{"id":"https://openalex.org/W4403713345","doi":"https://doi.org/10.1145/3689091.3690089","title":"Bridging the Lexical Gap: Generative Text-to-Image Retrieval for Parts-of-Speech Imbalance in Vision-Language Models","display_name":"Bridging the Lexical Gap: Generative Text-to-Image Retrieval for Parts-of-Speech Imbalance in Vision-Language Models","publication_year":2024,"publication_date":"2024-10-23","ids":{"openalex":"https://openalex.org/W4403713345","doi":"https://doi.org/10.1145/3689091.3690089"},"language":"en","primary_location":{"id":"doi:10.1145/3689091.3690089","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3689091.3690089","pdf_url":null,"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 2nd International Workshop on Deep Multimodal Generation and Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3689091.3690089","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Hyesu Hwang","orcid":"https://orcid.org/0009-0009-8673-2432"},"institutions":[{"id":"https://openalex.org/I124633538","display_name":"University of Seoul","ror":"https://ror.org/05en5nh73","country_code":"KR","type":"education","lineage":["https://openalex.org/I124633538"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyesu Hwang","raw_affiliation_strings":["University of Seoul, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0009-8673-2432","affiliations":[{"raw_affiliation_string":"University of Seoul, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I124633538"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Daeun Kim","orcid":"https://orcid.org/0009-0003-9545-8937"},"institutions":[{"id":"https://openalex.org/I124633538","display_name":"University of Seoul","ror":"https://ror.org/05en5nh73","country_code":"KR","type":"education","lineage":["https://openalex.org/I124633538"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Daeun Kim","raw_affiliation_strings":["University of Seoul, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0003-9545-8937","affiliations":[{"raw_affiliation_string":"University of Seoul, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I124633538"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101573857","display_name":"Jaehui Park","orcid":"https://orcid.org/0000-0002-7385-5494"},"institutions":[{"id":"https://openalex.org/I124633538","display_name":"University of Seoul","ror":"https://ror.org/05en5nh73","country_code":"KR","type":"education","lineage":["https://openalex.org/I124633538"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaehui Park","raw_affiliation_strings":["University of Seoul, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-7385-5494","affiliations":[{"raw_affiliation_string":"University of Seoul, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I124633538"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073211722","display_name":"Yongjin Kwon","orcid":null},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yongjin Kwon","raw_affiliation_strings":["Electronics and Telecommunications Research Institute, Daejeon, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0001-8818-4657","affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I142401562"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2187,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.52005992,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"26","last_page":"34"},"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/T10028","display_name":"Topic Modeling","score":0.9955999851226807,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9947999715805054,"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/bridging","display_name":"Bridging (networking)","score":0.8858425617218018},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7678173780441284},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6946616172790527},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6556327939033508},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6117066144943237},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.43257784843444824},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4121488630771637}],"concepts":[{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.8858425617218018},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7678173780441284},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6946616172790527},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6556327939033508},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6117066144943237},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.43257784843444824},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4121488630771637},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3689091.3690089","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3689091.3690089","pdf_url":null,"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 2nd International Workshop on Deep Multimodal Generation and Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3689091.3690089","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3689091.3690089","pdf_url":null,"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 2nd International Workshop on Deep Multimodal Generation and Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1566289585","https://openalex.org/W2187089797","https://openalex.org/W2277195237","https://openalex.org/W2533180076","https://openalex.org/W2998702515","https://openalex.org/W3182937942","https://openalex.org/W3187879352","https://openalex.org/W3213351348","https://openalex.org/W4285605356","https://openalex.org/W4312910992","https://openalex.org/W4319299938","https://openalex.org/W4367189613","https://openalex.org/W4385565351","https://openalex.org/W4389518671","https://openalex.org/W4389518784","https://openalex.org/W4389519254","https://openalex.org/W4389520758","https://openalex.org/W4391092966"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W2087346071","https://openalex.org/W2967848559","https://openalex.org/W4299831724","https://openalex.org/W4283803360"],"abstract_inverted_index":{"Retrieving":[0],"relevant":[1,127],"images":[2],"based":[3],"on":[4,93,102],"text":[5,73],"is":[6,66],"challenging":[7],"due":[8],"to":[9,31,56,109,128],"the":[10,33,37,80,94,129,140,146,153,157,161,181,187],"non-trivial":[11],"nature":[12],"of":[13,36,46,77,98,115,142,160,183],"aligning":[14],"vision":[15],"and":[16,51,72,132,163,179],"language":[17,121],"representations.":[18],"Large-scale":[19],"vision-language":[20,82,99,147,188],"models":[21],"such":[22],"as":[23,113],"CLIP":[24],"are":[25,126],"widely":[26],"used":[27],"in":[28,54,79,145,186],"recent":[29],"studies":[30],"leverage":[32],"pre-trained":[34],"knowledge":[35,185],"alignment.":[38],"However,":[39],"our":[40,171],"observations":[41],"reveal":[42],"a":[43,90,107,119,134],"performance":[44,178],"decrease":[45],"60.8%":[47],"for":[48],"verb,":[49],"adjective,":[50],"adverb":[52],"queries":[53,112],"contrast":[55],"noun":[57],"queries.":[58,117],"With":[59],"preliminary":[60],"studies,":[61],"we":[62,150],"found":[63],"that":[64,87,125,137,170],"there":[65],"an":[67],"insufficient":[68],"alignment":[69,144],"between":[70],"image":[71],"regarding":[74],"specific":[75],"parts":[76,141],"speech":[78,143],"popular":[81],"models.":[83,100,189],"We":[84],"also":[85],"observed":[86],"nouns":[88,124],"have":[89],"high":[91],"influence":[92],"text-to-image":[95,176],"retrieval":[96,177],"results":[97],"Based":[101],"this,":[103],"this":[104],"paper":[105],"proposes":[106],"method":[108,172],"generate":[110],"noun-based":[111],"part":[114],"rewriting":[116],"First,":[118],"large":[120],"model":[122],"extracts":[123],"initial":[130],"query":[131,136,155,162],"generates":[133],"hypothetical":[135,154],"best":[138],"matches":[139],"model.":[148],"Then,":[149],"verify":[151],"whether":[152],"preserves":[156],"original":[158],"intent":[159],"iteratively":[164],"rewrite":[165],"it.":[166],"Our":[167],"experiments":[168],"show":[169],"can":[173],"significantly":[174],"enhance":[175],"highlight":[180],"understanding":[182],"lexical":[184]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}