{"id":"https://openalex.org/W4388195081","doi":"https://doi.org/10.1145/3607827.3616840","title":"ImEW: A Framework for Editing Image in the Wild","display_name":"ImEW: A Framework for Editing Image in the Wild","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4388195081","doi":"https://doi.org/10.1145/3607827.3616840"},"language":"en","primary_location":{"id":"doi:10.1145/3607827.3616840","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3607827.3616840","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3607827.3616840","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st Workshop on Large Generative Models Meet Multimodal Applications","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3607827.3616840","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056169983","display_name":"Tasnim Mohiuddin","orcid":"https://orcid.org/0009-0003-0955-7200"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tasnim Mohiuddin","raw_affiliation_strings":["Huawei Singapore Research Center, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0003-0955-7200","affiliations":[{"raw_affiliation_string":"Huawei Singapore Research Center, Singapore, Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014128599","display_name":"Tianyi Zhang","orcid":"https://orcid.org/0009-0000-8140-2199"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianyi Zhang","raw_affiliation_strings":["Huawei Singapore Research Center, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0000-8140-2199","affiliations":[{"raw_affiliation_string":"Huawei Singapore Research Center, Singapore, Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015471481","display_name":"Maowen Nie","orcid":"https://orcid.org/0009-0009-5306-0297"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maowen Nie","raw_affiliation_strings":["Huawei Singapore Research Center, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0009-5306-0297","affiliations":[{"raw_affiliation_string":"Huawei Singapore Research Center, Singapore, Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101522204","display_name":"Jing Huang","orcid":"https://orcid.org/0009-0005-5651-9033"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jing Huang","raw_affiliation_strings":["Huawei Singapore Research Center, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0005-5651-9033","affiliations":[{"raw_affiliation_string":"Huawei Singapore Research Center, Singapore, Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085721939","display_name":"Qianqian Chen","orcid":"https://orcid.org/0009-0008-3863-8882"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qianqian Chen","raw_affiliation_strings":["Huawei Singapore Research Center, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0008-3863-8882","affiliations":[{"raw_affiliation_string":"Huawei Singapore Research Center, Singapore, Singapore","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071266799","display_name":"Wei Shi","orcid":"https://orcid.org/0009-0006-2717-4192"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Shi","raw_affiliation_strings":["Huawei Singapore Research Center, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0006-2717-4192","affiliations":[{"raw_affiliation_string":"Huawei Singapore Research Center, Singapore, Singapore","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17184571,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"34","last_page":"44"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9993000030517578,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9993000030517578,"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":0.9700999855995178,"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":0.95660001039505,"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/image-editing","display_name":"Image editing","score":0.8663402795791626},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8148168325424194},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5472856760025024},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5043541193008423},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5006530284881592},{"id":"https://openalex.org/keywords/video-editing","display_name":"Video editing","score":0.48745250701904297},{"id":"https://openalex.org/keywords/image-translation","display_name":"Image translation","score":0.4786892533302307},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45093122124671936},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.44258710741996765},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.42585402727127075},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.42436936497688293},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.41522371768951416},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4033240079879761}],"concepts":[{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.8663402795791626},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8148168325424194},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5472856760025024},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5043541193008423},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5006530284881592},{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.48745250701904297},{"id":"https://openalex.org/C2779757391","wikidata":"https://www.wikidata.org/wiki/Q6002292","display_name":"Image translation","level":3,"score":0.4786892533302307},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45093122124671936},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.44258710741996765},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.42585402727127075},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.42436936497688293},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.41522371768951416},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4033240079879761},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3607827.3616840","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3607827.3616840","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3607827.3616840","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st Workshop on Large Generative Models Meet Multimodal Applications","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3607827.3616840","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3607827.3616840","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3607827.3616840","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st Workshop on Large Generative Models Meet Multimodal Applications","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Zero hunger","id":"https://metadata.un.org/sdg/2","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4388195081.pdf","grobid_xml":"https://content.openalex.org/works/W4388195081.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W1993120651","https://openalex.org/W2070604790","https://openalex.org/W2095297868","https://openalex.org/W2125873654","https://openalex.org/W3177399056","https://openalex.org/W4301488715","https://openalex.org/W4312497550","https://openalex.org/W4385270985","https://openalex.org/W4385801729","https://openalex.org/W4386047807","https://openalex.org/W4386075631","https://openalex.org/W4386076027","https://openalex.org/W6603963165"],"related_works":["https://openalex.org/W4206059703","https://openalex.org/W4389500762","https://openalex.org/W4210895630","https://openalex.org/W4384652403","https://openalex.org/W2990774877","https://openalex.org/W4311389145","https://openalex.org/W4319453795","https://openalex.org/W2017202843","https://openalex.org/W4385527149","https://openalex.org/W4389713802"],"abstract_inverted_index":{"The":[0,129],"ability":[1],"to":[2,41],"edit":[3],"images":[4],"in":[5,16,97,117,163,176],"a":[6,13,27,123],"realistic":[7,137],"and":[8,53,80,92,103,113,138,143,156],"visually":[9,139],"appealing":[10,140],"manner":[11],"is":[12],"fundamental":[14],"requirement":[15],"various":[17],"computer":[18],"vision":[19],"applications.":[20],"In":[21],"this":[22,177],"paper,":[23],"we":[24,109,152],"present":[25],"ImEW,":[26],"unified":[28],"framework":[29,131],"designed":[30],"for":[31,136,160],"solving":[32],"image":[33,58,99,119,141,149,167],"editing":[34,45,120,142,168],"tasks.":[35],"ImEW":[36,116],"utilizes":[37],"off-the-shelf":[38,170],"foundation":[39,70,171],"models":[40,84],"address":[42],"four":[43],"essential":[44],"tasks:":[46],"object":[47,49,51,101],"removal,":[48],"translation,":[50],"replacement,":[52],"generative":[54],"fill":[55],"beyond":[56],"the":[57,66,73,111,154,164],"frame.":[59],"These":[60,83],"tasks":[61,121],"are":[62],"accomplished":[63],"by":[64],"leveraging":[65],"capabilities":[67],"of":[68,115,126,166],"state-of-the-art":[69],"models,":[71,172],"namely":[72],"Segment":[74],"Anything":[75],"Model,":[76],"Grounding":[77],"DINO,":[78],"LaMa,":[79],"Stable":[81],"Diffusion.":[82],"have":[85,93],"undergone":[86],"extensive":[87,107],"training":[88],"on":[89],"large-scale":[90],"datasets":[91],"exhibited":[94],"exceptional":[95],"performance":[96],"understanding":[98],"context,":[100],"manipulation,":[102],"texture":[104],"synthesis.":[105],"Through":[106],"experimentation,":[108],"demonstrate":[110],"effectiveness":[112],"versatility":[114],"accomplishing":[118],"across":[122],"wide":[124],"range":[125],"real-world":[127],"scenarios.":[128],"proposed":[130],"opens":[132],"up":[133],"new":[134],"possibilities":[135],"enables":[144],"diverse":[145],"applications":[146],"requiring":[147],"sophisticated":[148],"modifications.":[150],"Additionally,":[151],"discuss":[153],"limitations":[155],"outline":[157],"potential":[158],"directions":[159],"future":[161],"research":[162],"field":[165],"using":[169],"enabling":[173],"continued":[174],"advancements":[175],"domain.":[178]},"counts_by_year":[],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-10-10T00:00:00"}