{"id":"https://openalex.org/W4406311321","doi":"https://doi.org/10.1109/tpami.2025.3528394","title":"Video DataFlywheel: Resolving the Impossible Data Trinity in Video-Language Understanding","display_name":"Video DataFlywheel: Resolving the Impossible Data Trinity in Video-Language Understanding","publication_year":2025,"publication_date":"2025-01-13","ids":{"openalex":"https://openalex.org/W4406311321","doi":"https://doi.org/10.1109/tpami.2025.3528394","pmid":"https://pubmed.ncbi.nlm.nih.gov/40031003"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3528394","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3528394","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":"https://openalex.org/A5100411534","display_name":"Xiao Wang","orcid":"https://orcid.org/0000-0003-4879-2169"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Wang","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-4879-2169","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jianlong Wu","orcid":"https://orcid.org/0000-0003-0247-5221"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianlong Wu","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-0247-5221","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077882811","display_name":"Zijia Lin","orcid":"https://orcid.org/0000-0002-1390-7424"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zijia Lin","raw_affiliation_strings":["Kuaishou Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1390-7424","affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101586840","display_name":"Fuzheng Zhang","orcid":"https://orcid.org/0000-0002-6079-6392"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuzheng Zhang","raw_affiliation_strings":["Kuaishou Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113221769","display_name":"Di Zhang","orcid":"https://orcid.org/0009-0009-7102-5313"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Di Zhang","raw_affiliation_strings":["Kuaishou Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038612499","display_name":"Liqiang Nie","orcid":"https://orcid.org/0000-0003-1476-0273"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liqiang Nie","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-1476-0273","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7655,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.66372644,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"47","issue":"4","first_page":"2912","last_page":"2923"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9419000148773193,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9419000148773193,"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/computer-science","display_name":"Computer science","score":0.6924788951873779},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4992835521697998},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3981372117996216},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3415222465991974},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.323472797870636}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6924788951873779},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4992835521697998},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3981372117996216},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3415222465991974},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.323472797870636}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2025.3528394","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3528394","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:40031003","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40031003","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":[],"awards":[{"id":"https://openalex.org/G5630254371","display_name":null,"funder_award_id":"62236003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5954055007","display_name":null,"funder_award_id":"62376069","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G873523568","display_name":null,"funder_award_id":"2024A1515012027","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W2425121537","https://openalex.org/W2787894218","https://openalex.org/W2952132648","https://openalex.org/W2963017553","https://openalex.org/W2963293463","https://openalex.org/W2963524571","https://openalex.org/W2963916161","https://openalex.org/W2984008963","https://openalex.org/W2989322838","https://openalex.org/W3035635319","https://openalex.org/W3035725000","https://openalex.org/W3126721948","https://openalex.org/W3204588463","https://openalex.org/W4226289673","https://openalex.org/W4229449886","https://openalex.org/W4285606530","https://openalex.org/W4386076010","https://openalex.org/W4386918752","https://openalex.org/W4387968589","https://openalex.org/W4389519587","https://openalex.org/W4390872366","https://openalex.org/W4390873082","https://openalex.org/W4402671548","https://openalex.org/W4402702917","https://openalex.org/W4402727142","https://openalex.org/W4402753903","https://openalex.org/W4402754220","https://openalex.org/W4402955558","https://openalex.org/W4403002096","https://openalex.org/W6684090549","https://openalex.org/W6790724836","https://openalex.org/W6791353385","https://openalex.org/W6797109355","https://openalex.org/W6803448863","https://openalex.org/W6804424445","https://openalex.org/W6811013733","https://openalex.org/W6838434436","https://openalex.org/W6843018836","https://openalex.org/W6843263998","https://openalex.org/W6846867676","https://openalex.org/W6847435255","https://openalex.org/W6849177959","https://openalex.org/W6850071735","https://openalex.org/W6851592950","https://openalex.org/W6851948999","https://openalex.org/W6852776751","https://openalex.org/W6852874933","https://openalex.org/W6852952677","https://openalex.org/W6853320480","https://openalex.org/W6853336233","https://openalex.org/W6854451932","https://openalex.org/W6854992507","https://openalex.org/W6857175771","https://openalex.org/W6858543224","https://openalex.org/W6859490940","https://openalex.org/W6861614576","https://openalex.org/W6866333221","https://openalex.org/W6872853535"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Recently,":[0],"video-language":[1,113,186,221],"understanding":[2,222],"has":[3],"achieved":[4],"great":[5],"success":[6],"through":[7,46],"large-scale":[8],"pre-training.":[9],"However,":[10],"data":[11,25,196],"scarcity":[12],"remains":[13],"a":[14,112,121,136,152,200],"prevailing":[15],"challenge.":[16],"This":[17,162],"study":[18],"quantitatively":[19],"reveals":[20],"an":[21],"\"impossible":[22],"trinity\"":[23],"among":[24],"quantity,":[26],"diversity,":[27],"and":[28,78,129,170,179,204,228],"quality":[29,45,207],"in":[30,60,120,167,185,219],"pre-training":[31],"datasets.":[32],"Recent":[33],"efforts":[34],"seek":[35],"to":[36,72,115],"refine":[37,52],"large-scale,":[38],"diverse":[39],"ASR":[40,66],"datasets":[41,169],"compromised":[42],"by":[43,56],"low":[44],"synthetic":[47,76,117],"annotations.":[48],"These":[49,139],"methods":[50],"successfully":[51],"the":[53,82,92],"original":[54],"annotations":[55,77,100],"leveraging":[57],"useful":[58],"information":[59],"multimodal":[61],"video":[62,99,225],"content":[63],"(frames,":[64],"tags,":[65],"transcripts,":[67],"etc.).":[68],"Nevertheless,":[69],"they":[70],"struggle":[71],"mitigate":[73],"noise":[74,103,147,160],"within":[75],"lack":[79],"scalability":[80,184],"as":[81],"dataset":[83,206,215],"size":[84],"expands.":[85],"To":[86],"address":[87],"these":[88],"issues,":[89],"we":[90,109,125,149],"introduce":[91],"Video":[93],"DataFlywheel":[94],"framework,":[95],"which":[96],"iteratively":[97],"refines":[98],"with":[101,208],"improved":[102],"control":[104],"methods.":[105],"For":[106,146],"iterative":[107,177],"refinement,":[108],"first":[110],"leverage":[111],"model":[114],"generate":[116],"annotations,":[118],"resulting":[119],"refined":[122,214],"dataset.":[123],"Then,":[124],"pre-train":[126],"on":[127,131,159],"it":[128],"fine-tune":[130],"human":[132],"refinement":[133,178,197],"examples":[134],"for":[135,143],"stronger":[137],"model.":[138],"processes":[140],"are":[141],"repeated":[142],"continuous":[144],"improvement.":[145],"control,":[148],"present":[150],"AdaTaiLr,":[151],"novel":[153],"method":[154,163],"that":[155,191],"requires":[156],"weaker":[157],"assumptions":[158],"distribution.":[161],"proves":[164],"more":[165],"effective":[166],"large":[168],"offers":[171],"theoretical":[172],"guarantees.":[173],"The":[174],"combination":[175],"of":[176],"AdaTaiLr":[180],"can":[181],"achieve":[182],"better":[183],"understanding.":[187],"Extensive":[188],"experiments":[189],"show":[190],"our":[192,213],"framework":[193],"outperforms":[194],"existing":[195],"baselines,":[198],"delivering":[199],"3%":[201],"performance":[202],"boost":[203],"improving":[205],"minimal":[209],"diversity":[210],"loss.":[211],"Furthermore,":[212],"facilitates":[216],"significant":[217],"improvements":[218],"various":[220],"tasks,":[223],"including":[224],"question":[226],"answering":[227],"text-video":[229],"retrieval.":[230]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}