{"id":"https://openalex.org/W3207896692","doi":"https://doi.org/10.1145/3474085.3481541","title":"Once and for All","display_name":"Once and for All","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3207896692","doi":"https://doi.org/10.1145/3474085.3481541","mag":"3207896692"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3481541","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3481541","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","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":"https://openalex.org/A5019994258","display_name":"Lianghua Huang","orcid":"https://orcid.org/0000-0002-9686-9354"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lianghua Huang","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100345619","display_name":"Yu Liu","orcid":"https://orcid.org/0000-0001-6449-2129"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Liu","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068611007","display_name":"Xiangzeng Zhou","orcid":"https://orcid.org/0000-0003-3123-6561"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangzeng Zhou","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015521097","display_name":"Ansheng You","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ansheng You","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100351449","display_name":"Ming Li","orcid":"https://orcid.org/0000-0002-6406-1983"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Li","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100372368","display_name":"Bin Wang","orcid":"https://orcid.org/0000-0002-5176-9202"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Wang","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059194274","display_name":"Yingya Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingya Zhang","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100667153","display_name":"Pan Pan","orcid":"https://orcid.org/0000-0001-5828-0234"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pan Pan","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110763379","display_name":"Yinghui Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Yinghui","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I45928872"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1148","last_page":"1156"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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/T11714","display_name":"Multimodal Machine Learning Applications","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":0.9995999932289124,"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":0.9986000061035156,"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":0.8638891577720642},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5392407774925232},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5039228796958923},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4976997673511505},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.47176292538642883},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.44244641065597534},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.43547409772872925},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.43256333470344543},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.41616740822792053},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.407619833946228},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38483989238739014},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.36890023946762085},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.13376015424728394}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8638891577720642},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5392407774925232},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5039228796958923},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4976997673511505},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.47176292538642883},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44244641065597534},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.43547409772872925},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.43256333470344543},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.41616740822792053},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.407619833946228},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38483989238739014},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.36890023946762085},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.13376015424728394},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3474085.3481541","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3481541","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","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":50,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W1532327008","https://openalex.org/W2048679005","https://openalex.org/W2052666245","https://openalex.org/W2108598243","https://openalex.org/W2126579184","https://openalex.org/W2194775991","https://openalex.org/W2326925005","https://openalex.org/W2732026016","https://openalex.org/W2740306440","https://openalex.org/W2743473392","https://openalex.org/W2757910899","https://openalex.org/W2761659801","https://openalex.org/W2888166343","https://openalex.org/W2896457183","https://openalex.org/W2948242301","https://openalex.org/W2963125010","https://openalex.org/W2963155035","https://openalex.org/W2963163009","https://openalex.org/W2963370182","https://openalex.org/W2963465221","https://openalex.org/W2964051877","https://openalex.org/W2972943112","https://openalex.org/W2975813532","https://openalex.org/W2977076530","https://openalex.org/W2982376094","https://openalex.org/W2984008963","https://openalex.org/W2990503944","https://openalex.org/W2995181141","https://openalex.org/W2995923603","https://openalex.org/W3009205145","https://openalex.org/W3009561768","https://openalex.org/W3010094231","https://openalex.org/W3020933450","https://openalex.org/W3034978746","https://openalex.org/W3035118106","https://openalex.org/W3035524453","https://openalex.org/W3035635319","https://openalex.org/W3047740097","https://openalex.org/W3047826509","https://openalex.org/W3048918001","https://openalex.org/W3099782249","https://openalex.org/W3100177202","https://openalex.org/W3100859887","https://openalex.org/W3101537861","https://openalex.org/W3103215803","https://openalex.org/W3110190397","https://openalex.org/W3119786062","https://openalex.org/W3123146796","https://openalex.org/W3176179208"],"related_works":["https://openalex.org/W2366107444","https://openalex.org/W4388145910","https://openalex.org/W2381570729","https://openalex.org/W1976205134","https://openalex.org/W4248336175","https://openalex.org/W2031260042","https://openalex.org/W2185469136","https://openalex.org/W2391445434","https://openalex.org/W3009369890","https://openalex.org/W4312490297"],"abstract_inverted_index":{"Videos":[0],"grow":[1],"to":[2,17,49,117],"be":[3],"one":[4],"of":[5,20,35,93,135],"the":[6,10,69,86,119,195,202,210],"largest":[7],"mediums":[8],"on":[9,32,145,153,185,198],"Internet.":[11],"E-commerce":[12],"platforms":[13],"like":[14],"Alibaba":[15],"need":[16],"process":[18],"millions":[19],"video":[21],"data":[22,113],"across":[23],"multimedia":[24,187],"(e.g.,":[25,37,102],"visual,":[26],"audio,":[27,165],"image,":[28,166],"and":[29,31,40,53,61,88,111,115,141,159,168,182,209],"text)":[30],"a":[33,51,75,130],"variety":[34],"tasks":[36,188],"retrieval,":[38],"tagging,":[39],"summary)":[41],"every":[42],"day.":[43],"In":[44],"this":[45],"work,":[46],"we":[47,67,177,192,214],"aim":[48],"develop":[50],"once":[52],"for":[54,58],"all":[55],"pretraining":[56,208],"technique":[57],"diverse":[59,186],"modalities":[60],"downstream":[62],"tasks.":[63],"To":[64],"achieve":[65],"this,":[66],"make":[68],"following":[70],"contributions:":[71],"(1)":[72],"We":[73,97,128],"propose":[74],"self-supervised":[76],"multi-modal":[77,132],"co-training":[78],"framework.":[79],"It":[80],"takes":[81,149],"cross-modal":[82],"pseudo-label":[83],"consistency":[84],"as":[85],"supervision":[87],"can":[89],"jointly":[90],"learn":[91],"representations":[92],"multiple":[94],"modalities.":[95],"(2)":[96],"introduce":[98],"several":[99],"novel":[100],"techniques":[101],"sliding-window":[103],"subset":[104],"sampling,":[105],"coarse-to-fine":[106],"clustering,":[107],"fast":[108],"spatial-temporal":[109],"convolution":[110],"parallel":[112],"transmission":[114],"processing)":[116],"optimize":[118],"training":[120,125,148],"process,":[121],"making":[122],"billion-scale":[123],"stable":[124],"feasible.":[126],"(3)":[127],"construct":[129],"large-scale":[131],"dataset":[133],"consisting":[134],"1.4":[136],"billion":[137],"videos":[138],"(~0.5":[139],"PB)":[140],"train":[142],"our":[143,174,206],"framework":[144],"it.":[146],"The":[147],"only":[150],"4.6":[151],"days":[152],"an":[154],"in-house":[155],"256":[156],"GPUs":[157],"cluster,":[158],"it":[160],"simultaneously":[161],"produces":[162],"pretrained":[163,175],"video,":[164],"motion,":[167],"text":[169],"networks.":[170],"(4)":[171],"Finetuning":[172],"from":[173],"models,":[176],"obtain":[178],"significant":[179],"performance":[180],"gains":[181],"faster":[183],"convergence":[184],"at":[189],"Alibaba.":[190],"Furthermore,":[191],"also":[193],"validate":[194],"learned":[196],"representation":[197],"public":[199],"datasets.":[200],"Despite":[201],"domain":[203],"gap":[204],"between":[205],"commodity-centric":[207],"action-centric":[211],"evaluation":[212],"data,":[213],"show":[215],"superior":[216],"results":[217],"against":[218],"state-of-the-arts.":[219]},"counts_by_year":[{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2021-10-25T00:00:00"}