{"id":"https://openalex.org/W4315473444","doi":"https://doi.org/10.1109/tcsvt.2023.3235704","title":"Self-Training Vision Language BERTs With a Unified Conditional Model","display_name":"Self-Training Vision Language BERTs With a Unified Conditional Model","publication_year":2023,"publication_date":"2023-01-10","ids":{"openalex":"https://openalex.org/W4315473444","doi":"https://doi.org/10.1109/tcsvt.2023.3235704"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2023.3235704","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3235704","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-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/A5047646096","display_name":"Xiaofeng Yang","orcid":"https://orcid.org/0000-0003-1882-9733"},"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":true,"raw_author_name":"Xiaofeng Yang","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University (NTU), Jurong West, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University (NTU), Jurong West, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009594218","display_name":"Fengmao Lv","orcid":"https://orcid.org/0000-0003-1640-0992"},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fengmao Lv","raw_affiliation_strings":["School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, China","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042271198","display_name":"Fayao Liu","orcid":"https://orcid.org/0000-0001-6649-7660"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Fayao Liu","raw_affiliation_strings":["Agency for Science, Technology and Research (A*STAR), Fusionopolis, Singapore"],"affiliations":[{"raw_affiliation_string":"Agency for Science, Technology and Research (A*STAR), Fusionopolis, Singapore","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029912845","display_name":"Guosheng Lin","orcid":"https://orcid.org/0000-0002-0329-7458"},"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":"Guosheng Lin","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University (NTU), Jurong West, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University (NTU), Jurong West, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5047646096"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":2.5827,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.91325902,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"33","issue":"8","first_page":"3560","last_page":"3569"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.989799976348877,"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":0.9793000221252441,"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":0.6889907717704773},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5613998770713806},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5368483662605286},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48421382904052734},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.43135446310043335},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3985232710838318},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3470900356769562},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3235032260417938}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6889907717704773},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5613998770713806},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5368483662605286},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48421382904052734},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.43135446310043335},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3985232710838318},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3470900356769562},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3235032260417938},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2023.3235704","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3235704","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8500000238418579,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G2950739391","display_name":null,"funder_award_id":"2022YFG0031","funder_id":"https://openalex.org/F4320329861","funder_display_name":"Natural Science Foundation of Sichuan Province"},{"id":"https://openalex.org/G3220463999","display_name":null,"funder_award_id":"AISG-RP-2018-003","funder_id":"https://openalex.org/F4320320709","funder_display_name":"National Research Foundation Singapore"},{"id":"https://openalex.org/G3793288322","display_name":null,"funder_award_id":"2682022CX068","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G6665417076","display_name":null,"funder_award_id":"62106204","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7064285343","display_name":null,"funder_award_id":"2022NSFSC0911","funder_id":"https://openalex.org/F4320329861","funder_display_name":"Natural Science Foundation of Sichuan Province"}],"funders":[{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320329861","display_name":"Natural Science Foundation of Sichuan Province","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1889081078","https://openalex.org/W2277195237","https://openalex.org/W2422843715","https://openalex.org/W2560730294","https://openalex.org/W2741631785","https://openalex.org/W2745461083","https://openalex.org/W2886641317","https://openalex.org/W2896457183","https://openalex.org/W2908056713","https://openalex.org/W2913129712","https://openalex.org/W2914134937","https://openalex.org/W2943152387","https://openalex.org/W2945260553","https://openalex.org/W2949985837","https://openalex.org/W2953070460","https://openalex.org/W2963084599","https://openalex.org/W2963216553","https://openalex.org/W2963518342","https://openalex.org/W2964303913","https://openalex.org/W2966715458","https://openalex.org/W2968124245","https://openalex.org/W2970231061","https://openalex.org/W2970311224","https://openalex.org/W2997591391","https://openalex.org/W2998356391","https://openalex.org/W3003478339","https://openalex.org/W3034727271","https://openalex.org/W3035003500","https://openalex.org/W3035160371","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3107094551","https://openalex.org/W3119243803","https://openalex.org/W3136792391","https://openalex.org/W3173909648","https://openalex.org/W3185066916","https://openalex.org/W3216470601","https://openalex.org/W4200475325","https://openalex.org/W4285283873","https://openalex.org/W4287813958","https://openalex.org/W4292779060","https://openalex.org/W4385245566","https://openalex.org/W6620707391","https://openalex.org/W6639432524","https://openalex.org/W6695909211","https://openalex.org/W6733814495","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6757712183","https://openalex.org/W6758779242","https://openalex.org/W6761825139","https://openalex.org/W6762122294","https://openalex.org/W6766904570","https://openalex.org/W6775644863","https://openalex.org/W6778883912","https://openalex.org/W6779101013"],"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":{"Natural":[0],"language":[1,6,14,17,55],"BERTs":[2,18],"are":[3,144],"trained":[4,93,161],"with":[5,48,162],"corpus":[7],"in":[8],"a":[9,33,53,87,115,128],"self-supervised":[10],"manner.":[11],"Unlike":[12],"natural":[13],"BERTs,":[15],"vision":[16,54],"need":[19],"paired":[20],"data":[21,84,108,112],"to":[22,85,95,113,146,154],"train,":[23],"which":[24],"restricts":[25],"the":[26,67,81,92,106,124,133,155],"scale":[27],"of":[28,157],"VL-BERT":[29],"pretraining.":[30],"We":[31,79,103],"propose":[32],"self-training":[34,135],"approach":[35,136],"that":[36,58],"allows":[37],"training":[38],"VL-BERTs":[39],"from":[40],"unlabeled":[41,100,140],"image":[42,83,101,166],"data.":[43,102,167],"The":[44,118],"proposed":[45,134],"method":[46],"starts":[47],"our":[49],"unified":[50,68],"conditional":[51,62,69],"model\u2013":[52],"BERT":[56],"model":[57,70,89,94,126,159],"can":[59,71],"perform":[60],"zero-shot":[61],"generation.":[63],"Given":[64],"different":[65],"conditions,":[66],"generate":[72,96],"captions,":[73,75],"dense":[74],"and":[76,90,109,137],"even":[77,150],"questions.":[78],"use":[80,91],"labeled":[82,107,111],"train":[86,114],"teacher":[88],"pseudo":[97,110],"captions":[98],"on":[99],"then":[104],"combine":[105],"student":[116,125],"model.":[117],"process":[119],"is":[120],"iterated":[121],"by":[122],"putting":[123],"as":[127],"new":[129],"teacher.":[130],"By":[131],"using":[132],"only":[138],"300k":[139],"extra":[141,165],"data,":[142],"we":[143],"able":[145],"get":[147],"competitive":[148],"or":[149],"better":[151],"performances":[152],"compared":[153],"models":[156],"similar":[158],"size":[160],"3":[163],"million":[164]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}