{"id":"https://openalex.org/W4316661142","doi":"https://doi.org/10.1109/tmm.2023.3237166","title":"Effective End-to-End Vision Language Pretraining With Semantic Visual Loss","display_name":"Effective End-to-End Vision Language Pretraining With Semantic Visual Loss","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4316661142","doi":"https://doi.org/10.1109/tmm.2023.3237166"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2023.3237166","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3237166","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2301.07236","any_repository_has_fulltext":true},"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), Singapore"],"raw_orcid":"https://orcid.org/0000-0003-1882-9733","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University (NTU), Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"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), Singapore"],"raw_orcid":"https://orcid.org/0000-0001-6649-7660","affiliations":[{"raw_affiliation_string":"Agency for Science, Technology and Research (A*STAR), 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), Singapore"],"raw_orcid":"https://orcid.org/0000-0002-0329-7458","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University (NTU), Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5047646096"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":1.2952,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.81758503,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"25","issue":null,"first_page":"8408","last_page":"8417"},"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":0.9993000030517578,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9941999912261963,"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":0.8879889249801636},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6914434432983398},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6876327991485596},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6811496019363403},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6203219890594482},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.5639106035232544},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5307602286338806},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4979586601257324},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48161858320236206},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4392286539077759},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4130690097808838},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38243669271469116},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36560577154159546},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32617777585983276}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8879889249801636},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6914434432983398},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6876327991485596},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6811496019363403},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6203219890594482},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.5639106035232544},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5307602286338806},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4979586601257324},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48161858320236206},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4392286539077759},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4130690097808838},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38243669271469116},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36560577154159546},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32617777585983276},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tmm.2023.3237166","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3237166","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2301.07236","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2301.07236","pdf_url":"https://arxiv.org/pdf/2301.07236","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:2301.07236","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2301.07236","pdf_url":"https://arxiv.org/pdf/2301.07236","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","id":"https://metadata.un.org/sdg/4","score":0.6000000238418579}],"awards":[{"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/G6960108870","display_name":null,"funder_award_id":"A20H6b0151","funder_id":"https://openalex.org/F4320320696","funder_display_name":"Agency for Science, Technology and Research"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320320696","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09"},{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"},{"id":"https://openalex.org/F4320322724","display_name":"Ministry of Education, India","ror":"https://ror.org/048xjjh50"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4316661142.pdf"},"referenced_works_count":60,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W1889081078","https://openalex.org/W2122469558","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2560730294","https://openalex.org/W2561196672","https://openalex.org/W2568262903","https://openalex.org/W2741631785","https://openalex.org/W2745461083","https://openalex.org/W2886641317","https://openalex.org/W2896457183","https://openalex.org/W2906314281","https://openalex.org/W2938082352","https://openalex.org/W2953461088","https://openalex.org/W2963115613","https://openalex.org/W2963448089","https://openalex.org/W2963518342","https://openalex.org/W2965373594","https://openalex.org/W2966715458","https://openalex.org/W2970231061","https://openalex.org/W2970454332","https://openalex.org/W2975501350","https://openalex.org/W2978017171","https://openalex.org/W2998167787","https://openalex.org/W2998356391","https://openalex.org/W3001555892","https://openalex.org/W3005881764","https://openalex.org/W3014611590","https://openalex.org/W3016211260","https://openalex.org/W3033529678","https://openalex.org/W3034425145","https://openalex.org/W3034727271","https://openalex.org/W3035003500","https://openalex.org/W3035682985","https://openalex.org/W3043039073","https://openalex.org/W3094502228","https://openalex.org/W3096609285","https://openalex.org/W3105966348","https://openalex.org/W3126792443","https://openalex.org/W4287614078","https://openalex.org/W4288256350","https://openalex.org/W4295838474","https://openalex.org/W4385245566","https://openalex.org/W6638523607","https://openalex.org/W6639432524","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6766673545","https://openalex.org/W6766904570","https://openalex.org/W6768438993","https://openalex.org/W6768851824","https://openalex.org/W6771626834","https://openalex.org/W6773248631","https://openalex.org/W6775188310","https://openalex.org/W6779101013","https://openalex.org/W6779163297","https://openalex.org/W6784333009","https://openalex.org/W6784874100","https://openalex.org/W6789753369"],"related_works":["https://openalex.org/W3179968364","https://openalex.org/W1999612375","https://openalex.org/W2938107654","https://openalex.org/W2151749779","https://openalex.org/W2085033728","https://openalex.org/W3008587939","https://openalex.org/W4285411112","https://openalex.org/W2171299904","https://openalex.org/W1647606319","https://openalex.org/W3173456895"],"abstract_inverted_index":{"Current":[0],"vision":[1,38,77],"language":[2,39,78],"pretraining":[3,71,143],"models":[4,40,103],"are":[5],"dominated":[6],"by":[7],"methods":[8],"using":[9],"region":[10,58,98],"visual":[11,70,85],"features":[12],"extracted":[13],"from":[14,41],"object":[15],"detectors.":[16],"Given":[17],"their":[18,32],"good":[19],"performance,":[20],"the":[21,26,48,142],"extract-then-process":[22],"pipeline":[23],"significantly":[24],"restricts":[25],"inference":[27],"speed":[28],"and":[29,92,113],"therefore":[30],"limits":[31],"real-world":[33],"use":[34],"cases.":[35],"However,":[36],"training":[37,75],"raw":[42,49],"image":[43,50],"pixels":[44,51],"is":[45],"difficult,":[46],"as":[47],"give":[52],"much":[53,89],"less":[54],"prior":[55],"knowledge":[56],"than":[57,116],"features.":[59],"In":[60],"this":[61],"paper,":[62],"we":[63],"systematically":[64],"study":[65],"how":[66],"to":[67,73],"leverage":[68],"auxiliary":[69],"tasks":[72,112],"help":[74],"end-to-end":[76,102,125],"models.":[79],"We":[80],"introduce":[81],"three":[82],"types":[83],"of":[84,141],"losses":[86],"that":[87],"enable":[88],"faster":[90,119],"convergence":[91],"better":[93,108,134],"finetuning":[94],"accuracy.":[95],"Compared":[96,122],"with":[97,123],"feature":[99],"models,":[100,126],"our":[101,127],"could":[104,130],"achieve":[105,131],"similar":[106,132],"or":[107,133],"performance":[109,135],"on":[110],"down-stream":[111],"run":[114],"more":[115],"10":[117],"times":[118],"during":[120],"inference.":[121],"other":[124],"proposed":[128],"method":[129],"when":[136],"pretrained":[137],"for":[138],"only":[139],"10%":[140],"GPU":[144],"hours.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2023-01-17T00:00:00"}