{"id":"https://openalex.org/W4388834708","doi":"https://doi.org/10.3390/s23229287","title":"Manipulation Direction: Evaluating Text-Guided Image Manipulation Based on Similarity between Changes in Image and Text Modalities","display_name":"Manipulation Direction: Evaluating Text-Guided Image Manipulation Based on Similarity between Changes in Image and Text Modalities","publication_year":2023,"publication_date":"2023-11-20","ids":{"openalex":"https://openalex.org/W4388834708","doi":"https://doi.org/10.3390/s23229287","pmid":"https://pubmed.ncbi.nlm.nih.gov/38005673"},"language":"en","primary_location":{"id":"doi:10.3390/s23229287","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s23229287","pdf_url":"https://www.mdpi.com/1424-8220/23/22/9287/pdf?version=1700487235","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1424-8220/23/22/9287/pdf?version=1700487235","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089220692","display_name":"Yuto Watanabe","orcid":"https://orcid.org/0000-0002-9841-4089"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuto Watanabe","raw_affiliation_strings":["Graduate School of Information Science and Technology, Hokkaido University, N-14, W-9, Kita-ku, Sapporo 060-0814, Hokkaido, Japan"],"raw_orcid":"https://orcid.org/0000-0002-9841-4089","affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, Hokkaido University, N-14, W-9, Kita-ku, Sapporo 060-0814, Hokkaido, Japan","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002757875","display_name":"Ren Togo","orcid":"https://orcid.org/0000-0002-4474-3995"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ren Togo","raw_affiliation_strings":["Faculty of Information Science and Technology, Hokkaido University, N-14, W-9, Kita-ku, Sapporo 060-0814, Hokkaido, Japan"],"raw_orcid":"https://orcid.org/0000-0002-4474-3995","affiliations":[{"raw_affiliation_string":"Faculty of Information Science and Technology, Hokkaido University, N-14, W-9, Kita-ku, Sapporo 060-0814, Hokkaido, Japan","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033215072","display_name":"Keisuke Maeda","orcid":"https://orcid.org/0000-0001-8039-3462"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keisuke Maeda","raw_affiliation_strings":["Faculty of Information Science and Technology, Hokkaido University, N-14, W-9, Kita-ku, Sapporo 060-0814, Hokkaido, Japan"],"raw_orcid":"https://orcid.org/0000-0001-8039-3462","affiliations":[{"raw_affiliation_string":"Faculty of Information Science and Technology, Hokkaido University, N-14, W-9, Kita-ku, Sapporo 060-0814, Hokkaido, Japan","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009032240","display_name":"Takahiro Ogawa","orcid":"https://orcid.org/0000-0001-5332-8112"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takahiro Ogawa","raw_affiliation_strings":["Faculty of Information Science and Technology, Hokkaido University, N-14, W-9, Kita-ku, Sapporo 060-0814, Hokkaido, Japan"],"raw_orcid":"https://orcid.org/0000-0001-5332-8112","affiliations":[{"raw_affiliation_string":"Faculty of Information Science and Technology, Hokkaido University, N-14, W-9, Kita-ku, Sapporo 060-0814, Hokkaido, Japan","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"last","author":{"id":null,"display_name":"Miki Haseyama","orcid":"https://orcid.org/0000-0003-1496-1761"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Miki Haseyama","raw_affiliation_strings":["Faculty of Information Science and Technology, Hokkaido University, N-14, W-9, Kita-ku, Sapporo 060-0814, Hokkaido, Japan"],"raw_orcid":"https://orcid.org/0000-0003-1496-1761","affiliations":[{"raw_affiliation_string":"Faculty of Information Science and Technology, Hokkaido University, N-14, W-9, Kita-ku, Sapporo 060-0814, Hokkaido, Japan","institution_ids":["https://openalex.org/I205349734"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I205349734"],"apc_list":{"value":2400,"currency":"CHF","value_usd":2673},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2673},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1733528,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"23","issue":"22","first_page":"9287","last_page":"9287"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.991100013256073,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.991100013256073,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9836000204086304,"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":0.9814000129699707,"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/image","display_name":"Image (mathematics)","score":0.6771765947341919},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6494787335395813},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6201967000961304},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.618920087814331},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5996438264846802},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5863796472549438},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5474293231964111},{"id":"https://openalex.org/keywords/image-manipulation","display_name":"Image manipulation","score":0.5269299745559692},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40553218126296997},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.39850932359695435},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35195988416671753}],"concepts":[{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6771765947341919},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6494787335395813},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6201967000961304},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.618920087814331},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5996438264846802},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5863796472549438},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5474293231964111},{"id":"https://openalex.org/C2987933465","wikidata":"https://www.wikidata.org/wiki/Q141130","display_name":"Image manipulation","level":3,"score":0.5269299745559692},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40553218126296997},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39850932359695435},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35195988416671753},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.3390/s23229287","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s23229287","pdf_url":"https://www.mdpi.com/1424-8220/23/22/9287/pdf?version=1700487235","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},{"id":"pmid:38005673","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38005673","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors (Basel, Switzerland)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:10675000","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10675000","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10675000/pdf/sensors-23-09287.