{"id":"https://openalex.org/W4408355747","doi":"https://doi.org/10.1109/icassp49660.2025.10890562","title":"Enhancing Image Editing with Chain-of-Thought Reasoning and Multimodal Large Language Models","display_name":"Enhancing Image Editing with Chain-of-Thought Reasoning and Multimodal Large Language Models","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355747","doi":"https://doi.org/10.1109/icassp49660.2025.10890562"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890562","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890562","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5102678209","display_name":"Mengxue Kang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210092862","display_name":"Arctic Monitoring And Assessment Programme","ror":"https://ror.org/00hgq1a05","country_code":"NO","type":"other","lineage":["https://openalex.org/I4210092862"]}],"countries":["NO"],"is_corresponding":true,"raw_author_name":"Mengxue Kang","raw_affiliation_strings":["AMAP"],"affiliations":[{"raw_affiliation_string":"AMAP","institution_ids":["https://openalex.org/I4210092862"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100390704","display_name":"Xinyu Zhang","orcid":"https://orcid.org/0000-0002-6829-4522"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinyu Zhang","raw_affiliation_strings":["Meituan Inc"],"affiliations":[{"raw_affiliation_string":"Meituan Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087764024","display_name":"Fei Wei","orcid":"https://orcid.org/0000-0002-8675-7973"},"institutions":[{"id":"https://openalex.org/I4210092862","display_name":"Arctic Monitoring And Assessment Programme","ror":"https://ror.org/00hgq1a05","country_code":"NO","type":"other","lineage":["https://openalex.org/I4210092862"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Fei Wei","raw_affiliation_strings":["AMAP"],"affiliations":[{"raw_affiliation_string":"AMAP","institution_ids":["https://openalex.org/I4210092862"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075666789","display_name":"Shuang Xu","orcid":"https://orcid.org/0000-0001-8071-2830"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuang Xu","raw_affiliation_strings":["Meituan Inc"],"affiliations":[{"raw_affiliation_string":"Meituan Inc","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001504472","display_name":"Yuhe Liu","orcid":"https://orcid.org/0000-0002-7470-1905"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yuhe Liu","raw_affiliation_strings":["National University of Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102678209"],"corresponding_institution_ids":["https://openalex.org/I4210092862"],"apc_list":null,"apc_paid":null,"fwci":1.3104,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.77935289,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9587000012397766,"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":0.9587000012397766,"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":0.743369460105896},{"id":"https://openalex.org/keywords/chain","display_name":"Chain (unit)","score":0.46070897579193115},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4261905252933502},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3766222298145294},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3604620099067688},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.34606289863586426}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.743369460105896},{"id":"https://openalex.org/C199185054","wikidata":"https://www.wikidata.org/wiki/Q552299","display_name":"Chain (unit)","level":2,"score":0.46070897579193115},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4261905252933502},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3766222298145294},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3604620099067688},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.34606289863586426},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890562","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890562","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W4312933868","https://openalex.org/W4378439092","https://openalex.org/W4386072096","https://openalex.org/W4386076215","https://openalex.org/W4390874575","https://openalex.org/W4402727536","https://openalex.org/W4402727574","https://openalex.org/W4402754134","https://openalex.org/W6809885388","https://openalex.org/W6841366371","https://openalex.org/W6848774630","https://openalex.org/W6853182488","https://openalex.org/W6854484269","https://openalex.org/W6856851587","https://openalex.org/W6857083971","https://openalex.org/W6857351366","https://openalex.org/W6859151486","https://openalex.org/W6860041859","https://openalex.org/W6860430936","https://openalex.org/W6861022559","https://openalex.org/W6862974260","https://openalex.org/W6864731054","https://openalex.org/W6865186587"],"related_works":["https://openalex.org/W2742360428","https://openalex.org/W2060570504","https://openalex.org/W4320830217","https://openalex.org/W4231937131","https://openalex.org/W3188962172","https://openalex.org/W323219885","https://openalex.org/W2063928587","https://openalex.org/W2772917594","https://openalex.org/W1487966966","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Image":[0],"editing":[1,25,38,63],"in":[2,23,83,148],"our":[3,104,128,142,156],"daily":[4],"lives":[5],"often":[6],"requires":[7],"models":[8,39,82,121,147],"to":[9,42,79,106],"first":[10],"understand":[11],"user\u2019s":[12],"intention":[13],"and":[14,28,70,99,111,125,153,166],"then":[15],"proceed":[16],"with":[17,51,122,132],"the":[18,108,112,115],"editing.":[19],"Despite":[20],"significant":[21],"advancements":[22],"image":[24,37,62,149],"technology,":[26],"understanding":[27,135,163],"executing":[29],"complex":[30,44,164],"instructions":[31],"remains":[32],"a":[33,91,133],"substantial":[34],"challenge.":[35],"Existing":[36],"either":[40],"fail":[41],"comprehend":[43],"intentions":[45],"or":[46],"make":[47],"errors":[48],"when":[49],"dealing":[50],"multiple":[52],"objects.":[53],"To":[54],"address":[55],"these":[56],"challenges,":[57],"we":[58],"present":[59],"an":[60,159],"innovative":[61],"framework":[64],"that":[65,141],"employs":[66],"Chain-of-Thought":[67],"(CoT)":[68],"reasoning":[69],"localizing":[71],"capabilities":[72],"of":[73,114,136,162],"multimodal":[74],"Large":[75],"Language":[76],"Models":[77],"(LLMs)":[78],"assist":[80],"diffusion":[81,120],"generating":[84,167],"more":[85],"refined":[86],"images.":[87,169],"We":[88,102],"meticulously":[89],"design":[90],"CoT":[92,109],"process":[93,110],"comprising":[94],"instruction":[95],"decomposition,":[96],"region":[97],"localization,":[98],"detailed":[100],"description.":[101],"train":[103],"model":[105,129,143,157],"learn":[107],"mask":[113],"edited":[116],"image.":[117],"By":[118],"providing":[119],"generated":[123,126],"prompts":[124,165],"masks,":[127],"edits":[130],"images":[131],"superior":[134],"instructions.":[137],"Extensive":[138],"experiments":[139],"demonstrate":[140],"outperforms":[144],"existing":[145],"state-of-the-art":[146],"generation":[150],"both":[151],"qualitatively":[152],"quantitatively.":[154],"Notably,":[155],"exhibits":[158],"enhanced":[160],"ability":[161],"corresponding":[168]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}
