{"id":"https://openalex.org/W4295935122","doi":"https://doi.org/10.1109/tmm.2022.3207000","title":"Language-Based Image Manipulation Built on Language-Guided Ranking","display_name":"Language-Based Image Manipulation Built on Language-Guided Ranking","publication_year":2022,"publication_date":"2022-09-15","ids":{"openalex":"https://openalex.org/W4295935122","doi":"https://doi.org/10.1109/tmm.2022.3207000"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2022.3207000","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3207000","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5054902681","display_name":"Fuxiang Wu","orcid":"https://orcid.org/0000-0002-4542-4486"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Fuxiang Wu","raw_affiliation_strings":["Guangdong Provincial Key Laboratory of Robotics and Intelligent System, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, China","Chinese University of Hong Kong, Hong Kong, SAR, China"],"raw_orcid":"https://orcid.org/0000-0002-4542-4486","affiliations":[{"raw_affiliation_string":"Guangdong Provincial Key Laboratory of Robotics and Intelligent System, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4210145761","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Chinese University of Hong Kong, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100324286","display_name":"Liu Liu","orcid":"https://orcid.org/0000-0002-8128-2788"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Liu Liu","raw_affiliation_strings":["School of Computer Science, Faculty of Engineering, The University of Sydney, Darlington, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-8128-2788","affiliations":[{"raw_affiliation_string":"School of Computer Science, Faculty of Engineering, The University of Sydney, Darlington, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100604062","display_name":"Fusheng Hao","orcid":"https://orcid.org/0000-0003-1490-2235"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Fusheng Hao","raw_affiliation_strings":["Guangdong Provincial Key Laboratory of Robotics and Intelligent System, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, China","Chinese University of Hong Kong, Hong Kong, SAR, China"],"raw_orcid":"https://orcid.org/0000-0003-1490-2235","affiliations":[{"raw_affiliation_string":"Guangdong Provincial Key Laboratory of Robotics and Intelligent System, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4210145761","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Chinese University of Hong Kong, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100635369","display_name":"Fengxiang He","orcid":"https://orcid.org/0000-0001-5584-2385"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fengxiang He","raw_affiliation_strings":["JD Explore Academy, JD.com Inc., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD Explore Academy, JD.com Inc., Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101705358","display_name":"Jun Cheng","orcid":"https://orcid.org/0000-0002-3131-3275"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Jun Cheng","raw_affiliation_strings":["Guangdong Provincial Key Laboratory of Robotics and Intelligent System, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, China","Chinese University of Hong Kong, Hong Kong, SAR, China"],"raw_orcid":"https://orcid.org/0000-0002-3131-3275","affiliations":[{"raw_affiliation_string":"Guangdong Provincial Key Laboratory of Robotics and Intelligent System, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4210145761","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Chinese University of Hong Kong, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2936,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.52927538,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"25","issue":null,"first_page":"6219","last_page":"6231"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9965999722480774,"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":0.9965999722480774,"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":0.9925000071525574,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9909999966621399,"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":0.9147309064865112},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.6722707748413086},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.632187008857727},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5868567824363708},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.49033141136169434},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.48727452754974365},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.48617905378341675},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4632595181465149},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4493742287158966},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.4482630491256714},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4316740334033966},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.42841625213623047},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4124065041542053},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.41008591651916504},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.38914862275123596},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13901492953300476}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9147309064865112},