{"id":"https://openalex.org/W4307186884","doi":"https://doi.org/10.1145/3552484.3555751","title":"Text-based Image Editing for Food Images with CLIP","display_name":"Text-based Image Editing for Food Images with CLIP","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4307186884","doi":"https://doi.org/10.1145/3552484.3555751"},"language":"en","primary_location":{"id":"doi:10.1145/3552484.3555751","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3552484.3555751","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th International Workshop on Multimedia Assisted Dietary Management on Multimedia Assisted Dietary Management","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/A5101628755","display_name":"Kazuhiro Yamamoto","orcid":"https://orcid.org/0000-0001-5647-6735"},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Kohei Yamamoto","raw_affiliation_strings":["The University of Electro-Communications, Chofu-shi, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Electro-Communications, Chofu-shi, Tokyo, Japan","institution_ids":["https://openalex.org/I20529979"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054600485","display_name":"\u202aKeiji Yanai\u202c","orcid":"https://orcid.org/0000-0002-0431-183X"},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keiji Yanai","raw_affiliation_strings":["The University of Electro-Communications, Chofu-shi, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Electro-Communications, Chofu-shi, Tokyo, Japan","institution_ids":["https://openalex.org/I20529979"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101628755"],"corresponding_institution_ids":["https://openalex.org/I20529979"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09850913,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"29","last_page":"37"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9678000211715698,"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":0.9678000211715698,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.944599986076355,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9423999786376953,"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":0.7516164779663086},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.7381643056869507},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.5725036263465881},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5386495590209961},{"id":"https://openalex.org/keywords/image-manipulation","display_name":"Image manipulation","score":0.48688140511512756},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4661482572555542},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4660799205303192},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4515126049518585},{"id":"https://openalex.org/keywords/image-synthesis","display_name":"Image synthesis","score":0.44385677576065063},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09524911642074585},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.043691784143447876}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7516164779663086},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.7381643056869507},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.5725036263465881},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5386495590209961},{"id":"https://openalex.org/C2987933465","wikidata":"https://www.wikidata.org/wiki/Q141130","display_name":"Image manipulation","level":3,"score":0.48688140511512756},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4661482572555542},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4660799205303192},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4515126049518585},{"id":"https://openalex.org/C2989087649","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Image synthesis","level":3,"score":0.44385677576065063},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09524911642074585},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.043691784143447876},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3552484.3555751","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3552484.3555751","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th International Workshop on Multimedia Assisted Dietary Management on Multimedia Assisted Dietary Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"display_name":"Zero hunger","id":"https://metadata.un.org/sdg/2"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1928278792","https://openalex.org/W2737041163","https://openalex.org/W2893749619","https://openalex.org/W2896655446","https://openalex.org/W2904367110","https://openalex.org/W2963373786","https://openalex.org/W2963981733","https://openalex.org/W3036167779","https://openalex.org/W3048693722","https://openalex.org/W3110969460","https://openalex.org/W3111551570","https://openalex.org/W3130296038","https://openalex.org/W3140373187","https://openalex.org/W3187570516","https://openalex.org/W4301206121","https://openalex.org/W6687483927","https://openalex.org/W6718379498","https://openalex.org/W6739901393","https://openalex.org/W6757817989","https://openalex.org/W6766037382","https://openalex.org/W6770484295","https://openalex.org/W6779823529","https://openalex.org/W6791846518","https://openalex.org/W6800895557"],"related_works":["https://openalex.org/W2144279858","https://openalex.org/W2772330423","https://openalex.org/W2770776392","https://openalex.org/W3176454756","https://openalex.org/W3163523050","https://openalex.org/W3122887115","https://openalex.org/W3006381446","https://openalex.org/W4295277049","https://openalex.org/W4307186884","https://openalex.org/W2147435674"],"abstract_inverted_index":{"Recently,":[0],"the":[1,60,75,78,89],"large-scale":[2],"language-image":[3],"pre-trained":[4],"model,":[5],"such":[6],"as":[7],"CLIP,":[8],"has":[9,64],"drawn":[10],"much":[11],"attention":[12],"due":[13],"to":[14],"its":[15],"remarkable":[16],"ability":[17],"for":[18,35],"various":[19],"tasks,":[20],"including":[21],"classification":[22],"and":[23,30,39,49,87],"image":[24,37,41,62,83,93],"synthesis.":[25],"The":[26],"combination":[27,46],"of":[28,44,47,77,91],"CLIP":[29,48],"GAN":[31,50],"can":[32],"be":[33],"used":[34],"text-based":[36,40,81],"manipulation":[38,84,94],"synthesis.Several":[42],"models":[43],"a":[45],"have":[51],"been":[52,66],"proposed":[53],"so":[54],"far.":[55],"However,":[56],"their":[57],"effectiveness":[58],"in":[59],"food":[61,82,92],"domain":[63],"not":[65],"examined":[67],"comprehensively":[68],"yet.":[69],"In":[70],"this":[71],"paper,":[72],"we":[73],"reported":[74],"results":[76],"experiments":[79],"on":[80],"using":[85],"VQGAN-CLIP":[86],"discussed":[88],"possibility":[90],"by":[95],"texts.":[96]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}