{"id":"https://openalex.org/W7125820988","doi":"https://doi.org/10.1109/tcsvt.2026.3657945","title":"SoEdit: Improving Instruction-Driven Object Editing by Focusing on a Single Object Within a Cropped Region","display_name":"SoEdit: Improving Instruction-Driven Object Editing by Focusing on a Single Object Within a Cropped Region","publication_year":2026,"publication_date":"2026-01-27","ids":{"openalex":"https://openalex.org/W7125820988","doi":"https://doi.org/10.1109/tcsvt.2026.3657945"},"language":null,"primary_location":{"id":"doi:10.1109/tcsvt.2026.3657945","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3657945","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","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/A5123930559","display_name":"Wuyang Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wuyang Luo","raw_affiliation_strings":["School of Future Technology, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0002-1447-3445","affiliations":[{"raw_affiliation_string":"School of Future Technology, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124017003","display_name":"Su Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Su Yang","raw_affiliation_strings":["Shanghai Key Laboratory of Intelligent Information Processing, College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-6706-6640","affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Intelligent Information Processing, College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123961163","display_name":"Hao Niu","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Niu","raw_affiliation_strings":["School of Computer Science, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-3818-5816","affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09093541,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"6","first_page":"8461","last_page":"8474"},"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":0.33980000019073486,"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":0.33980000019073486,"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":0.056299999356269836,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.039799999445676804,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.9003000259399414},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.7425000071525574},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7160000205039978},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5685999989509583},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5407000184059143},{"id":"https://openalex.org/keywords/video-editing","display_name":"Video editing","score":0.48829999566078186},{"id":"https://openalex.org/keywords/post-production","display_name":"Post-production","score":0.46140000224113464},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4507000148296356}],"concepts":[{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.9003000259399414},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8574000000953674},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.7425000071525574},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7160000205039978},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5943999886512756},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5831999778747559},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5685999989509583},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5407000184059143},{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.48829999566078186},{"id":"https://openalex.org/C87829876","wikidata":"https://www.wikidata.org/wiki/Q648877","display_name":"Post-production","level":2,"score":0.46140000224113464},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4507000148296356},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.447299987077713},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.37049999833106995},{"id":"https://openalex.org/C3019973339","wikidata":"https://www.wikidata.org/wiki/Q899523","display_name":"Object based","level":3,"score":0.35280001163482666},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3497999906539917},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.29589998722076416},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2946999967098236},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.28349998593330383},{"id":"https://openalex.org/C512554520","wikidata":"https://www.wikidata.org/wiki/Q815844","display_name":"Method","level":3,"score":0.2750999927520752},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2694000005722046},{"id":"https://openalex.org/C146044194","wikidata":"https://www.wikidata.org/wiki/Q5157334","display_name":"Computational photography","level":4,"score":0.2549000084400177}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2026.3657945","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3657945","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8170563578605652,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G3039549732","display_name":null,"funder_award_id":"IIPL-2025-RD4-01","funder_id":"https://openalex.org/F4320332588","funder_display_name":"Shanghai Key Laboratory of Intelligent Information Processing"},{"id":"https://openalex.org/G4187886802","display_name":null,"funder_award_id":"DUT25YG207","funder_id":"https://openalex.org/F4320321630","funder_display_name":"Dalian University of Technology"},{"id":"https://openalex.org/G7796410472","display_name":null,"funder_award_id":"DUT25YG207","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G910885334","display_name":null,"funder_award_id":"62506061","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321630","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876"},{"id":"https://openalex.org/F4320332588","display_name":"Shanghai Key Laboratory of Intelligent Information Processing","ror":"https://ror.org/013q1eq08"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recently,":[0],"instruction-driven":[1],"image":[2,16,44],"editing":[3,28,77,81,142,174],"methods":[4],"have":[5],"demonstrated":[6],"promising":[7],"capabilities,":[8],"requiring":[9],"only":[10],"a":[11,67,86,119,151],"brief":[12],"text":[13],"to":[14,33,50,53,128,155,172],"guide":[15],"modifications.":[17],"However,":[18],"most":[19],"of":[20,42,125],"them":[21],"often":[22],"yield":[23],"suboptimal":[24],"results":[25],"for":[26],"object":[27,69,92,107,181],"in":[29,56,169],"complex":[30,76],"scenes,":[31],"due":[32],"two":[34],"major":[35],"defects:":[36],"(1)":[37],"Over-editing,":[38],"where":[39],"unintended":[40],"regions":[41,84],"the":[43,140,158],"are":[45],"inadvertently":[46],"altered;":[47],"(2)":[48],"Inability":[49],"precisely":[51],"adhere":[52],"instructions,":[54],"particularly":[55],"scenes":[57],"with":[58,144],"numerous":[59],"elements.":[60],"To":[61],"resolve":[62],"these":[63],"issues,":[64],"we":[65,117,149],"propose":[66],"Single":[68],"Editing":[70],"scheme,":[71],"termed":[72],"SoEdit,":[73],"which":[74],"distills":[75],"tasks":[78],"into":[79],"single-object":[80],"within":[82],"cropped":[83],"through":[85],"pipeline":[87],"that":[88,163],"integrates":[89],"task":[90],"parsing,":[91],"localization,":[93],"editing,":[94],"and":[95,109,111,137,179],"context":[96],"blending.":[97],"This":[98],"approach":[99],"minimizes":[100],"interference":[101],"from":[102],"irrelevant":[103],"areas,":[104],"ensures":[105],"proper":[106],"size":[108],"placement,":[110],"ultimately":[112],"enhances":[113],"model":[114,130],"performance.":[115],"Furthermore,":[116],"introduce":[118,150],"lightweight":[120],"<italic":[121],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[122],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Spatially-Adaptive":[123],"Mixture":[124],"Experts":[126],"(SAMOE)</i>":[127],"better":[129],"spatial":[131],"heterogeneity,":[132],"enabling":[133],"tokenwise":[134],"adaptive":[135],"processing":[136],"further":[138,156],"enhancing":[139],"overall":[141],"capability":[143],"minimal":[145],"additional":[146],"parameters.":[147],"Moreover,":[148],"large-scale":[152],"object-centric":[153],"dataset":[154],"optimize":[157],"model.":[159],"Extensive":[160],"experiments":[161],"demonstrate":[162],"SoEdit":[164],"outperforms":[165],"existing":[166],"methods,":[167],"especially":[168],"precise":[170],"responses":[171],"fine-grained":[173],"requirements,":[175],"such":[176],"as":[177],"multi-action":[178],"quantity-sensitive":[180],"editing.":[182]},"counts_by_year":[],"updated_date":"2026-06-06T06:22:57.294733","created_date":"2026-01-28T00:00:00"}
