{"id":"https://openalex.org/W4415537149","doi":"https://doi.org/10.1145/3746027.3754926","title":"EditMaster: Bridging Text instruction and Visual Example for Multimodal guided Image Editing","display_name":"EditMaster: Bridging Text instruction and Visual Example for Multimodal guided Image Editing","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415537149","doi":"https://doi.org/10.1145/3746027.3754926"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754926","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754926","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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":null,"display_name":"Jiahui Zhang","orcid":"https://orcid.org/0009-0000-3219-5779"},"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":"Jiahui Zhang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0000-3219-5779","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101682697","display_name":"Mengtian Li","orcid":"https://orcid.org/0009-0001-7281-2812"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]},{"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":"Mengtian Li","raw_affiliation_strings":["Shanghai University, Shanghai, China and Fudan University, Shang hai, China"],"raw_orcid":"https://orcid.org/0009-0001-7281-2812","affiliations":[{"raw_affiliation_string":"Shanghai University, Shanghai, China and Fudan University, Shang hai, China","institution_ids":["https://openalex.org/I24943067","https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiewei Tang","orcid":"https://orcid.org/0009-0008-8711-4866"},"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":"Jiewei Tang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0008-8711-4866","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110371465","display_name":"Junyu Deng","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":"Junyu Deng","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0004-6313-7378","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Siyu Tian","orcid":"https://orcid.org/0009-0000-4739-3065"},"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":"Siyu Tian","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0000-4739-3065","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiang Liu","orcid":"https://orcid.org/0009-0004-7261-0454"},"institutions":[{"id":"https://openalex.org/I258800397","display_name":"New York University Shanghai","ror":"https://ror.org/02vpsdb40","country_code":"CN","type":"education","lineage":["https://openalex.org/I258800397","https://openalex.org/I57206974"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Liu","raw_affiliation_strings":["New York University Shanghai, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0004-7261-0454","affiliations":[{"raw_affiliation_string":"New York University Shanghai, Shanghai, China","institution_ids":["https://openalex.org/I258800397"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Meng Zhang","orcid":"https://orcid.org/0009-0000-2174-3629"},"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":"Meng Zhang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0000-2174-3629","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003276783","display_name":"Guangnan Ye","orcid":"https://orcid.org/0009-0007-4973-7942"},"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":"Guangnan Ye","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0007-4973-7942","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047962986","display_name":"Yu\u2013Gang Jiang","orcid":"https://orcid.org/0000-0002-1907-8567"},"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":"Yu-Gang Jiang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-1907-8567","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9509","last_page":"9518"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.996999979019165,"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":0.996999979019165,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9485999941825867,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10028","display_name":"Topic Modeling","score":0.9419999718666077,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/bridging","display_name":"Bridging (networking)","score":0.6499000191688538},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.6341999769210815},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.49900001287460327},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.39399999380111694},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.385699987411499},{"id":"https://openalex.org/keywords/visual-language","display_name":"Visual language","score":0.3822999894618988},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.3741999864578247},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3707999885082245}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8414000272750854},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.6499000191688538},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.6341999769210815},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5012999773025513},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.49900001287460327},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.39399999380111694},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38760000467300415},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.385699987411499},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.3822999894618988},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.3741999864578247},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3707999885082245},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.36320000886917114},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.35269999504089355},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3285999894142151},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.3167000114917755},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2851000130176544},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C522192633","wikidata":"https://www.wikidata.org/wiki/Q34228","display_name":"Sign language","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.25690001249313354},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754926","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754926","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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":15,"referenced_works":["https://openalex.org/W3095319910","https://openalex.org/W3173998882","https://openalex.org/W3176641147","https://openalex.org/W3198377975","https://openalex.org/W4312933868","https://openalex.org/W4386057725","https://openalex.org/W4386076215","https://openalex.org/W4386083141","https://openalex.org/W4387596111","https://openalex.org/W4390873054","https://openalex.org/W4390873195","https://openalex.org/W4393148714","https://openalex.org/W4402716004","https://openalex.org/W4402727040","https://openalex.org/W4402753379"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,9,31,156],"image":[3,62],"editing":[4,131],"systems":[5],"reveal":[6],"critical":[7],"limitations":[8],"handling":[10],"complex":[11,157],"real-world":[12],"scenarios":[13],"requiring":[14],"multimodal":[15,57,74,136,158],"condition":[16],"controls.":[17],"While":[18],"text":[19,52,85],"instructions":[20],"enable":[21],"broad":[22],"semantic":[23],"guidance,":[24],"visual":[25,29,54,81,89,96,119],"examples":[26,97],"provide":[27],"precise":[28,61],"reference":[30],"specific":[32],"scenarios,":[33],"existing":[34],"unimodal":[35,130,152],"approaches":[36],"fail":[37],"to":[38,98],"synergize":[39],"these":[40],"complementary":[41],"modalities":[42],"effectively.":[43],"We":[44],"propose":[45],"EditMaster,":[46],"a":[47,134,162],"unified":[48],"framework":[49,68],"that":[50,91,148],"integrates":[51],"and":[53,154],"controls":[55],"through":[56,114],"instruction":[58,159],"learning,":[59],"enabling":[60],"manipulation":[63],"with":[64,79,95],"bidirectional":[65],"consistency.":[66],"Our":[67],"introduces":[69],"three":[70],"core":[71],"innovations:":[72],"A":[73,124],"large":[75],"language":[76],"model":[77,101],"enhanced":[78],"extended":[80],"tokens":[82],"replaces":[83],"CLIP":[84],"encoders,":[86],"generating":[87],"pre-edited":[88],"guidance":[90],"aligns":[92],"textual":[93],"commands":[94],"guide":[99],"diffusion":[100],"toward":[102],"high-quality":[103],"outputs;":[104],"The":[105],"Mask-Based":[106],"Decoupled":[107],"Residual":[108],"Exemplar-Attention":[109],"module":[110],"preserves":[111],"unedited":[112],"regions":[113],"spatial":[115],"masking":[116],"while":[117],"integrating":[118],"details":[120],"via":[121],"residual":[122],"pathways;":[123],"systematic":[125],"data":[126,144],"construction":[127],"method":[128],"converts":[129],"datasets":[132],"into":[133],"task-specific":[135],"dataset,":[137],"eliminating":[138],"the":[139],"need":[140],"for":[141,165],"de":[142],"novo":[143],"construction.":[145],"Experiments":[146],"show":[147],"our":[149],"approach":[150],"outperforms":[151],"baselines":[153],"excels":[155],"editing,":[160],"setting":[161],"new":[163],"benchmark":[164],"this":[166],"field.":[167]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}