{"id":"https://openalex.org/W4224932539","doi":"https://doi.org/10.1109/icassp43922.2022.9746970","title":"Generative Adversarial Network Including Referring Image Segmentation For Text-Guided Image Manipulation","display_name":"Generative Adversarial Network Including Referring Image Segmentation For Text-Guided Image Manipulation","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224932539","doi":"https://doi.org/10.1109/icassp43922.2022.9746970"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746970","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746970","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/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":["Hokkaido University,School of Engineering,Japan","School of Engineering, Hokkaido University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hokkaido University,School of Engineering,Japan","institution_ids":["https://openalex.org/I205349734"]},{"raw_affiliation_string":"School of Engineering, Hokkaido University, 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/I156971308","display_name":"Hokkaido University of Education","ror":"https://ror.org/02gn38d51","country_code":"JP","type":"education","lineage":["https://openalex.org/I156971308"]},{"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":["Hokkaido University,Education and Research Center for Mathematical and Data Science,Japan","Education and Research Center for Mathematical and Data Science, Hokkaido University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hokkaido University,Education and Research Center for Mathematical and Data Science,Japan","institution_ids":["https://openalex.org/I156971308"]},{"raw_affiliation_string":"Education and Research Center for Mathematical and Data Science, Hokkaido University, 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":["Hokkaido University,Office of Institutional Research,Japan","Office of Institutional Research, Hokkaido University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hokkaido University,Office of Institutional Research,Japan","institution_ids":["https://openalex.org/I205349734"]},{"raw_affiliation_string":"Office of Institutional Research, Hokkaido University, 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":["Hokkaido University,Faculty of Information Science and Technology,Japan","Faculty of Information Science and Technology, Hokkaido University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hokkaido University,Faculty of Information Science and Technology,Japan","institution_ids":["https://openalex.org/I205349734"]},{"raw_affiliation_string":"Faculty of Information Science and Technology, Hokkaido University, Japan","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"last","author":{"id":null,"display_name":"Miki Haseyama","orcid":null},"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":"Miki Haseyama","raw_affiliation_strings":["Hokkaido University,Faculty of Information Science and Technology,Japan","Faculty of Information Science and Technology, Hokkaido University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hokkaido University,Faculty of Information Science and Technology,Japan","institution_ids":["https://openalex.org/I205349734"]},{"raw_affiliation_string":"Faculty of Information Science and Technology, Hokkaido University, Japan","institution_ids":["https://openalex.org/I205349734"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"30","issue":null,"first_page":"4818","last_page":"4822"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.996999979019165,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.996999979019165,"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/T13114","display_name":"Image Processing Techniques and Applications","score":0.9939000010490417,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9758999943733215,"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":0.8068453073501587},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6955307722091675},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6759477853775024},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.657585859298706},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6507800817489624},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6036023497581482},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5998880863189697},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5887364745140076},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4771149456501007},{"id":"https://openalex.org/keywords/generative-adversarial-network","display_name":"Generative adversarial network","score":0.4479045569896698},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4341222643852234},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.43082353472709656},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06288036704063416}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8068453073501587},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6955307722091675},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6759477853775024},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.657585859298706},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6507800817489624},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6036023497581482},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5998880863189697},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5887364745140076},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4771149456501007},{"id":"https://openalex.org/C2988773926","wikidata":"https://www.wikidata.org/wiki/Q25104379","display_name":"Generative adversarial network","level":3,"score":0.4479045569896698},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4341222643852234},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.43082353472709656},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06288036704063416},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746970","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746970","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1591801644","https://openalex.org/W1686810756","https://openalex.org/W1797268635","https://openalex.org/W2295537950","https://openalex.org/W2326925005","https://openalex.org/W2461158874","https://openalex.org/W2475287302","https://openalex.org/W2489434015","https://openalex.org/W2621350877","https://openalex.org/W2950111065","https://openalex.org/W2950404765","https://openalex.org/W2962793481","https://openalex.org/W2963073614","https://openalex.org/W2963373786","https://openalex.org/W2963420272","https://openalex.org/W2963920537","https://openalex.org/W2963966654","https://openalex.org/W2964013315","https://openalex.org/W2972328244","https://openalex.org/W2989505547","https://openalex.org/W3034319502","https://openalex.org/W3034325957","https://openalex.org/W3035316078","https://openalex.org/W3104956649","https://openalex.org/W3193652355","https://openalex.org/W4301206121","https://openalex.org/W4320013936","https://openalex.org/W6631190155","https://openalex.org/W6635446068","https://openalex.org/W6637373629","https://openalex.org/W6638319203","https://openalex.org/W6640174519","https://openalex.org/W6701655646","https://openalex.org/W6718379498","https://openalex.org/W6739139180","https://openalex.org/W6755102824","https://openalex.org/W6765779288","https://openalex.org/W6767384525","https://openalex.org/W6784364625"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W2888032422","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4395044357","https://openalex.org/W2996316059","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W2087346071"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,65],"novel":[4],"generative":[5,52],"adversarial":[6,53],"network":[7,54],"to":[8,27,63,108],"improve":[9,155],"the":[10,34,51,70,75,79,83,85,90,97,109,114,118,130,136,140,143,150,156],"performance":[11,157],"of":[12,78,132,158],"image":[13,24,31,48,56,60,159],"manipulation":[14,25],"using":[15],"natural":[16],"language":[17],"descriptions":[18],"that":[19,68,149],"contain":[20],"desired":[21],"attributes.":[22],"Text-guided":[23],"aims":[26,62],"semantically":[28],"manipulate":[29,113],"an":[30,126],"aligned":[32,116],"with":[33,117],"text":[35,119],"description":[36],"while":[37],"preserving":[38],"text-irrelevant":[39,144],"regions.":[40,145],"To":[41],"achieve":[42,125],"this,":[43],"we":[44],"newly":[45],"introduce":[46],"referring":[47,59],"segmentation":[49,61,66,80],"into":[50],"for":[55],"manipulation.":[57,160],"The":[58],"generate":[64],"mask":[67,81],"extracts":[69],"text-relevant":[71,91,110,137],"region.":[72],"By":[73],"utilizing":[74],"feature":[76],"map":[77],"in":[82,135,142],"network,":[84],"proposed":[86,151],"method":[87,152],"explicitly":[88],"distinguishes":[89],"and":[92,95,112,139],"irrelevant":[93],"regions":[94],"has":[96],"following":[98],"two":[99],"contributions.":[100],"First,":[101],"our":[102,122],"model":[103,123],"can":[104,124,153],"pay":[105],"attention":[106],"only":[107],"region":[111,115,138],"description.":[120],"Second,":[121],"appropriate":[127],"balance":[128],"between":[129],"generation":[131],"accurate":[133],"attributes":[134],"reconstruction":[141],"Experimental":[146],"results":[147],"show":[148],"significantly":[154]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}