{"id":"https://openalex.org/W4387698264","doi":"https://doi.org/10.1145/3607541.3616818","title":"Nonword-to-Image Generation Considering Perceptual Association of Phonetically Similar Words","display_name":"Nonword-to-Image Generation Considering Perceptual Association of Phonetically Similar Words","publication_year":2023,"publication_date":"2023-10-17","ids":{"openalex":"https://openalex.org/W4387698264","doi":"https://doi.org/10.1145/3607541.3616818"},"language":"en","primary_location":{"id":"doi:10.1145/3607541.3616818","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3607541.3616818","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st International Workshop on Multimedia Content Generation and Evaluation: New Methods and Practice","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://nagoya.repo.nii.ac.jp/records/2010850","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031528895","display_name":"Chihaya Matsuhira","orcid":"https://orcid.org/0000-0003-2453-4560"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Chihaya Matsuhira","raw_affiliation_strings":["Nagoya University, Nagoya, Japan"],"raw_orcid":"https://orcid.org/0000-0003-2453-4560","affiliations":[{"raw_affiliation_string":"Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102907439","display_name":"Marc A. Kastner","orcid":"https://orcid.org/0000-0002-9193-5973"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Marc A. Kastner","raw_affiliation_strings":["Kyoto University, Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0002-9193-5973","affiliations":[{"raw_affiliation_string":"Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047823141","display_name":"Takahiro Komamizu","orcid":"https://orcid.org/0000-0002-3041-4330"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takahiro Komamizu","raw_affiliation_strings":["Nagoya University, Nagoya, Japan"],"raw_orcid":"https://orcid.org/0000-0002-3041-4330","affiliations":[{"raw_affiliation_string":"Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036735172","display_name":"Takatsugu Hirayama","orcid":"https://orcid.org/0000-0001-6290-9680"},"institutions":[{"id":"https://openalex.org/I84985371","display_name":"University of Human Environments","ror":"https://ror.org/029smmd76","country_code":"JP","type":"education","lineage":["https://openalex.org/I84985371"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takatsugu Hirayama","raw_affiliation_strings":["University of Human Environments, Okazaki, Japan"],"raw_orcid":"https://orcid.org/0000-0001-6290-9680","affiliations":[{"raw_affiliation_string":"University of Human Environments, Okazaki, Japan","institution_ids":["https://openalex.org/I84985371"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058196829","display_name":"Keisuke Doman","orcid":"https://orcid.org/0000-0001-6040-4988"},"institutions":[{"id":"https://openalex.org/I98940699","display_name":"Chukyo University","ror":"https://ror.org/04ajrmg05","country_code":"JP","type":"education","lineage":["https://openalex.org/I98940699"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keisuke Doman","raw_affiliation_strings":["Chukyo University, Toyota, Japan"],"raw_orcid":"https://orcid.org/0000-0001-6040-4988","affiliations":[{"raw_affiliation_string":"Chukyo University, Toyota, Japan","institution_ids":["https://openalex.org/I98940699"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034941095","display_name":"Ichiro Ide","orcid":"https://orcid.org/0000-0003-3942-9296"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ichiro Ide","raw_affiliation_strings":["Nagoya University, Nagoya, Japan"],"raw_orcid":"https://orcid.org/0000-0003-3942-9296","affiliations":[{"raw_affiliation_string":"Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"115","last_page":"125"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9939000010490417,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9939000010490417,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9873999953269958,"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":0.9872999787330627,"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":0.7469367980957031},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5868329405784607},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5811269283294678},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5804920792579651},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5760124325752258},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.533562421798706},{"id":"https://openalex.org/keywords/association","display_name":"Association (psychology)","score":0.4875435531139374},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4858660101890564},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3332406282424927},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.19420480728149414},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09447285532951355}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7469367980957031},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5868329405784607},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5811269283294678},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5804920792579651},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5760124325752258},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.533562421798706},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.4875435531139374},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4858660101890564},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3332406282424927},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.19420480728149414},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09447285532951355},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3607541.3616818","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3607541.3616818","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st International Workshop on Multimedia Content Generation and Evaluation: New Methods and Practice","raw_type":"proceedings-article"},{"id":"pmh:oai:irdb.nii.ac.jp:01152:0006258591","is_oa":true,"landing_page_url":"https://nagoya.repo.nii.ac.jp/records/2010850","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"McGE '23: Proceedings of the 1st International Workshop on Multimedia Content Generation and Evaluation: New Methods and Practice","raw_type":"conference paper"}],"best_oa_location":{"id":"pmh:oai:irdb.nii.ac.jp:01152:0006258591","is_oa":true,"landing_page_url":"https://nagoya.repo.nii.ac.jp/records/2010850","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"McGE '23: Proceedings of the 1st International Workshop on Multimedia Content Generation and Evaluation: New Methods and Practice","raw_type":"conference paper"},"sustainable_development_goals":[{"score":0.8199999928474426,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G4943039908","display_name":null,"funder_award_id":"22H03612","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W4941964","https://openalex.org/W1614298861","https://openalex.org/W1990948551","https://openalex.org/W2962784628","https://openalex.org/W2973029704","https://openalex.org/W3127602238","https://openalex.org/W4224035735","https://openalex.org/W4224951336","https://openalex.org/W4281485151","https://openalex.org/W4284898017","https://openalex.org/W4299814950","https://openalex.org/W4302470888","https://openalex.org/W4312599396","https://openalex.org/W4312933868","https://openalex.org/W4321275178","https://openalex.org/W4323570466","https://openalex.org/W6949294850"],"related_works":["https://openalex.org/W2352440174","https://openalex.org/W4309440960","https://openalex.org/W2062168445","https://openalex.org/W2348940229","https://openalex.org/W2363046693","https://openalex.org/W2389491697","https://openalex.org/W2375480909","https://openalex.org/W2353314428","https://openalex.org/W4301044699","https://openalex.org/W2012019886"],"abstract_inverted_index":{"Text-to-Image":[0],"(T2I)":[1],"generation":[2,63,149],"has":[3],"long":[4],"been":[5],"a":[6,22,49,71,91,127,146,158],"popular":[7],"field":[8],"of":[9,24,27,61,77,96,130,134,154,174],"multimedia":[10],"processing.":[11],"Recent":[12],"advances":[13],"in":[14,163,178],"large-scale":[15],"vision":[16],"and":[17,55,142,181],"language":[18,50,182],"pretraining":[19],"have":[20,45],"brought":[21],"number":[23],"models":[25,64],"capable":[26],"very":[28],"high-quality":[29],"T2I":[30,62,148],"generation.":[31],"However,":[32],"they":[33,120],"are":[34],"reported":[35],"to":[36],"generate":[37],"unexpected":[38],"images":[39,89,133,156],"when":[40,119],"users":[41],"input":[42],"words":[43,54,118],"that":[44,73,86,108],"no":[46],"definition":[47],"within":[48],"(nonwords),":[51],"including":[52],"coined":[53],"pseudo-words.":[56],"To":[57],"make":[58],"the":[59,87,94,105,122,131,135,161,172,175],"behavior":[60],"against":[65],"nonwords":[66,113],"more":[67],"intuitive,":[68],"we":[69],"propose":[70],"method":[72,137,177],"considers":[74],"phonetic":[75,81,140],"information":[76],"text":[78],"inputs.":[79],"The":[80,151],"similarity":[82],"is":[83,102],"adopted":[84],"so":[85],"generated":[88,132,155],"from":[90],"nonword":[92,159],"contain":[93],"concept":[95],"its":[97],"phonetically":[98,116],"similar":[99,117],"words.":[100],"This":[101],"based":[103],"on":[104],"psycholinguistic":[106],"finding":[107],"humans":[109],"would":[110],"also":[111],"associate":[112],"with":[114,138],"their":[115],"perceive":[121],"sound.":[123],"Our":[124],"evaluations":[125],"confirm":[126],"better":[128],"agreement":[129],"proposed":[136,176],"both":[139],"relationships":[141],"human":[143],"expectations":[144],"than":[145],"conventional":[147],"model.":[150],"cross-lingual":[152],"comparison":[153],"for":[157],"highlights":[160],"differences":[162],"language-specific":[164],"nonword-imagery":[165],"correspondences.":[166],"These":[167],"results":[168],"provide":[169],"insight":[170],"into":[171],"usefulness":[173],"brand":[179],"naming":[180],"learning.":[183]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}