{"id":"https://openalex.org/W7152374180","doi":"https://doi.org/10.1145/3774904.3792099","title":"LoVR: A Benchmark for Long Video Retrieval in Multimodal Contexts","display_name":"LoVR: A Benchmark for Long Video Retrieval in Multimodal Contexts","publication_year":2026,"publication_date":"2026-04-09","ids":{"openalex":"https://openalex.org/W7152374180","doi":"https://doi.org/10.1145/3774904.3792099"},"language":null,"primary_location":{"id":"doi:10.1145/3774904.3792099","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792099","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 ACM Web Conference 2026","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774904.3792099","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Hao Liang","orcid":"https://orcid.org/0009-0000-2963-2210"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hao Liang","raw_affiliation_strings":["Peking University, Beijing, China and Zhongguancun Academy, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-2963-2210","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China and Zhongguancun Academy, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qifeng Cai","orcid":"https://orcid.org/0009-0008-5086-8285"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qifeng Cai","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0008-5086-8285","affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhaoyang Han","orcid":"https://orcid.org/0009-0003-1837-9071"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaoyang Han","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0003-1837-9071","affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hejun Dong","orcid":"https://orcid.org/0009-0000-5579-8812"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hejun Dong","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-5579-8812","affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120132025","display_name":"Meiyi Qiang","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meiyi Qiang","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-3009-2886","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102639331","display_name":"Ruichuan An","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruichuan An","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-3758-4335","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074979952","display_name":"Quanqing Xu","orcid":"https://orcid.org/0000-0001-8989-9662"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Quanqing Xu","raw_affiliation_strings":["OceanBase, Ant Group, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8989-9662","affiliations":[{"raw_affiliation_string":"OceanBase, Ant Group, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062357883","display_name":"Bin Cui","orcid":"https://orcid.org/0000-0003-1681-4677"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Cui","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1681-4677","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":null,"display_name":"Wentao Zhang","orcid":"https://orcid.org/0000-0002-7532-5550"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wentao Zhang","raw_affiliation_strings":["Peking University, Beijing, China and Zhongguancun Academy, Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7532-5550","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China and Zhongguancun Academy, Beijing, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.76387819,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1911","last_page":"1922"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6054999828338623,"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":0.6054999828338623,"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/T11439","display_name":"Video Analysis and Summarization","score":0.14720000326633453,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.09399999678134918,"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":0.5188000202178955},{"id":"https://openalex.org/keywords/video-retrieval","display_name":"Video retrieval","score":0.43380001187324524},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.35429999232292175},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3122999966144562},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2734000086784363}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6990000009536743},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5188000202178955},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47049999237060547},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.43380001187324524},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3716999888420105},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.35429999232292175},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.25769999623298645},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.24279999732971191}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774904.3792099","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792099","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 ACM Web Conference 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3774904.3792099","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792099","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 ACM Web Conference 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2425121537","https://openalex.org/W2963017553","https://openalex.org/W2964220823","https://openalex.org/W2984008963","https://openalex.org/W3100732527","https://openalex.org/W4312661097","https://openalex.org/W4321614506","https://openalex.org/W4390873312","https://openalex.org/W4392172801","https://openalex.org/W4400721967","https://openalex.org/W4402702917"],"related_works":[],"abstract_inverted_index":{"Long":[0],"videos":[1,39,77],"contain":[2],"a":[3,65,123,146,167],"vast":[4],"amount":[5],"of":[6,90,173],"information,":[7],"making":[8],"video-text":[9,71],"retrieval":[10],"an":[11,96],"essential":[12],"and":[13,19,54,78,109,145,155,176],"challenging":[14,168],"task":[15],"in":[16],"multimodal":[17],"learning":[18],"web-scale":[20],"search.":[21],"On":[22],"today's":[23],"Web,":[24],"where":[25],"users":[26],"increasingly":[27],"expect":[28],"to":[29,48,127],"locate":[30],"not":[31],"only":[32],"relevant":[33],"pages":[34],"but":[35],"also":[36],"specific":[37],"long":[38,70,76],"or":[40],"fine-grained":[41,81],"clips,":[42],"existing":[43],"benchmarks":[44],"fall":[45],"short":[46],"due":[47],"limited":[49],"video":[50,153],"duration,":[51],"low-quality":[52],"captions,":[53,144],"coarse":[55],"annotation":[56,115],"granularity.":[57],"To":[58,86],"address":[59],"these":[60],"limitations,":[61],"we":[62,94,121],"introduce":[63,122],"LoVR,":[64],"benchmark":[66,138],"specifically":[67],"designed":[68],"for":[69,152,180],"retrieval.":[72,156],"LoVR":[73,165],"contains":[74],"467":[75],"over":[79],"40,804":[80],"clips":[82],"with":[83],"high-quality":[84],"captions.":[85],"overcome":[87],"the":[88,171,185],"issue":[89],"poor":[91],"machine-generated":[92],"annotations,":[93],"propose":[95],"efficient":[97],"caption":[98,106],"generation":[99],"framework":[100],"that":[101,164],"integrates":[102],"VLM":[103],"automatic":[104],"generation,":[105],"quality":[107],"scoring,":[108],"dynamic":[110],"refinement.":[111],"This":[112],"pipeline":[113],"improves":[114],"accuracy":[116],"while":[117],"maintaining":[118],"scalability.":[119],"Furthermore,":[120],"semantic":[124],"fusion":[125],"method":[126],"generate":[128],"coherent":[129],"full-video":[130],"captions":[131],"without":[132],"losing":[133],"important":[134],"contextual":[135],"information.":[136],"Our":[137],"introduces":[139],"longer":[140],"videos,":[141],"more":[142],"detailed":[143],"larger-scale":[147],"dataset,":[148],"presenting":[149],"new":[150],"challenges":[151],"understanding":[154],"Extensive":[157],"experiments":[158],"on":[159],"various":[160],"advanced":[161],"models":[162],"demonstrate":[163],"is":[166],"benchmark,":[169],"revealing":[170],"limitations":[172],"current":[174],"approaches":[175],"providing":[177],"valuable":[178],"insights":[179],"future":[181],"research.":[182],"We":[183],"release":[184],"code":[186],"link":[187],"at":[188],"https://github.com/TechNomad-ds/LoVR-benchmark/.":[189]},"counts_by_year":[],"updated_date":"2026-04-29T09:16:38.111599","created_date":"2026-04-10T00:00:00"}