{"id":"https://openalex.org/W4415797648","doi":"https://doi.org/10.52202/079017-1684","title":"HourVideo: 1-Hour Video-Language Understanding","display_name":"HourVideo: 1-Hour Video-Language Understanding","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4415797648","doi":"https://doi.org/10.52202/079017-1684"},"language":"en","primary_location":{"id":"doi:10.52202/079017-1684","doi":"https://doi.org/10.52202/079017-1684","is_oa":false,"landing_page_url":"https://doi.org/10.52202/079017-1684","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 37","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2411.04998","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070592728","display_name":"Keshigeyan Chandrasegaran","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Keshigeyan Chandrasegaran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079573718","display_name":"Agrim Gupta","orcid":"https://orcid.org/0000-0002-5213-0224","observed_orcids":["https://orcid.org/0000-0002-5213-0224"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Agrim Gupta","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114640997","display_name":"Lea M. Hadzic","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lea Hadzic","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114640998","display_name":"Taran Kota","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Taran Kota","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Jimming He","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jimming He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075608006","display_name":"Crist\u00f3bal Eyzaguirre","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cristobal Eyzaguirre","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091286087","display_name":"Zane Durante","orcid":"https://orcid.org/0000-0001-9038-8915","observed_orcids":["https://orcid.org/0000-0001-9038-8915"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zane Durante","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Manling Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Manling Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100621605","display_name":"Jiajun Wu","orcid":"https://orcid.org/0000-0002-4176-343X","observed_orcids":["https://orcid.org/0000-0002-4176-343X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiajun Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100450462","display_name":"Li Fei-Fei","orcid":"https://orcid.org/0000-0002-7481-0810","observed_orcids":["https://orcid.org/0000-0002-7481-0810","https://orcid.org/0000-0001-7652-0473"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li Fei-Fei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.2876,"has_fulltext":true,"cited_by_count":52,"citation_normalized_percentile":{"value":0.97821658,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"53168","last_page":"53197"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T10028","display_name":"Topic Modeling","score":0.0,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/egocentric-video","display_name":"egocentric video","score":0.765999972820282},{"id":"https://openalex.org/keywords/video-summarization","display_name":"video summarization","score":0.8650000095367432},{"id":"https://openalex.org/keywords/visual-perception","display_name":"visual perception","score":0.453000009059906},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"visual reasoning","score":0.6919999718666077},{"id":"https://openalex.org/keywords/causal-reasoning","display_name":"causal reasoning","score":0.5989999771118164},{"id":"https://openalex.org/keywords/counterfactual-thinking","display_name":"counterfactual reasoning","score":0.8870000243186951},{"id":"https://openalex.org/keywords/object-retrieval","display_name":"object retrieval","score":0.546999990940094},{"id":"https://openalex.org/keywords/ego4d","display_name":"Ego4D","score":0.7799999713897705},{"id":"https://openalex.org/keywords/benchmark-dataset","display_name":"benchmark dataset","score":0.7429999709129333}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7039999961853027},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.699999988079071},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6603000164031982},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6401000022888184},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6384000182151794},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6150000095367432},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.5490999817848206},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.510200023651123},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.45080000162124634},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.439300000667572},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39809998869895935},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3711000084877014},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.325300008058548},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.31279999017715454},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2969000041484833},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.29159998893737793},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.28139999508857727},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C121687571","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity recognition","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.25189998745918274}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.52202/079017-1684","doi":"https://doi.org/10.52202/079017-1684","is_oa":false,"landing_page_url":"https://doi.org/10.52202/079017-1684","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 37","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2411.04998","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.04998","pdf_url":"https://arxiv.org/pdf/2411.04998","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,"listed_in":[],"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.2411.04998","doi":"https://doi.org/10.48550/arxiv.2411.04998","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.04998","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,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2411.04998","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.04998","pdf_url":"https://arxiv.org/pdf/2411.04998","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,"listed_in":[],"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"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1590227012","display_name":null,"funder_award_id":"N00014-23-1-2355","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320317153","display_name":"DeepMind","ror":"https://ror.org/00971b260"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415797648.pdf","grobid_xml":"https://content.openalex.org/works/W4415797648.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W2619947201","https://openalex.org/W3008526508","https://openalex.org/W3180718533","https://openalex.org/W3206166878","https://openalex.org/W4302010597","https://openalex.org/W4327810158","https://openalex.org/W4384392955","https://openalex.org/W4387156669","https://openalex.org/W4391710055","https://openalex.org/W4392679398","https://openalex.org/W4394973308","https://openalex.org/W4400341198","https://openalex.org/W4402702917","https://openalex.org/W4402716120","https://openalex.org/W4402753903","https://openalex.org/W4402754220","https://openalex.org/W4402780269","https://openalex.org/W4403725941","https://openalex.org/W4404654739","https://openalex.org/W4404781975","https://openalex.org/W7128773051","https://openalex.org/W7133236192"],"related_works":["https://openalex.org/W4415708389","https://openalex.org/W4416076732","https://openalex.org/W4400221713","https://openalex.org/W4399694514","https://openalex.org/W7115702888","https://openalex.org/W7161802676","https://openalex.org/W4415798209","https://openalex.org/W4414855583","https://openalex.org/W4415901680","https://openalex.org/W7133228365"],"abstract_inverted_index":{"We":[0],"present":[1],"HourVideo,":[2],"a":[3,14,96],"benchmark":[4],"dataset":[5,11],"for":[6],"hour-long":[7],"video-language":[8],"understanding.":[9],"Our":[10,102],"consists":[12],"of":[13,49],"novel":[15],"task":[16],"suite":[17],"comprising":[18],"summarization,":[19],"perception":[20],"(recall,":[21],"tracking),":[22],"visual":[23],"reasoning":[24],"(spatial,":[25],"temporal,":[26],"predictive,":[27],"causal,":[28],"counterfactual),":[29],"and":[30,54,69,107],"navigation":[31],"(room-to-room,":[32],"object":[33],"retrieval)":[34],"tasks.":[35],"HourVideo":[36],"includes":[37],"500":[38],"manually":[39],"curated":[40],"egocentric":[41],"videos":[42],"from":[43],"the":[44,84],"Ego4D":[45],"dataset,":[46],"spanning":[47],"durations":[48],"20":[50],"to":[51],"120":[52],"minutes,":[53],"features":[55],"12,976":[56],"high-quality,":[57],"five-way":[58],"multiple-choice":[59],"questions.":[60],"Benchmarking":[61],"results":[62],"reveal":[63],"that":[64],"multimodal":[65,87,100],"models,":[66],"including":[67],"GPT-4":[68],"LLaVA-NeXT,":[70],"achieve":[71],"marginal":[72],"improvements":[73],"over":[74],"random":[75],"chance.":[76],"In":[77],"stark":[78],"contrast,":[79],"human":[80],"experts":[81],"significantly":[82],"outperform":[83],"state-of-the-art":[85],"long-context":[86],"model,":[88],"Gemini":[89],"Pro":[90],"1.5":[91],"(85.0%":[92],"vs.":[93],"37.3%),":[94],"highlighting":[95],"substantial":[97],"gap":[98],"in":[99],"capabilities.":[101],"benchmark,":[103],"evaluation":[104],"toolkit,":[105],"prompts,":[106],"documentation":[108],"are":[109],"available":[110],"at":[111],"https://hourvideo.stanford.edu":[112]},"counts_by_year":[{"year":2026,"cited_by_count":27},{"year":2025,"cited_by_count":24},{"year":2024,"cited_by_count":1}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2025-11-03T00:00:00"}