{"id":"https://openalex.org/W3198693420","doi":"https://doi.org/10.1145/3460426.3470947","title":"MMPT'21: International Joint Workshop on Multi-Modal Pre-Training for Multimedia Understanding","display_name":"MMPT'21: International Joint Workshop on Multi-Modal Pre-Training for Multimedia Understanding","publication_year":2021,"publication_date":"2021-08-24","ids":{"openalex":"https://openalex.org/W3198693420","doi":"https://doi.org/10.1145/3460426.3470947","mag":"3198693420"},"language":"en","primary_location":{"id":"doi:10.1145/3460426.3470947","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3460426.3470947","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Multimedia Retrieval","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/A5073199084","display_name":"Bei Liu","orcid":"https://orcid.org/0000-0001-8857-0953"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bei Liu","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072029041","display_name":"Jianlong Fu","orcid":"https://orcid.org/0000-0002-1025-2012"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianlong Fu","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101776086","display_name":"Shizhe Chen","orcid":"https://orcid.org/0000-0002-7313-9703"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Shizhe Chen","raw_affiliation_strings":["INRIA, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA, Paris, France","institution_ids":["https://openalex.org/I1326498283"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009985839","display_name":"Qin Jin","orcid":"https://orcid.org/0000-0001-6486-6020"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qin Jin","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107836252","display_name":"Alexander G. Hauptmann","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander Hauptmann","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100728762","display_name":"Yong Rui","orcid":"https://orcid.org/0000-0002-9142-5914"},"institutions":[{"id":"https://openalex.org/I4210156165","display_name":"Lenovo (China)","ror":"https://ror.org/04srd9d93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156165"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Rui","raw_affiliation_strings":["Lenovo Group, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lenovo Group, Beijing, China","institution_ids":["https://openalex.org/I4210156165"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5073199084"],"corresponding_institution_ids":["https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11075745,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"694","last_page":"695"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9957000017166138,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.790528416633606},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.7376107573509216},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.608734667301178},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5705493688583374},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5434151291847229},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4610852599143982},{"id":"https://openalex.org/keywords/video-retrieval","display_name":"Video retrieval","score":0.44348180294036865},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.33749669790267944},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2968266010284424},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07029929757118225}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.790528416633606},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.7376107573509216},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.608734667301178},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5705493688583374},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5434151291847229},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4610852599143982},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.44348180294036865},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33749669790267944},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2968266010284424},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07029929757118225},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3460426.3470947","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3460426.3470947","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2969862959","https://openalex.org/W2970608575","https://openalex.org/W2995460200","https://openalex.org/W2997591391","https://openalex.org/W3090449556","https://openalex.org/W3184784418"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W2495260952","https://openalex.org/W4366179611","https://openalex.org/W2996078371"],"abstract_inverted_index":{"Pre-training":[0],"has":[1],"been":[2],"an":[3],"emerging":[4],"topic":[5],"that":[6],"provides":[7],"a":[8],"way":[9],"to":[10,58,72,76],"learn":[11],"strong":[12],"representation":[13],"in":[14],"many":[15,31,43],"fields":[16],"(e.g.,":[17,46],"natural":[18],"language":[19],"processing,":[20],"computing":[21],"vision).":[22],"In":[23,53],"the":[24],"last":[25],"few":[26],"years,":[27],"we":[28,56],"have":[29,38],"witnessed":[30],"research":[32],"works":[33],"on":[34,42,62],"multi-modal":[35],"pre-training":[36,87],"which":[37],"achieved":[39],"state-of-the-art":[40],"performances":[41],"multimedia":[44,90],"tasks":[45],"image-text":[47],"retrieval,":[48],"video":[49],"localization,":[50],"speech":[51],"recognition).":[52],"this":[54],"workshop,":[55],"aim":[57],"gather":[59],"peer":[60],"researchers":[61,75],"related":[63],"topics":[64],"for":[65,89],"more":[66,74,80],"insightful":[67],"discussion.":[68],"We":[69],"also":[70],"intend":[71],"attract":[73],"explore":[77],"and":[78,84],"investigate":[79],"opportunities":[81],"of":[82],"designing":[83],"using":[85],"innovative":[86],"models":[88],"tasks.":[91]},"counts_by_year":[],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2025-10-10T00:00:00"}