{"id":"https://openalex.org/W4304080240","doi":"https://doi.org/10.1145/3503161.3548346","title":"CLOP: Video-and-Language Pre-Training with Knowledge Regularizations","display_name":"CLOP: Video-and-Language Pre-Training with Knowledge Regularizations","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304080240","doi":"https://doi.org/10.1145/3503161.3548346"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548346","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548346","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2211.03314","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100759678","display_name":"Guohao Li","orcid":"https://orcid.org/0000-0003-0260-5129"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Guohao Li","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100338243","display_name":"Hu Yang","orcid":"https://orcid.org/0000-0001-6589-8534"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hu Yang","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101637267","display_name":"Feng He","orcid":"https://orcid.org/0000-0002-0798-1820"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng He","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059003026","display_name":"Zhifan Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhifan Feng","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000515409","display_name":"Yajuan Lyu","orcid":null},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yajuan Lyu","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100677198","display_name":"Hua Wu","orcid":"https://orcid.org/0000-0002-5687-7800"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hua Wu","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100386394","display_name":"Haifeng Wang","orcid":"https://orcid.org/0000-0002-0672-7468"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haifeng Wang","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100759678"],"corresponding_institution_ids":["https://openalex.org/I98301712"],"apc_list":null,"apc_paid":null,"fwci":0.0598,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.27963094,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"4584","last_page":"4593"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9947999715805054,"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":0.7845604419708252},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6383087635040283},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6117389798164368},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6060130596160889},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5768334269523621},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5257483124732971},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5235373973846436},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5096004009246826},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5002167224884033},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4785633385181427},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4200289249420166},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.31877899169921875}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7845604419708252},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6383087635040283},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6117389798164368},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6060130596160889},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5768334269523621},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5257483124732971},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5235373973846436},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5096004009246826},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5002167224884033},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4785633385181427},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4200289249420166},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31877899169921875},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3503161.3548346","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548346","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2211.03314","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2211.03314","pdf_url":"https://arxiv.org/pdf/2211.03314","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2211.03314","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2211.03314","pdf_url":"https://arxiv.org/pdf/2211.03314","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8199999928474426,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W1996430422","https://openalex.org/W2096733369","https://openalex.org/W2123442489","https://openalex.org/W2152790380","https://openalex.org/W2164290393","https://openalex.org/W2425121537","https://openalex.org/W2745461083","https://openalex.org/W2786464815","https://openalex.org/W2885775891","https://openalex.org/W2896457183