{"id":"https://openalex.org/W4388196266","doi":"https://doi.org/10.1145/3607827.3616843","title":"Subsampling of Frequent Words in Text for Pre-training a Vision-Language Model","display_name":"Subsampling of Frequent Words in Text for Pre-training a Vision-Language Model","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4388196266","doi":"https://doi.org/10.1145/3607827.3616843"},"language":"en","primary_location":{"id":"doi:10.1145/3607827.3616843","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1145/3607827.3616843","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3607827.3616843","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st Workshop on Large Generative Models Meet Multimodal Applications","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3607827.3616843","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020087557","display_name":"Mingliang Liang","orcid":"https://orcid.org/0000-0002-7129-6799"},"institutions":[{"id":"https://openalex.org/I145872427","display_name":"Radboud University Nijmegen","ror":"https://ror.org/016xsfp80","country_code":"NL","type":"education","lineage":["https://openalex.org/I145872427"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Mingliang Liang","raw_affiliation_strings":["Radboud University, Nijmegen, Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-7129-6799","affiliations":[{"raw_affiliation_string":"Radboud University, Nijmegen, Netherlands","institution_ids":["https://openalex.org/I145872427"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063223989","display_name":"Martha Larson","orcid":"https://orcid.org/0000-0002-1430-4721"},"institutions":[{"id":"https://openalex.org/I145872427","display_name":"Radboud University Nijmegen","ror":"https://ror.org/016xsfp80","country_code":"NL","type":"education","lineage":["https://openalex.org/I145872427"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Martha Larson","raw_affiliation_strings":["Radboud University, Nijmegen, Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-1430-4721","affiliations":[{"raw_affiliation_string":"Radboud University, Nijmegen, Netherlands","institution_ids":["https://openalex.org/I145872427"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145872427"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"61","last_page":"67"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9995999932289124,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9883999824523926,"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":0.8340615034103394},{"id":"https://openalex.org/keywords/notice","display_name":"Notice","score":0.6618609428405762},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6093414425849915},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5986942052841187},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5924994349479675},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.576083242893219},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5229388475418091},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5054917335510254},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.489702969789505},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.45418253540992737},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.4499005079269409},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3930712342262268}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8340615034103394},{"id":"https://openalex.org/C2779913896","wikidata":"https://www.wikidata.org/wiki/Q7063001","display_name":"Notice","level":2,"score":0.6618609428405762},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6093414425849915},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5986942052841187},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5924994349479675},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.576083242893219},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5229388475418091},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5054917335510254},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.489702969789505},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.45418253540992737},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.4499005079269409},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3930712342262268},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3607827.3616843","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1145/3607827.3616843","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3607827.3616843","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st Workshop on Large Generative Models Meet Multimodal Applications","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.ubn.ru.nl:2066/297973","is_oa":true,"landing_page_url":"https://repository.ubn.ru.nl/handle/2066/297973","pdf_url":"https://repository.ubn.ru.nl//bitstream/handle/2066/297973/297973.pdf","source":{"id":"https://openalex.org/S4306401067","display_name":"Radboud Repository (Radboud University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I145872427","host_organization_name":"Radboud University Nijmegen","host_organization_lineage":["https://openalex.org/I145872427"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Wang, Z. (ed.), LGM3A '23: Proceedings of the 1st Workshop on Large Generative Models Meet Multimodal\\nApplications. Co-located with: MM '23: The 31st ACM International Conference on Multimedia Ottawa ON Canada 2 November 2023, pp. 61\u201367","raw_type":"Article in monograph or in proceedings"}],"best_oa_location":{"id":"doi:10.1145/3607827.3616843","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1145/3607827.3616843","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3607827.3616843","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st Workshop on Large Generative Models Meet Multimodal Applications","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6499999761581421}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4388196266.pdf","grobid_xml":"https://content.openalex.org/works/W4388196266.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W12634471","https://openalex.org/W2017814585","https://openalex.org/W2108598243","https://openalex.org/W2115579991","https://openalex.org/W2194775991","https://openalex.org/W2533598788","https://openalex.org/W2806857275","https://openalex.org/W3213454282","https://openalex.org/W4386076084","https://openalex.org/W6601630192"],"related_works":["https://openalex.org/W2250909759","https://openalex.org/W2532616038","https://openalex.org/W2787311093","https://openalex.org/W155946694","https://openalex.org/W1555968995","https://openalex.org/W4307474317","https://openalex.org/W2147879411","https://openalex.org/W2624072012","https://openalex.org/W2057384730","https://openalex.org/W2008468404"],"abstract_inverted_index":{"In":[0],"this":[1,142],"paper,":[2],"we":[3],"introduce":[4],"Subsampling":[5],"of":[6,27,50,60,79,107,124,130,138,156],"frequent":[7],"Words":[8],"for":[9,17,153],"Contrastive":[10],"Language-Image":[11],"Pre-training":[12],"(SW-CLIP),":[13],"a":[14,71,77,121],"novel":[15],"approach":[16],"the":[18,46,58,89,105,108,115,131,136,154],"training":[19,48,66,116,133,155],"Vision-Language":[20],"Models":[21],"(VLMs).":[22],"SW-CLIP":[23,95,139],"uses":[24],"frequency-based":[25,61,128],"subsampling":[26,62,129,152],"words":[28,113],"that":[29,56,88],"has":[30],"been":[31],"previously":[32],"proposed":[33],"to":[34,45,63,69,97,145],"train":[35],"skip-gram":[36],"models":[37],"in":[38,74,76,103,114,141,150],"natural":[39],"language":[40],"processing":[41],"and":[42,67,118,160],"applies":[43],"it":[44],"textual":[47],"data":[49],"VLMs.":[51,157],"We":[52,86],"report":[53],"on":[54,93],"experiments":[55],"demonstrate":[57],"ability":[59],"speed":[64],"up":[65],"also":[68],"deliver":[70],"substantial":[72],"improvement":[73],"accuracy":[75],"number":[78],"downstream":[80],"zero-shot":[81],"(i.e.,":[82],"transfer)":[83],"classification":[84,90],"tasks.":[85],"notice":[87],"test":[91],"sets":[92],"which":[94,104],"seems":[96],"be":[98],"particularly":[99],"effective":[100],"are":[101,163],"those":[102],"labels":[106],"classes":[109],"occur":[110],"infrequently":[111],"as":[112],"data,":[117],"thus":[119],"have":[120],"high":[122],"probability":[123],"being":[125],"retained":[126],"during":[127],"model":[132],"data.":[134],"Overall,":[135],"advantages":[137],"demonstrated":[140],"paper":[143],"serves":[144],"motivated":[146],"further":[147],"future":[148],"work":[149],"text":[151],"Our":[158],"code":[159],"pre-trained":[161],"weights":[162],"available":[164],"at":[165],"https://github.com/Anastasiais-ml/sw_clip.git":[166]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}