{"id":"https://openalex.org/W4386598426","doi":"https://doi.org/10.1109/icip49359.2023.10223174","title":"BATINeT: Background-Aware Text to Image Synthesis and Manipulation Network","display_name":"BATINeT: Background-Aware Text to Image Synthesis and Manipulation Network","publication_year":2023,"publication_date":"2023-09-11","ids":{"openalex":"https://openalex.org/W4386598426","doi":"https://doi.org/10.1109/icip49359.2023.10223174"},"language":"en","primary_location":{"id":"doi:10.1109/icip49359.2023.10223174","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip49359.2023.10223174","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Image Processing (ICIP)","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/A5008003363","display_name":"Ryugo Morita","orcid":"https://orcid.org/0009-0007-6324-9291"},"institutions":[{"id":"https://openalex.org/I204291657","display_name":"Hosei University","ror":"https://ror.org/00bx6dj65","country_code":"JP","type":"education","lineage":["https://openalex.org/I204291657"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryugo Morita","raw_affiliation_strings":["Hosei University,Faculty of Science and Engineering,Tokyo,Japan","Faculty of Science and Engineering, Hosei University, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hosei University,Faculty of Science and Engineering,Tokyo,Japan","institution_ids":["https://openalex.org/I204291657"]},{"raw_affiliation_string":"Faculty of Science and Engineering, Hosei University, Tokyo, Japan","institution_ids":["https://openalex.org/I204291657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019348755","display_name":"Zhiqiang Zhang","orcid":"https://orcid.org/0000-0002-2408-366X"},"institutions":[{"id":"https://openalex.org/I204291657","display_name":"Hosei University","ror":"https://ror.org/00bx6dj65","country_code":"JP","type":"education","lineage":["https://openalex.org/I204291657"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Zhiqiang Zhang","raw_affiliation_strings":["Hosei University,Faculty of Science and Engineering,Tokyo,Japan","Faculty of Science and Engineering, Hosei University, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hosei University,Faculty of Science and Engineering,Tokyo,Japan","institution_ids":["https://openalex.org/I204291657"]},{"raw_affiliation_string":"Faculty of Science and Engineering, Hosei University, Tokyo, Japan","institution_ids":["https://openalex.org/I204291657"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021863826","display_name":"Jinjia Zhou","orcid":"https://orcid.org/0000-0002-5078-0522"},"institutions":[{"id":"https://openalex.org/I204291657","display_name":"Hosei University","ror":"https://ror.org/00bx6dj65","country_code":"JP","type":"education","lineage":["https://openalex.org/I204291657"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jinjia Zhou","raw_affiliation_strings":["Hosei University,Faculty of Science and Engineering,Tokyo,Japan","Faculty of Science and Engineering, Hosei University, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hosei University,Faculty of Science and Engineering,Tokyo,Japan","institution_ids":["https://openalex.org/I204291657"]},{"raw_affiliation_string":"Faculty of Science and Engineering, Hosei University, Tokyo, Japan","institution_ids":["https://openalex.org/I204291657"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4491,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.64024287,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"765","last_page":"769"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9983999729156494,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9983999729156494,"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":0.9983000159263611,"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":0.996399998664856,"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":0.8248056173324585},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.7017727494239807},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7015693187713623},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6576067209243774},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6138256192207336},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6040068864822388},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5245442986488342},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5171222686767578},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.47703737020492554},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.4743860065937042},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4446071684360504},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.42776620388031006},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.42502737045288086},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3530266582965851},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3318201005458832},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32627689838409424}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8248056173324585},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.7017727494239807},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7015693187713623},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6576067209243774},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6138256192207336},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6040068864822388},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5245442986488342},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5171222686767578},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.47703737020492554},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.4743860065937042},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4446071684360504},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.42776620388031006},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.42502737045288086},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3530266582965851},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3318201005458832},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32627689838409424},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip49359.2023.10223174","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip49359.2023.10223174","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1797268635","https://openalex.org/W2754213847","https://openalex.org/W2798312861","https://openalex.org/W2963073614","https://openalex.org/W2963373786","https://openalex.org/W2964309882","https://openalex.org/W2966792645","https://openalex.org/W3034419329","https://openalex.org/W3035316078","https://openalex.org/W3103635814","https://openalex.org/W3129576130","https://openalex.org/W3163145292","https://openalex.org/W4226125322","https://openalex.org/W4281485151","https://openalex.org/W4312502952","https://openalex.org/W4312977351","https://openalex.org/W4319299830","https://openalex.org/W4320013936","https://openalex.org/W4365421094","https://openalex.org/W6638319203","https://openalex.org/W6718379498","https://openalex.org/W6729966448","https://openalex.org/W6748481559","https://openalex.org/W6750427546","https://openalex.org/W6790978476","https://openalex.org/W6795432354","https://openalex.org/W6810471779","https://openalex.org/W6810940779","https://openalex.org/W6838639034"],"related_works":["https://openalex.org/W2012531322","https://openalex.org/W2402761219","https://openalex.org/W2785900585","https://openalex.org/W2353730437","https://openalex.org/W2490303674","https://openalex.org/W86540734","https://openalex.org/W2372390102","https://openalex.org/W2002113093","https://openalex.org/W4292830139","https://openalex.org/W4319309705"],"abstract_inverted_index":{"Background-Induced":[0],"Text2Image":[1,42],"(BIT2I)":[2],"aims":[3],"to":[4,9,59,101,119,129],"generate":[5],"foreground":[6,23],"content":[7,49,99],"according":[8],"the":[10,13,28,31,47,51,82,87,91,97,108,114,135,141,154,158],"text":[11],"on":[12,20,153],"given":[14],"background":[15,92,102],"image.":[16,93],"Most":[17],"studies":[18],"focus":[19],"generating":[21],"high-quality":[22],"content,":[24],"although":[25],"they":[26],"ignore":[27],"relationship":[29],"between":[30],"two":[32,68],"contents.":[33],"In":[34],"this":[35],"study,":[36],"we":[37,106,125],"analyzed":[38],"a":[39,56],"novel":[40],"Background-Aware":[41,57],"(BAT2I)":[43],"task":[44,138],"in":[45,90],"which":[46,66,111],"generated":[48,98],"matches":[50],"input":[52],"background.":[53],"We":[54,146],"proposed":[55,159],"Text":[58],"Image":[60],"synthesis":[61],"and":[62,75,116,150],"manipulation":[63],"Network":[64,73,77],"(BATINet),":[65],"contains":[67],"key":[69],"components:":[70],"Position":[71],"Detect":[72],"(PDN)":[74],"Harmonize":[76],"(HN).":[78],"The":[79,94],"PDN":[80],"detects":[81],"most":[83,136],"plausible":[84],"position":[85],"of":[86,113,139,143],"text-relevant":[88],"object":[89],"HN":[95],"harmonizes":[96],"referring":[100],"style":[103],"information.":[104],"Finally,":[105],"reconstructed":[107],"generation":[109],"network,":[110],"consists":[112],"multi-GAN":[115],"attention":[117],"module":[118],"match":[120],"more":[121],"user":[122],"preferences.":[123],"Moreover,":[124],"can":[126],"apply":[127],"BATINet":[128],"text-guided":[130],"image":[131],"manipulation.":[132],"It":[133],"solves":[134],"challenging":[137],"manipulating":[140],"shape":[142],"an":[144],"object.":[145],"demonstrated":[147],"through":[148],"qualitative":[149],"quantitative":[151],"evaluations":[152],"CUB":[155],"dataset":[156],"that":[157],"model":[160],"outperforms":[161],"other":[162],"state-of-the-art":[163],"methods.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}