{"id":"https://openalex.org/W3206020652","doi":"https://doi.org/10.1145/3474085.3475431","title":"Understanding Chinese Video and Language via Contrastive Multimodal Pre-Training","display_name":"Understanding Chinese Video and Language via Contrastive Multimodal Pre-Training","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3206020652","doi":"https://doi.org/10.1145/3474085.3475431","mag":"3206020652"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475431","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475431","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":"article","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/A5046590511","display_name":"Chenyi Lei","orcid":"https://orcid.org/0000-0001-6287-3673"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"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":"Chenyi Lei","raw_affiliation_strings":["University of Science and Technology of China & Alibaba Group, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China & Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872","https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041301168","display_name":"Shixian Luo","orcid":"https://orcid.org/0000-0003-1538-0950"},"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":"Shixian Luo","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072988055","display_name":"Yong Liu","orcid":"https://orcid.org/0000-0001-9031-9696"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yong Liu","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008173176","display_name":"Wanggui He","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":"Wanggui He","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026446674","display_name":"Jiamang Wang","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":"Jiamang Wang","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101457292","display_name":"Guoxin Wang","orcid":"https://orcid.org/0000-0003-2363-8595"},"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":"Guoxin Wang","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101669398","display_name":"Haihong Tang","orcid":"https://orcid.org/0000-0002-7103-975X"},"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":"Haihong Tang","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100382077","display_name":"Chunyan Miao","orcid":"https://orcid.org/0000-0002-0300-3448"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chunyan Miao","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078141810","display_name":"Houqiang Li","orcid":"https://orcid.org/0000-0003-2188-3028"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Houqiang Li","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0078,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.92875921,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2567","last_page":"2576"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9975000023841858,"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":0.9957000017166138,"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":0.8603900074958801},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5340204834938049},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.530921995639801},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5088308453559875},{"id":"https://openalex.org/keywords/proxy","display_name":"Proxy (statistics)","score":0.4969017803668976},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.48104360699653625},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4343509376049042},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4142324924468994},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.17537429928779602}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8603900074958801},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5340204834938049},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.530921995639801},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5088308453559875},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.4969017803668976},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.48104360699653625},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4343509376049042},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4142324924468994},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.17537429928779602},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3474085.3475431","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475431","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":[{"score":0.8199999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G505446668","display_name":null,"funder_award_id":"61836011,62021001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W1572567476","https://openalex.org/W1995820507","https://openalex.org/W2078238240","https://openalex.org/W2108598243","https://openalex.org/W2342350679","https://openalex.org/W2425121537","https