{"id":"https://openalex.org/W4415708389","doi":"https://doi.org/10.1109/icme59968.2025.11208965","title":"HLV-1K: A Large-scale Hour-Long Video Benchmark for Time-Specific Long Video Understanding","display_name":"HLV-1K: A Large-scale Hour-Long Video Benchmark for Time-Specific Long Video Understanding","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708389","doi":"https://doi.org/10.1109/icme59968.2025.11208965"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11208965","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11208965","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"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":"Heqing Zou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heqing Zou","raw_affiliation_strings":["TikTok"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TikTok","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029866838","display_name":"Tianze Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianze Luo","raw_affiliation_strings":["TikTok"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TikTok","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Guiyang Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guiyang Xie","raw_affiliation_strings":["TikTok"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TikTok","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101765640","display_name":"Victor Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Victor Xiao Jie Zhang","raw_affiliation_strings":["TikTok"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TikTok","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009594218","display_name":"Fengmao Lv","orcid":"https://orcid.org/0000-0003-1640-0992"},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fengmao Lv","raw_affiliation_strings":["Southwest Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southwest Jiaotong University","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028380963","display_name":"Guangcong Wang","orcid":"https://orcid.org/0000-0002-6627-814X"},"institutions":[{"id":"https://openalex.org/I4396570619","display_name":"Great Bay University","ror":"https://ror.org/01hdgge16","country_code":null,"type":"education","lineage":["https://openalex.org/I4396570619"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Guangcong Wang","raw_affiliation_strings":["Great Bay University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Great Bay University","institution_ids":["https://openalex.org/I4396570619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045191293","display_name":"Junyang Chen","orcid":"https://orcid.org/0000-0002-1139-8654"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junyang Chen","raw_affiliation_strings":["Shenzhen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen University","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065450231","display_name":"Zhuochen Wang","orcid":"https://orcid.org/0000-0002-8116-6090"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuochen Wang","raw_affiliation_strings":["TikTok"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TikTok","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071553123","display_name":"Hai\u2010Feng Zhang","orcid":"https://orcid.org/0000-0003-2519-7973"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hansheng Zhang","raw_affiliation_strings":["TikTok"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TikTok","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042372240","display_name":"Huaijian Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huaijian Zhang","raw_affiliation_strings":["TikTok"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TikTok","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"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":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9883000254631042,"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":0.9883000254631042,"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":0.002400000113993883,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.0019000000320374966,"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":0.781499981880188},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5092999935150146},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.3953999876976013},{"id":"https://openalex.org/keywords/video-recording","display_name":"Video recording","score":0.39340001344680786},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.38609999418258667},{"id":"https://openalex.org/keywords/online-video","display_name":"Online video","score":0.38530001044273376}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.781499981880188},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7746999859809875},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5092999935150146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49779999256134033},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.3953999876976013},{"id":"https://openalex.org/C2988634675","wikidata":"https://www.wikidata.org/wiki/Q34508","display_name":"Video recording","level":2,"score":0.39340001344680786},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.38609999418258667},{"id":"https://openalex.org/C2988167200","wikidata":"https://www.wikidata.org/wiki/Q16885149","display_name":"Online video","level":2,"score":0.38530001044273376},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.3716999888420105},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.3400000035762787},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.32330000400543213},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.3179999887943268},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2759999930858612}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11208965","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11208965","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2140199336","https://openalex.org/W2606982687","https://openalex.org/W2765716052","https://openalex.org/W2955874753","https://openalex.org/W4226289673","https://openalex.org/W4402702917","https://openalex.org/W4402702960","https://openalex.org/W4402727272","https://openalex.org/W4413146669"],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"large":[1],"language":[2],"models":[3],"have":[4],"become":[5],"a":[6,64,147],"popular":[7],"topic":[8],"in":[9,57],"deep":[10,126,152],"visual":[11,33],"understanding":[12,79,129,144,153],"due":[13],"to":[14,75],"many":[15],"promising":[16],"real-world":[17],"applications.":[18],"However,":[19],"hour-long":[20,66,84],"video":[21,42,68,78,128,143],"understanding,":[22],"spanning":[23],"over":[24],"one":[25],"hour":[26],"and":[27,48,92,101,108,120,134,160],"containing":[28],"tens":[29],"of":[30,32,38,51,154],"thousands":[31],"frames,":[34],"remains":[35],"under-explored":[36],"because":[37],"1)":[39],"challenging":[40],"long-term":[41,109],"analyses,":[43],"2)":[44],"inefficient":[45],"large-model":[46],"approaches,":[47],"3)":[49],"lack":[50],"large-scale":[52,65],"benchmark":[53,115],"datasets.":[54],"Among":[55],"them,":[56],"this":[58],"paper,":[59],"we":[60],"focus":[61],"on":[62],"building":[63],"long":[67,77,127,142,155],"benchmark,":[69],"HLV-1K":[70,81],"<sup":[71],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[72],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>,":[73],"designed":[74],"evaluate":[76,113],"models.":[80],"comprises":[82],"1009":[83],"videos":[85],"with":[86,98],"14,847":[87],"high-quality":[88],"question":[89,94],"answering":[90],"(QA)":[91],"multi-choice":[93],"asnwering":[95],"(MCQA)":[96],"pairs":[97],"time-aware":[99],"query":[100],"diverse":[102],"annotations,":[103],"covering":[104],"frame-level,":[105],"within-event-level,":[106],"cross-event-level,":[107],"reasoning":[110],"tasks.":[111,137],"We":[112],"our":[114],"using":[116],"existing":[117],"state-of-the-art":[118],"methods":[119],"demonstrate":[121],"its":[122],"value":[123],"for":[124,135],"testing":[125],"capabilities":[130],"at":[131,146],"different":[132],"levels":[133],"various":[136],"This":[138],"includes":[139],"promoting":[140],"future":[141],"tasks":[145],"granular":[148],"level,":[149],"such":[150],"as":[151],"live":[156],"videos,":[157],"meeting":[158],"recordings,":[159],"movies.":[161]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-30T00:00:00"}