{"id":"https://openalex.org/W4395030939","doi":"https://doi.org/10.1145/3638884.3638906","title":"Referring Image Harmonization","display_name":"Referring Image Harmonization","publication_year":2023,"publication_date":"2023-12-14","ids":{"openalex":"https://openalex.org/W4395030939","doi":"https://doi.org/10.1145/3638884.3638906"},"language":"en","primary_location":{"id":"doi:10.1145/3638884.3638906","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3638884.3638906","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 9th International Conference on Communication and Information Processing","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/A5101995916","display_name":"Zhenghui Wang","orcid":"https://orcid.org/0009-0002-6871-204X"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenghui Wang","raw_affiliation_strings":["Beijing University of Posts & Telecommunications, China"],"raw_orcid":"https://orcid.org/0009-0002-6871-204X","affiliations":[{"raw_affiliation_string":"Beijing University of Posts & Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027927925","display_name":"Xiaoxuan Fan","orcid":"https://orcid.org/0000-0002-4153-0695"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoxuan Fan","raw_affiliation_strings":["State Grid Smart Grid Research Institute Co., Ltd, China"],"raw_orcid":"https://orcid.org/0000-0002-4153-0695","affiliations":[{"raw_affiliation_string":"State Grid Smart Grid Research Institute Co., Ltd, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062609147","display_name":"Zhuangzhuang Li","orcid":"https://orcid.org/0009-0005-6987-3648"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuangzhuang Li","raw_affiliation_strings":["State Grid Shandong Electric Power Research Institute, China"],"raw_orcid":"https://orcid.org/0009-0005-6987-3648","affiliations":[{"raw_affiliation_string":"State Grid Shandong Electric Power Research Institute, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013283012","display_name":"Fangxiang Feng","orcid":"https://orcid.org/0000-0002-4798-4233"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangxiang Feng","raw_affiliation_strings":["Beijing University of Posts & Telecommunications, China"],"raw_orcid":"https://orcid.org/0000-0002-4798-4233","affiliations":[{"raw_affiliation_string":"Beijing University of Posts & Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100351304","display_name":"Xiaojie Wang","orcid":"https://orcid.org/0000-0003-0314-8951"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojie Wang","raw_affiliation_strings":["Beijing University of Posts & Telecommunications, China"],"raw_orcid":"https://orcid.org/0000-0003-0314-8951","affiliations":[{"raw_affiliation_string":"Beijing University of Posts & Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"147","last_page":"152"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9972000122070312,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9972000122070312,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9970999956130981,"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":0.9936000108718872,"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/harmonization","display_name":"Harmonization","score":0.8852081894874573},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7476141452789307},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6392178535461426},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6296452283859253},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5859283208847046},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5370783805847168},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5369925498962402},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.47083401679992676},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4484642446041107},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4473438262939453},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.05228865146636963}],"concepts":[{"id":"https://openalex.org/C2779962950","wikidata":"https://www.wikidata.org/wiki/Q5659376","display_name":"Harmonization","level":2,"score":0.8852081894874573},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7476141452789307},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6392178535461426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6296452283859253},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5859283208847046},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5370783805847168},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5369925498962402},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.47083401679992676},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4484642446041107},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4473438262939453},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.05228865146636963},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3638884.3638906","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3638884.3638906","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 9th International Conference on Communication and Information Processing","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":26,"referenced_works":["https://openalex.org/W2070604790","https://openalex.org/W2129112648","https://openalex.org/W2164847484","https://openalex.org/W2190424233","https://openalex.org/W2251512949","https://openalex.org/W2798556392","https://openalex.org/W2962737447","https://openalex.org/W2963109634","https://openalex.org/W2980088508","https://openalex.org/W3034684802","https://openalex.org/W3120025849","https://openalex.org/W3135367836","https://openalex.org/W3169823210","https://openalex.org/W3171358896","https://openalex.org/W3171714858","https://openalex.org/W3187664142","https://openalex.org/W3201770677","https://openalex.org/W3216551675","https://openalex.org/W4214738329","https://openalex.org/W4214919319","https://openalex.org/W4225322336","https://openalex.org/W4295903508","https://openalex.org/W4301409532","https://openalex.org/W4304098227","https://openalex.org/W4312420092","https://openalex.org/W4360594859"],"related_works":["https://openalex.org/W2006073222","https://openalex.org/W2488916264","https://openalex.org/W2323573032","https://openalex.org/W198625436","https://openalex.org/W1908077024","https://openalex.org/W2095388346","https://openalex.org/W2379751185","https://openalex.org/W2379404183","https://openalex.org/W2004509987","https://openalex.org/W3145231964"],"abstract_inverted_index":{"Image":[0],"harmonization":[1,28,98,111,160],"is":[2,55],"the":[3,7,22,39,87,95,105,129,139,156],"process":[4],"of":[5,9],"modifying":[6],"foreground":[8,40,48,74,106,130,140],"a":[10,17,30,63,109,122],"composite":[11],"image":[12,27,69,83,159],"in":[13,43],"order":[14],"to":[15,36,81],"achieve":[16,149],"cohesive":[18],"visual":[19,32],"consistency":[20],"with":[21,101,117],"background.":[23],"Existing":[24],"works":[25],"viewed":[26],"as":[29],"purely":[31],"task,":[33,66,92,119],"using":[34],"masks":[35],"distinguish":[37],"between":[38,47,73],"and":[41,49,75,136],"background":[42,50,76],"images.":[44],"However,":[45],"distinguishing":[46],"based":[51,77,132],"on":[52,78,133,152],"human":[53],"intention":[54],"more":[56],"intuitive.":[57],"In":[58],"this":[59,91,118],"paper,":[60],"we":[61,93,120],"developed":[62],"new":[64,110],"multimodal":[65],"named":[67],"referring":[68,102,134,158],"harmonization,":[70],"which":[71,126],"distinguishes":[72],"text":[79],"prompts":[80],"perform":[82],"harmonization.":[84],"To":[85,115],"collect":[86],"necessary":[88],"data":[89],"for":[90,104,155],"supplement":[94],"widely":[96],"used":[97],"dataset":[99,112,154],"iHarmony4":[100],"expressions":[103],"region,":[107],"creating":[108],"called":[113],"ReiHarmony4.":[114],"cope":[116],"propose":[121],"segmentation-harmonization":[123],"pipeline":[124],"method,":[125],"first":[127],"segments":[128],"region":[131],"expressions,":[135],"then":[137],"harmonizes":[138],"region.":[141],"Extensive":[142],"experiments":[143],"demonstrate":[144],"that":[145],"our":[146],"baseline":[147],"method":[148],"promising":[150],"results":[151],"ReiHarmony4":[153],"proposed":[157],"task.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}