","https://openalex.org/W2938830017","https://openalex.org/W2948859046","https://openalex.org/W2953356739","https://openalex.org/W2963017553","https://openalex.org/W2965373594","https://openalex.org/W2965458216","https://openalex.org/W2966715458","https://openalex.org/W2968124245","https://openalex.org/W2970231061","https://openalex.org/W2975501350","https://openalex.org/W2981851019","https://openalex.org/W2984008963","https://openalex.org/W2989322838","https://openalex.org/W2990503944","https://openalex.org/W2998356391","https://openalex.org/W2998385486","https://openalex.org/W2998702515","https://openalex.org/W3005680577","https://openalex.org/W3034693603","https://openalex.org/W3035265375","https://openalex.org/W3035356601","https://openalex.org/W3035524453","https://openalex.org/W3035635319","https://openalex.org/W3038476992","https://openalex.org/W3043840704","https://openalex.org/W3090114880","https://openalex.org/W3091588028","https://openalex.org/W3093274308","https://openalex.org/W3096655658","https://openalex.org/W3099206234","https://openalex.org/W3105232955","https://openalex.org/W3109894131","https://openalex.org/W3118062200","https://openalex.org/W3118668786","https://openalex.org/W3122640483","https://openalex.org/W3135367836","https://openalex.org/W3152798676","https://openalex.org/W3166396011","https://openalex.org/W3166893724","https://openalex.org/W3168640669","https://openalex.org/W3175593095","https://openalex.org/W3176481196","https://openalex.org/W3176750236","https://openalex.org/W3176799298","https://openalex.org/W3183139384","https://openalex.org/W3203711169","https://openalex.org/W3204588463","https://openalex.org/W3217102353","https://openalex.org/W4287547182","https://openalex.org/W4287552504","https://openalex.org/W4287757777","https://openalex.org/W4288275971","https://openalex.org/W4297808394","https://openalex.org/W4301372783","https://openalex.org/W4313186260","https://openalex.org/W4385245566","https://openalex.org/W4394659899","https://openalex.org/W6600617704","https://openalex.org/W6601630192","https://openalex.org/W6783961830"],"related_works":["https://openalex.org/W3125011624","https://openalex.org/W1508631387","https://openalex.org/W2370917603","https://openalex.org/W2952760143","https://openalex.org/W2017776670","https://openalex.org/W2347897961","https://openalex.org/W2340870721","https://openalex.org/W2358318464","https://openalex.org/W2979236518","https://openalex.org/W4390871823"],"abstract_inverted_index":{"Video-and-language":[0],"pre-training":[1],"has":[2],"shown":[3],"promising":[4],"results":[5],"for":[6,128],"learning":[7],"generalizable":[8],"representations.":[9],"Most":[10],"existing":[11,63],"approaches":[12,54],"usually":[13,65],"model":[14],"video":[15],"and":[16,121,148,169],"text":[17],"in":[18],"an":[19],"implicit":[20],"manner,":[21],"without":[22],"considering":[23],"explicit":[24],"structural":[25,38],"representations":[26,36,117],"of":[27,35,44,100,118,171,183],"the":[28,62,115,176,181],"multi-modal":[29],"content.":[30],"We":[31,139],"denote":[32],"such":[33,70],"form":[34],"as":[37,59,72],"knowledge,":[39],"which":[40],"express":[41],"rich":[42],"semantics":[43],"multiple":[45],"granularities.":[46],"There":[47,95],"are":[48,96],"related":[49],"works":[50,160],"that":[51],"propose":[52,85],"object-aware":[53],"to":[55,67,74,112,132],"inject":[56],"similar":[57,119],"knowledge":[58,71,185],"inputs.":[60],"However,":[61],"methods":[64,174],"fail":[66],"effectively":[68],"utilize":[69],"regularizations":[73,186],"shape":[75],"a":[76,86,103,123,162],"superior":[77],"cross-modal":[78,135],"representation":[79,178],"space.":[80],"To":[81],"this":[82],"end,":[83],"we":[84,166],"Cross-modaL":[87],"knOwledge-enhanced":[88],"Pre-training":[89],"(CLOP)":[90],"method":[91,142],"with":[92],"Knowledge":[93,108],"Regularizations.":[94],"two":[97],"key":[98],"designs":[99],"ours:":[101],"1)":[102],"simple":[104],"yet":[105],"effective":[106],"Structural":[107],"Prediction":[109],"(SKP)":[110],"task":[111],"pull":[113],"together":[114],"latent":[116,177],"videos;":[120],"2)":[122],"novel":[124],"Knowledge-guided":[125],"sampling":[126],"approach":[127],"Contrastive":[129],"Learning":[130],"(KCL)":[131],"push":[133],"apart":[134],"hard":[136],"negative":[137],"samples.":[138],"evaluate":[140],"our":[141,173],"on":[143],"four":[144],"text-video":[145],"retrieval":[146],"tasks":[147],"one":[149],"multi-choice":[150],"QA":[151],"task.":[152],"The":[153],"experiments":[154],"show":[155],"clear":[156],"improvements,":[157],"outperforming":[158],"prior":[159],"by":[161],"substantial":[163],"margin.":[164],"Besides,":[165],"provide":[167],"ablations":[168],"insights":[170],"how":[172],"affect":[175],"space,":[179],"demonstrating":[180],"value":[182],"incorporating":[184],"into":[187],"video-and-language":[188],"pre-training.":[189]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}