{"id":"https://openalex.org/W7124934333","doi":"https://doi.org/10.1109/cbmi66578.2025.11339344","title":"Enhancing Vision-Language Model Pre-Training with Image-Text Pair Pruning Based on Word Frequency","display_name":"Enhancing Vision-Language Model Pre-Training with Image-Text Pair Pruning Based on Word Frequency","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W7124934333","doi":"https://doi.org/10.1109/cbmi66578.2025.11339344"},"language":null,"primary_location":{"id":"doi:10.1109/cbmi66578.2025.11339344","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cbmi66578.2025.11339344","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Content-Based Multimedia Indexing (CBMI)","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/A5123437320","display_name":"Mingliang Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210109357","display_name":"Radboud Institute for Molecular Life Sciences","ror":"https://ror.org/01yb10j39","country_code":"NL","type":"facility","lineage":["https://openalex.org/I145872427","https://openalex.org/I4210109357"]},{"id":"https://openalex.org/I2802934949","display_name":"Radboud University Medical Center","ror":"https://ror.org/05wg1m734","country_code":"NL","type":"funder","lineage":["https://openalex.org/I2802934949"]},{"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":true,"raw_author_name":"Mingliang Liang","raw_affiliation_strings":["Institute for Computing and Information Sciences, Radboud University,Nijmegen,Netherlands"],"affiliations":[{"raw_affiliation_string":"Institute for Computing and Information Sciences, Radboud University,Nijmegen,Netherlands","institution_ids":["https://openalex.org/I145872427","https://openalex.org/I4210109357","https://openalex.org/I2802934949"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123420611","display_name":"Martha Larson","orcid":null},"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"]},{"id":"https://openalex.org/I2802934949","display_name":"Radboud University Medical Center","ror":"https://ror.org/05wg1m734","country_code":"NL","type":"funder","lineage":["https://openalex.org/I2802934949"]},{"id":"https://openalex.org/I4210109357","display_name":"Radboud Institute for Molecular Life Sciences","ror":"https://ror.org/01yb10j39","country_code":"NL","type":"facility","lineage":["https://openalex.org/I145872427","https://openalex.org/I4210109357"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Martha Larson","raw_affiliation_strings":["Institute for Computing and Information Sciences, Radboud University,Nijmegen,Netherlands"],"affiliations":[{"raw_affiliation_string":"Institute for Computing and Information Sciences, Radboud University,Nijmegen,Netherlands","institution_ids":["https://openalex.org/I145872427","https://openalex.org/I4210109357","https://openalex.org/I2802934949"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5123437320"],"corresponding_institution_ids":["https://openalex.org/I145872427","https://openalex.org/I2802934949","https://openalex.org/I4210109357"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.70063252,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7907000184059143,"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":0.7907000184059143,"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":0.07100000232458115,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.03319999948143959,"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/pruning","display_name":"Pruning","score":0.820900022983551},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5335999727249146},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5253000259399414},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.387800008058548},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.349700003862381},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.3395000100135803},{"id":"https://openalex.org/keywords/word-lists-by-frequency","display_name":"Word lists by frequency","score":0.3395000100135803}],"concepts":[{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.820900022983551},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.656000018119812},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5335999727249146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5324000120162964},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5253000259399414},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42809998989105225},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.387800008058548},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.349700003862381},{"id":"https://openalex.org/C175293574","wikidata":"https://www.wikidata.org/wiki/Q697133","display_name":"Word lists by frequency","level":3,"score":0.3395000100135803},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3395000100135803},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32690000534057617},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3100999891757965},{"id":"https://openalex.org/C2994428975","wikidata":"https://www.wikidata.org/wiki/Q8034367","display_name":"Word identification","level":4,"score":0.3073999881744385},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2921000123023987},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C151913843","wikidata":"https://www.wikidata.org/wiki/Q3454555","display_name":"Dominance (genetics)","level":3,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cbmi66578.2025.11339344","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cbmi66578.2025.11339344","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Content-Based Multimedia Indexing (CBMI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4270279109477997,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1905882502","https://openalex.org/W2108598243","https://openalex.org/W2185175083","https://openalex.org/W2250384498","https://openalex.org/W2886641317","https://openalex.org/W2952122856","https://openalex.org/W3037492894","https://openalex.org/W3176641147","https://openalex.org/W3177096435","https://openalex.org/W3213454282","https://openalex.org/W4247726808","https://openalex.org/W4294170691","https://openalex.org/W4312629998","https://openalex.org/W4312933868","https://openalex.org/W4386065512","https://openalex.org/W4386076084","https://openalex.org/W4389519859","https://openalex.org/W4390871860","https://openalex.org/W4402727234","https://openalex.org/W4410659598"],"related_works":[],"abstract_inverted_index":{"We":[0],"propose":[1],"Word-Frequency-based":[2],"Image-Text":[3],"Pair":[4],"Pruning":[5],"(WFPP),":[6],"a":[7,21,39,106,113],"novel":[8],"data":[9,17],"pruning":[10,87],"method":[11],"that":[12,101],"reduces":[13],"the":[14,33,43,58,63,71,83,91],"amount":[15],"of":[16,45,50,65,73,93,116],"needed":[18],"for":[19],"training":[20,35,59,105],"Visual-Language":[22],"Model":[23],"(VLM)":[24],"while":[25,69],"preserving":[26],"performance.":[27],"WFPP":[28,51,77,103],"removes":[29],"image-text":[30],"pairs":[31],"across":[32],"entire":[34],"dataset":[36],"according":[37],"to":[38,53],"score":[40],"calculated":[41],"on":[42,96,112],"basis":[44],"word":[46,55],"frequency.":[47],"The":[48],"effect":[49],"is":[52,78],"balance":[54],"frequency":[56],"in":[57],"data,":[60],"i.e.,":[61],"reduce":[62],"dominance":[64],"highly":[66],"frequent":[67,75],"words,":[68],"retaining":[70],"contribution":[72],"less":[74],"words.":[76],"competitive":[79],"with":[80],"MetaCLIP,":[81],"currently":[82],"leading":[84],"text-image":[85],"pair":[86],"approach,":[88],"but":[89],"has":[90],"advantage":[92],"not":[94],"relying":[95],"metadata.":[97],"Our":[98],"experiments":[99],"demonstrate":[100],"applying":[102],"when":[104],"CLIP":[107],"model":[108],"can":[109],"boost":[110],"performance":[111],"wide":[114],"range":[115],"downstream":[117],"tasks.":[118]},"counts_by_year":[],"updated_date":"2026-01-22T23:29:09.771500","created_date":"2026-01-21T00:00:00"}