{"id":"https://openalex.org/W4404059342","doi":"https://doi.org/10.1145/3702999","title":"SAMControl: Controlling Pose and Object for Image Editing with Soft Attention Mask","display_name":"SAMControl: Controlling Pose and Object for Image Editing with Soft Attention Mask","publication_year":2024,"publication_date":"2024-11-05","ids":{"openalex":"https://openalex.org/W4404059342","doi":"https://doi.org/10.1145/3702999"},"language":"en","primary_location":{"id":"doi:10.1145/3702999","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3702999","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3702999","source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3702999","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090414072","display_name":"Yue Zhang","orcid":"https://orcid.org/0000-0002-0431-6390"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yue Zhang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China","Zhejiang University, China"],"raw_orcid":"https://orcid.org/0000-0002-0431-6390","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115605144","display_name":"Chao Wang","orcid":"https://orcid.org/0000-0003-1297-768X"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Chao Wang","raw_affiliation_strings":["University of Technology Sydney, Sydney, Australia","University of Technology Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0003-1297-768X","affiliations":[{"raw_affiliation_string":"University of Technology Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]},{"raw_affiliation_string":"University of Technology Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Fei Fang","orcid":"https://orcid.org/0009-0006-9053-8972"},"institutions":[{"id":"https://openalex.org/I44468530","display_name":"Qingdao University of Technology","ror":"https://ror.org/01qzc0f54","country_code":"CN","type":"education","lineage":["https://openalex.org/I44468530"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Fang","raw_affiliation_strings":["Qingdao University of Technology, Qingdao, China","Qingdao University of Technology, China"],"raw_orcid":"https://orcid.org/0009-0006-9053-8972","affiliations":[{"raw_affiliation_string":"Qingdao University of Technology, Qingdao, China","institution_ids":["https://openalex.org/I44468530"]},{"raw_affiliation_string":"Qingdao University of Technology, China","institution_ids":["https://openalex.org/I44468530"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048521072","display_name":"Yunzhi Zhuge","orcid":"https://orcid.org/0000-0002-4288-4516"},"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":"Yunzhi Zhuge","raw_affiliation_strings":["Dalian University of Technology, Dalian, China","Dalian University of Technology, China"],"raw_orcid":"https://orcid.org/0000-0002-4288-4516","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"Dalian University of Technology, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002207978","display_name":"Hehe Fan","orcid":"https://orcid.org/0000-0001-9572-2345"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hehe Fan","raw_affiliation_strings":["Zhejiang University, Hangzhou, China","Zhejiang University, China"],"raw_orcid":"https://orcid.org/0000-0001-9572-2345","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034967388","display_name":"Xiaojun Chang","orcid":"https://orcid.org/0000-0002-7778-8807"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojun Chang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China","University of Science and Technology of China, China"],"raw_orcid":"https://orcid.org/0000-0002-7778-8807","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015874725","display_name":"Cheng Deng","orcid":"https://orcid.org/0000-0003-2620-3247"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Deng","raw_affiliation_strings":["Xidian University, X\u2019ian, China","Xidian University, China"],"raw_orcid":"https://orcid.org/0000-0003-2620-3247","affiliations":[{"raw_affiliation_string":"Xidian University, X\u2019ian, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"Xidian University, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005421447","display_name":"Yi Yang","orcid":"https://orcid.org/0000-0002-0512-880X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Yang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China","Zhejiang University, China"],"raw_orcid":"https://orcid.org/0000-0002-0512-880X","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5090414072"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":1.1054,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.87584066,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"21","issue":"11","first_page":"1","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9943000078201294,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9943000078201294,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.991599977016449,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.9890999794006348,"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":0.8983753323554993},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6709980964660645},