://openalex.org/W2619947201","https://openalex.org/W2626778328","https://openalex.org/W2723293840","https://openalex.org/W2784025607","https://openalex.org/W2795840542","https://openalex.org/W2842511635","https://openalex.org/W2896457183","https://openalex.org/W2931316642","https://openalex.org/W2948859046","https://openalex.org/W2949474740","https://openalex.org/W2950813464","https://openalex.org/W2952122856","https://openalex.org/W2952686080","https://openalex.org/W2962745591","https://openalex.org/W2963351113","https://openalex.org/W2964350391","https://openalex.org/W2965373594","https://openalex.org/W2968880719","https://openalex.org/W2969862959","https://openalex.org/W2970608575","https://openalex.org/W2975357369","https://openalex.org/W2981852735","https://openalex.org/W2982275843","https://openalex.org/W2989322838","https://openalex.org/W2995460200","https://openalex.org/W2997200074","https://openalex.org/W2998356391","https://openalex.org/W2998476971","https://openalex.org/W3005680577","https://openalex.org/W3013840636","https://openalex.org/W3014611590","https://openalex.org/W3035524453","https://openalex.org/W3043840704","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3105232955","https://openalex.org/W3105479157","https://openalex.org/W3122640483","https://openalex.org/W3127384563","https://openalex.org/W3127985042","https://openalex.org/W3129576130","https://openalex.org/W3133825286","https://openalex.org/W3134582802","https://openalex.org/W3135367836","https://openalex.org/W3145235298","https://openalex.org/W3166304536","https://openalex.org/W3166751026","https://openalex.org/W3168640669","https://openalex.org/W3174010726","https://openalex.org/W3175095612","https://openalex.org/W4288334671","https://openalex.org/W6601223237","https://openalex.org/W6601630192","https://openalex.org/W6684701029"],"related_works":["https://openalex.org/W2028495302","https://openalex.org/W2375873920","https://openalex.org/W2146114872","https://openalex.org/W2392060890","https://openalex.org/W2012531322","https://openalex.org/W2392760275","https://openalex.org/W2002261065","https://openalex.org/W1513656766","https://openalex.org/W2360644719","https://openalex.org/W2385471969"],"abstract_inverted_index":{"The":[0],"pre-trained":[1,193],"neural":[2,21],"models":[3,22],"have":[4],"recently":[5],"achieved":[6],"impressive":[7],"performance":[8],"in":[9],"understanding":[10,117,125],"multimodal":[11,162],"content.":[12],"However,":[13],"it":[14],"is":[15,84,171],"still":[16],"very":[17],"challenging":[18],"to":[19,34,158,196],"pre-train":[20],"for":[23,29,106,123],"video":[24,51,75],"and":[25,50,58,67,78,89,156,164,202,216],"language":[26,137],"understanding,":[27],"especially":[28],"Chinese":[30,91,176],"video-language":[31,40,62,92,116,177],"data,":[32],"due":[33],"the":[35,46,102,146,151,192,209],"following":[36],"reasons.":[37],"Firstly,":[38],"existing":[39],"pre-training":[41,107,211],"algorithms":[42],"mainly":[43],"focus":[44],"on":[45,173],"co-occurrence":[47],"of":[48,61,87,199],"words":[49],"frames,":[52],"but":[53],"ignore":[54],"other":[55,79],"valuable":[56],"semantic":[57,163],"structure":[59],"information":[60],"content,":[63],"e.g.,":[64],"sequential":[65],"order":[66],"spatiotemporal":[68],"relationships.":[69],"Secondly,":[70],"there":[71,83],"exist":[72],"conflicts":[73],"between":[74],"sentence":[76],"alignment":[77],"proxy":[80,132,143],"tasks.":[81],"Thirdly,":[82],"a":[85,114,174,197],"lack":[86],"large-scale":[88,175],"high-quality":[90,187],"datasets":[93],"(eg.":[94],"including":[95,179],"10":[96,181],"million":[97,182],"unique":[98],"videos),":[99],"which":[100,121],"are":[101],"fundamental":[103],"success":[104],"conditions":[105],"techniques.":[108],"In":[109],"this":[110],"work,":[111],"we":[112],"propose":[113],"novel":[115,142],"framework":[118],"named":[119],"Victor,":[120],"stands":[122],"VIdeo-language":[124],"via":[126],"Contrastive":[127],"mulTimOdal":[128],"pRe-training.":[129],"Besides":[130],"general":[131],"tasks":[133,144],"such":[134,213],"as":[135,214],"masked":[136],"modeling,":[138],"Victor":[139,170,194],"constructs":[140],"several":[141],"under":[145],"contrastive":[147],"learning":[148],"paradigm,":[149],"making":[150],"model":[152,195],"be":[153],"more":[154,160],"robust":[155],"able":[157],"capture":[159],"complex":[161],"structural":[165],"relationships":[166],"from":[167],"different":[168],"perspectives.":[169],"trained":[172],"dataset,":[178],"over":[180],"complete":[183],"videos":[184],"with":[185],"corresponding":[186],"textual":[188],"descriptions.":[189],"We":[190],"apply":[191],"series":[198],"downstream":[200],"applications":[201],"demonstrate":[203],"its":[204],"superior":[205],"performance,":[206],"comparing":[207],"against":[208],"state-of-the-art":[210],"methods":[212],"VideoBERT":[215],"UniVL.":[217]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}