{"id":"https://openalex.org/W2965891112","doi":"https://doi.org/10.1145/3292500.3330653","title":"Large-Scale Training Framework for Video Annotation","display_name":"Large-Scale Training Framework for Video Annotation","publication_year":2019,"publication_date":"2019-07-25","ids":{"openalex":"https://openalex.org/W2965891112","doi":"https://doi.org/10.1145/3292500.3330653","mag":"2965891112"},"language":"en","primary_location":{"id":"doi:10.1145/3292500.3330653","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3292500.3330653","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3292500.3330653","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3292500.3330653","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022991142","display_name":"Seong Jae Hwang","orcid":"https://orcid.org/0000-0002-3713-5553"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Seong Jae Hwang","raw_affiliation_strings":["University of Wisconsin-Madison, Madison, WI, USA"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison, Madison, WI, USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101859889","display_name":"Joonseok Lee","orcid":"https://orcid.org/0000-0002-0786-8086"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joonseok Lee","raw_affiliation_strings":["Google Research, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google Research, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114118962","display_name":"Balakrishnan Varadarajan","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Balakrishnan Varadarajan","raw_affiliation_strings":["Google Research, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google Research, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110773048","display_name":"Ariel Gordon","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ariel Gordon","raw_affiliation_strings":["Google Research, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google Research, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101651955","display_name":"Zheng Xu","orcid":"https://orcid.org/0009-0003-6747-3953"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zheng Xu","raw_affiliation_strings":["Google Research, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google Research, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030886753","display_name":"Apostol Natsev","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Apostol (Paul) Natsev","raw_affiliation_strings":["Google Research, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google Research, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5022991142"],"corresponding_institution_ids":["https://openalex.org/I135310074"],"apc_list":null,"apc_paid":null,"fwci":0.2024,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.5320821,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"2394","last_page":"2402"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9993000030517578,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9993000030517578,"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":0.8507077693939209},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.6141332387924194},{"id":"https://openalex.org/keywords/internet-video","display_name":"Internet video","score":0.6114757657051086},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5919121503829956},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.5599671602249146},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5308892130851746},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4742801785469055},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4683152139186859},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.44657814502716064},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43427854776382446},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.426231324672699},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35798847675323486},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.22204676270484924}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8507077693939209},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.6141332387924194},{"id":"https://openalex.org/C2779789524","wikidata":"https://www.wikidata.org/wiki/Q16885149","display_name":"Internet video","level":3,"score":0.6114757657051086},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5919121503829956},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.5599671602249146},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5308892130851746},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4742801785469055},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4683152139186859},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.44657814502716064},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43427854776382446},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.426231324672699},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35798847675323486},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.22204676270484924},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3292500.3330653","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3292500.3330653","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3292500.3330653","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3292500.3330653","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3292500.3330653","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3292500.3330653","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2965891112.pdf","grobid_xml":"https://content.openalex.org/works/W2965891112.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W130696423","https://openalex.org/W1923404803","https://openalex.org/W1993229407","https://openalex.org/W2016053056","https://openalex.org/W2025653905","https://openalex.org/W2064675550","https://openalex.org/W2081808304","https://openalex.org/W2097117768","https://openalex.org/W2109722477","https://openalex.org/W2142194269","https://openalex.org/W2143908786","https://openalex.org/W2163605009","https://openalex.org/W2168231600","https://openalex.org/W2173213060","https://openalex.org/W2193384753","https://openalex.org/W2194775991","https://openalex.org/W2235034809","https://openalex.org/W2274287116","https://openalex.org/W2277195237","https://openalex.org/W2409036552","https://openalex.org/W2526050071","https://openalex.org/W2560023338","https://openalex.org/W2613322955","https://openalex.org/W2625909586","https://openalex.org/W2732026016","https://openalex.org/W2734032374","https://openalex.org/W2736115865","https://openalex.org/W2808859004","https://openalex.org/W2894545902","https://openalex.org/W2912958214","https://openalex.org/W2913302158","https://openalex.org/W2913645016","https://openalex.org/W2953106684","https://openalex.org/W2962749469","https://openalex.org/W2963446712","https://openalex.org/W2963650529","https://openalex.org/W2963804082","https://openalex.org/W2963820951","https://openalex.org/W2964248098"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W4312814274","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":{"Video":[0],"is":[1,21,188],"one":[2],"of":[3,7,29,33,46,57,90,100,102,112,134,154,156],"the":[4,40,44,55,72,91,168,185,195],"richest":[5],"sources":[6],"information":[8],"available":[9],"online":[10],"but":[11],"extracting":[12],"deep":[13,96],"insights":[14],"from":[15],"video":[16,47,59,68,136,198],"content":[17],"at":[18,84],"internet":[19,85],"scale":[20,77,132,205],"still":[22],"an":[23],"open":[24],"problem,":[25],"both":[26,87,125],"in":[27,64,88],"terms":[28,89],"depth":[30,164],"and":[31,61,67,104,128,144,147,165,167,178,201,203],"breadth":[32],"understanding,":[34],"as":[35,37],"well":[36],"scale.":[38],"Over":[39],"last":[41],"few":[42],"years,":[43],"field":[45],"understanding":[48],"has":[49],"made":[50],"great":[51],"strides":[52],"due":[53],"to":[54,82,93,105,131,170,190,206],"availability":[56],"large-scale":[58],"datasets":[60,78],"core":[62],"advances":[63],"image,":[65],"audio,":[66],"modeling":[69],"architectures.":[70],"However,":[71],"state-of-the-art":[73,192],"architectures":[74],"on":[75,98,110,194],"small":[76],"are":[79],"frequently":[80],"impractical":[81],"deploy":[83,106],"scale,":[86],"ability":[92,169],"train":[94],"such":[95],"networks":[97],"hundreds":[99,153],"millions":[101],"videos,":[103],"them":[107],"for":[108],"inference":[109],"billions":[111],"videos.":[113],"In":[114],"this":[115],"paper,":[116],"we":[117],"present":[118],"a":[119,160],"MapReduce-based":[120],"training":[121,133],"framework,":[122],"which":[123,158],"exploits":[124],"data":[126],"parallelism":[127,130],"model":[129,163,172],"complex":[135],"models.":[137],"The":[138],"proposed":[139,186],"framework":[140,187],"uses":[141],"alternating":[142],"optimization":[143],"full-batch":[145],"fine-tuning,":[146],"supports":[148],"large":[149],"Mixture-of-Experts":[150],"classifiers":[151],"with":[152],"thousands":[155],"mixtures,":[157],"enables":[159],"trade-off":[161],"between":[162,174],"breadth,":[166],"shift":[171],"capacity":[173],"shared":[175],"(generalization)":[176],"layers":[177],"per-class":[179],"(specialization)":[180],"layers.":[181],"We":[182],"demonstrate":[183],"that":[184],"able":[189],"reach":[191],"performance":[193],"largest":[196],"public":[197],"datasets,":[199],"YouTube-8M":[200],"Sports-1M,":[202],"can":[204],"100":[207],"times":[208],"larger":[209],"datasets.":[210]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}