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.636675238609314},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5875916481018066},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5790575742721558},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5546249747276306},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.45661869645118713},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.44686809182167053}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8983753323554993},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6709980964660645},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.636675238609314},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5875916481018066},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5790575742721558},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5546249747276306},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.45661869645118713},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.44686809182167053}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3702999","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3702999","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3702999","source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3702999","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3702999","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3702999","source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2655623952","display_name":null,"funder_award_id":"226-2024-00058","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G3765385956","display_name":null,"funder_award_id":"62472381","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5586867142","display_name":null,"funder_award_id":"U2336212","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/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4404059342.pdf"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W2133665775","https://openalex.org/W2962770929","https://openalex.org/W2962785568","https://openalex.org/W2963966654","https://openalex.org/W3035574324","https://openalex.org/W3039828778","https://openalex.org/W3166541011","https://openalex.org/W3173531806","https://openalex.org/W3176368002","https://openalex.org/W4200150166","https://openalex.org/W4214926101","https://openalex.org/W4312053697","https://openalex.org/W4312740349","https://openalex.org/W4312933868","https://openalex.org/W4312938727","https://openalex.org/W4361271773","https://openalex.org/W4378473834","https://openalex.org/W4385527149","https://openalex.org/W4385810246","https://openalex.org/W4386057725","https://openalex.org/W4386075993","https://openalex.org/W4386076215","https://openalex.org/W4386076273","https://openalex.org/W4386076532","https://openalex.org/W4386113271","https://openalex.org/W4390872351","https://openalex.org/W4390873319","https://openalex.org/W4393148714","https://openalex.org/W4402715857","https://openalex.org/W4402753539","https://openalex.org/W4402753991","https://openalex.org/W6788812206","https://openalex.org/W6846948161"],"related_works":["https://openalex.org/W4319453795","https://openalex.org/W4205104112","https://openalex.org/W1974870326","https://openalex.org/W2770776392","https://openalex.org/W3176454756","https://openalex.org/W2772330423","https://openalex.org/W3163523050","https://openalex.org/W3006381446","https://openalex.org/W4386301887","https://openalex.org/W3015353979"],"abstract_inverted_index":{"To":[0],"achieve":[1],"content-consistent":[2],"results":[3,133],"in":[4,61,110],"text-conditioned":[5],"image":[6,19,32,43,94],"editing,":[7],"existing":[8],"methods":[9],"typically":[10],"employ":[11],"a":[12,25,78,116],"reconstruction":[13,112],"branch":[14,27],"to":[15,28,67,85,120],"capture":[16],"the":[17,30,35,40,53,59,62,88,111,122,135,138],"source":[18,42,48,71,125],"details":[20,49,92,126],"via":[21],"diffusion":[22,107],"inversion":[23,63,118],"and":[24,39,90,131],"generation":[26],"synthesize":[29],"target":[31],"based":[33],"on":[34],"given":[36],"textual":[37],"prompt":[38],"masked":[41],"details.":[44,72],"However,":[45],"accurately":[46],"segmenting":[47],"is":[50],"challenging":[51],"with":[52],"current":[54],"fixed-threshold":[55],"mask":[56],"strategy.":[57],"Additionally,":[58],"inadequacies":[60],"process":[64],"can":[65],"lead":[66],"insufficient":[68],"retention":[69],"of":[70,124,137],"In":[73],"this":[74],"article,":[75],"we":[76,114],"propose":[77],"method":[79],"called":[80],"SAMControl":[81,96],"(Soft":[82],"Attention":[83],"Mask)":[84],"adaptively":[86],"control":[87],"pose":[89],"object":[91],"for":[93,102],"editing.":[95],"dynamically":[97],"learns":[98],"flexible":[99],"attention":[100],"masks":[101],"different":[103],"images":[104],"at":[105],"various":[106],"steps.":[108],"Furthermore,":[109],"branch,":[113],"utilize":[115],"direct":[117],"technique":[119],"ensure":[121],"fidelity":[123],"within":[127],"SAM.":[128],"Extensive":[129],"qualitative":[130],"quantitative":[132],"demonstrate":[134],"effectiveness":[136],"proposed":[139],"method.":[140]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-23T08:51:43.019350","created_date":"2025-10-10T00:00:00"}
