29670000076293945},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.2935999929904938},{"id":"https://openalex.org/C2986160907","wikidata":"https://www.wikidata.org/wiki/Q220499","display_name":"Video streaming","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.26600000262260437},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2503.24008","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.24008","pdf_url":"https://arxiv.org/pdf/2503.24008","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.2503.24008","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.24008","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.24008","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.24008","pdf_url":"https://arxiv.org/pdf/2503.24008","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,7,38,93,123,139,157],"rapid":[2,140],"development":[3],"of":[4,41,142,159,212],"multimodal":[5,160,178],"models,":[6],"demand":[8],"for":[9,21,113,156,186],"assessing":[10],"video":[11,23,44,57,66,70,79,133,151,202],"understanding":[12,24,45,58,126,164,203],"capabilities":[13,127],"has":[14],"been":[15],"steadily":[16],"increasing.":[17],"However,":[18],"existing":[19,177],"benchmarks":[20],"evaluating":[22],"exhibit":[25],"significant":[26],"limitations":[27],"in":[28,97,163,188,201],"coverage,":[29],"task":[30],"diversity,":[31],"and":[32,55,67,106,116,209],"scene":[33],"adaptability.":[34],"These":[35,120],"shortcomings":[36],"hinder":[37],"accurate":[39],"assessment":[40,101],"models'":[42,124,161],"comprehensive":[43,88,208],"capabilities.":[46],"To":[47,135],"tackle":[48],"this":[49],"challenge,":[50],"we":[51,109,146],"propose":[52],"a":[53,168,207],"hierarchical":[54],"holistic":[56],"(H2VU)":[59],"benchmark":[60,73],"designed":[61],"to":[62,87],"evaluate":[63],"both":[64],"general":[65],"online":[68],"streaming":[69,150,165],"comprehension.":[71],"This":[72,153],"contributes":[74],"three":[75],"key":[76],"features:":[77],"Extended":[78],"duration:":[80],"Spanning":[81],"videos":[82,166],"from":[83,167,173],"brief":[84],"3-second":[85],"clips":[86],"1.5-hour":[89],"recordings,":[90],"thereby":[91],"bridging":[92],"temporal":[94],"gaps":[95],"found":[96],"current":[98,143],"benchmarks.":[99],"Comprehensive":[100],"tasks:":[102],"Beyond":[103],"traditional":[104],"perceptual":[105],"reasoning":[107],"tasks,":[108],"have":[110,147],"introduced":[111],"modules":[112],"countercommonsense":[114],"comprehension":[115],"trajectory":[117],"state":[118],"tracking.":[119],"additions":[121],"test":[122],"deep":[125],"beyond":[128],"mere":[129],"prior":[130],"knowledge.":[131],"Enriched":[132],"data:":[134],"keep":[136],"pace":[137],"with":[138],"evolution":[141],"AI":[144],"agents,":[145],"expanded":[148],"first-person":[149,169],"datasets.":[152],"expansion":[154],"allows":[155],"exploration":[158],"performance":[162],"perspective.":[170],"Extensive":[171],"results":[172],"H2VU":[174,197],"reveal":[175],"that":[176,196],"large":[179],"language":[180],"models":[181],"(MLLMs)":[182],"possess":[183],"substantial":[184],"potential":[185],"improvement":[187],"our":[189],"newly":[190],"proposed":[191],"evaluation":[192],"tasks.":[193],"We":[194],"expect":[195],"will":[198],"facilitate":[199],"advancements":[200],"research":[204],"by":[205],"offering":[206],"in-depth":[210],"analysis":[211],"MLLMs.":[213]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}