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors (Basel)","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:c675d897a6854ce28de499b826e4587c","is_oa":true,"landing_page_url":"https://doaj.org/article/c675d897a6854ce28de499b826e4587c","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors, Vol 23, Iss 22, p 9287 (2023)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1424-8220/23/22/9287/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/s23229287","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/s23229287","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s23229287","pdf_url":"https://www.mdpi.com/1424-8220/23/22/9287/pdf?version=1700487235","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.44999998807907104,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G4092381066","display_name":"General-purpose deep learning theory for ultra-low computational complexity and low capacity in the age of edge AI","funder_award_id":"23K21676","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4562627959","display_name":"\u753b\u50cf\u8a8d\u8b58\u306e\u9ad8\u5ea6\u5316\u306b\u5411\u3051\u305f\u753b\u50cf\u306e\u64ae\u5f71\u65b9\u6cd5\u3092\u6700\u9069\u5316\u3059\u308b\u7570\u74b0\u5883\u7570\u7a2e\u30c7\u30fc\u30bf\u9069\u5fdc\u578bAI\u306e\u69cb\u7bc9","funder_award_id":"23K11211","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7580542989","display_name":null,"funder_award_id":"JP23K11211","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8595477435","display_name":null,"funder_award_id":"JP23K11141","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8739887802","display_name":null,"funder_award_id":"JP21H03456","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":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4388834708.pdf"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1933349210","https://openalex.org/W1947481528","https://openalex.org/W2064675550","https://openalex.org/W2133665775","https://openalex.org/W2143668817","https://openalex.org/W2183341477","https://openalex.org/W2185175083","https://openalex.org/W2194775991","https://openalex.org/W2295537950","https://openalex.org/W2302548814","https://openalex.org/W2326925005","https://openalex.org/W2508429489","https://openalex.org/W2533598788","https://openalex.org/W2754213847","https://openalex.org/W2891417743","https://openalex.org/W2962770929","https://openalex.org/W2963420272","https://openalex.org/W2963920537","https://openalex.org/W2963966654","https://openalex.org/W2963981733","https://openalex.org/W2964013315","https://openalex.org/W2964313012","https://openalex.org/W3034319502","https://openalex.org/W3035316078","https://openalex.org/W3103635814","https://openalex.org/W3118694826","https://openalex.org/W3135367836","https://openalex.org/W3174194560","https://openalex.org/W3193652355","https://openalex.org/W3195830874","https://openalex.org/W3216551675","https://openalex.org/W4213186350","https://openalex.org/W4214926101","https://openalex.org/W4308235627","https://openalex.org/W4386065596","https://openalex.org/W4386072307","https://openalex.org/W4386076215","https://openalex.org/W4386076458","https://openalex.org/W6678470764","https://openalex.org/W6686423066","https://openalex.org/W6713645886","https://openalex.org/W6718379498","https://openalex.org/W6779823529"],"related_works":["https://openalex.org/W2185469136","https://openalex.org/W2011264131","https://openalex.org/W4306353150","https://openalex.org/W2026860389","https://openalex.org/W8219677","https://openalex.org/W3216879894","https://openalex.org/W2890132085","https://openalex.org/W3207883763","https://openalex.org/W2168054807","https://openalex.org/W2058990474"],"abstract_inverted_index":{"At":[0],"present,":[1],"text-guided":[2,52,78,116],"image":[3,19,30,53,79,86,117,125,132],"manipulation":[4,80,133],"is":[5,60],"a":[6,68],"notable":[7],"subject":[8],"of":[9,51,77,97,115],"study":[10,63],"in":[11],"the":[12,29,33,47,75,95,113,131,140,165,170],"vision":[13],"and":[14,20,49,70,87,101,105,129,134,146,161],"language":[15],"field.":[16],"Given":[17],"an":[18,124,153],"text":[21,88],"as":[22,94],"inputs,":[23],"these":[24],"methods":[25],"aim":[26],"to":[27,32,45,111,169],"manipulate":[28],"according":[31],"text,":[34],"while":[35],"preserving":[36],"text-irrelevant":[37],"regions.":[38],"Although":[39],"there":[40,151],"has":[41,126],"been":[42],"extensive":[43],"research":[44,55],"improve":[46],"versatility":[48],"performance":[50,58,76,114],"manipulation,":[54,118],"on":[56,83,144],"its":[57],"evaluation":[59],"inadequate.":[61],"This":[62],"proposes":[64],"Manipulation":[65],"Direction":[66],"(MD),":[67],"logical":[69],"robust":[71],"metric,":[72],"which":[73],"evaluates":[74],"by":[81],"focusing":[82],"changes":[84,98],"between":[85,99,156],"modalities.":[89],"Specifically,":[90],"we":[91,119],"define":[92],"MD":[93,110,159],"consistency":[96],"images":[100,167],"texts":[102],"occurring":[103],"before":[104,128],"after":[106,130],"manipulation.":[107],"By":[108],"using":[109],"evaluate":[112,122],"can":[120],"comprehensively":[121],"how":[123],"changed":[127],"whether":[135],"this":[136],"change":[137],"agrees":[138],"with":[139],"text.":[141],"Extensive":[142],"experiments":[143],"Multi-Modal-CelebA-HQ":[145],"Caltech-UCSD":[147],"Birds":[148],"confirmed":[149],"that":[150],"was":[152],"impressive":[154],"correlation":[155],"our":[157],"calculated":[158],"scores":[160,163],"subjective":[162],"for":[164],"manipulated":[166],"compared":[168],"existing":[171],"metrics.":[172]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