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.6722707748413086},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.632187008857727},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5868567824363708},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.49033141136169434},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.48727452754974365},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.48617905378341675},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4632595181465149},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4493742287158966},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.4482630491256714},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4316740334033966},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.42841625213623047},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4124065041542053},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.41008591651916504},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38914862275123596},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13901492953300476},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2022.3207000","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3207000","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G5258257467","display_name":null,"funder_award_id":"U21A20487","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5711944514","display_name":null,"funder_award_id":"DP-180103424","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W1797268635","https://openalex.org/W1861492603","https://openalex.org/W2405756170","https://openalex.org/W2739540493","https://openalex.org/W2885537606","https://openalex.org/W2939645724","https://openalex.org/W2942797348","https://openalex.org/W2950404765","https://openalex.org/W2961363059","https://openalex.org/W2962845008","https://openalex.org/W2963145877","https://openalex.org/W2963163163","https://openalex.org/W2963233340","https://openalex.org/W2963351004","https://openalex.org/W2963373786","https://openalex.org/W2963413689","https://openalex.org/W2963966654","https://openalex.org/W2966792645","https://openalex.org/W2972328244","https://openalex.org/W2973310602","https://openalex.org/W2984854289","https://openalex.org/W2987809065","https://openalex.org/W2996609772","https://openalex.org/W3005755659","https://openalex.org/W3006538026","https://openalex.org/W3015857268","https://openalex.org/W3016121695","https://openalex.org/W3016241024","https://openalex.org/W3029699545","https://openalex.org/W3034178211","https://openalex.org/W3035316078","https://openalex.org/W3035500781","https://openalex.org/W3035653890","https://openalex.org/W3048372515","https://openalex.org/W3085151711","https://openalex.org/W3092673631","https://openalex.org/W3092775865","https://openalex.org/W3093122931","https://openalex.org/W3095707326","https://openalex.org/W3104956649","https://openalex.org/W3109276915","https://openalex.org/W3119557339","https://openalex.org/W3122887115","https://openalex.org/W3166396011","https://openalex.org/W3167762716","https://openalex.org/W3178406257","https://openalex.org/W4320013936","https://openalex.org/W6639102338","https://openalex.org/W6713645886","https://openalex.org/W6718379498","https://openalex.org/W6747733185","https://openalex.org/W6755102824","https://openalex.org/W6767384525","https://openalex.org/W6773451322","https://openalex.org/W6784364625","https://openalex.org/W6791353385"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703","https://openalex.org/W41015297"],"abstract_inverted_index":{"Text-based":[0],"image":[1,106],"manipulation":[2,40],"is":[3,13,19],"a":[4,14,39,98,113],"popular":[5],"subject":[6],"and":[7,24,29,51,68,92,107,131,149],"has":[8],"many":[9,85],"applications.":[10],"However,":[11],"it":[12],"challenging":[15],"task":[16],"because":[17],"there":[18],"no":[20],"ground-truth":[21],"edited":[22,65,120,124],"dataset":[23],"textual":[25],"descriptions":[26],"have":[27],"abstractive":[28],"ambiguous":[30],"properties.":[31],"To":[32,88],"alleviate":[33],"the":[34,44,63,74,90,93,104,118,123,128,132,151],"difficult":[35],"issues,":[36],"we":[37,55,96,111],"propose":[38],"framework":[41],"consisting":[42],"of":[43,76],"proposal":[45,59],"attentional":[46],"GANs,":[47],"language-related":[48,99,133],"semantic":[49,70,100,134],"mask,":[50],"language-guided":[52,114],"ranker.":[53],"Specially,":[54],"construct":[56],"an":[57],"editing":[58,152],"generator":[60],"to":[61,78,116],"generate":[62],"suitable":[64],"proposals":[66,80,125],"with":[67],"without":[69],"conditions,":[71],"which":[72],"supports":[73],"reorganization":[75],"sub-generators":[77],"output":[79],"in":[81],"various":[82],"aspects":[83],"as":[84,86],"possible.":[87],"distinguish":[89],"text-relevant":[91],"text-irrelevant":[94],"regions,":[95],"introduce":[97],"mask":[101],"based":[102],"on":[103,138],"source":[105],"target":[108],"caption.":[109],"Then,":[110],"exploit":[112],"ranker":[115],"retrieve":[117],"best":[119],"result":[121],"from":[122],"through":[126],"using":[127],"multi-modal":[129],"similarity":[130],"mask.":[135],"Extensive":[136],"experiments":[137],"widely-used":[139],"datasets":[140],"demonstrate":[141],"that":[142],"our":[143],"model":[144],"could":[145],"manipulate":[146],"images":[147],"interactively":[148],"improve":[150],"quality":[153],"effectively.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}