{"id":"https://openalex.org/W4403791246","doi":"https://doi.org/10.1145/3664647.3680896","title":"Towards Small Object Editing: A Benchmark Dataset and A Training-Free Approach","display_name":"Towards Small Object Editing: A Benchmark Dataset and A Training-Free Approach","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791246","doi":"https://doi.org/10.1145/3664647.3680896"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680896","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680896","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5101355242","display_name":"Qihe Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qihe Pan","raw_affiliation_strings":["Zhejiang University of Technology, Hangzhou, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University of Technology, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072694516","display_name":"Zhen Zhao","orcid":"https://orcid.org/0000-0002-0796-4078"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zhen Zhao","raw_affiliation_strings":["University of Sydney, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"University of Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100347959","display_name":"Zicheng Wang","orcid":"https://orcid.org/0000-0001-8351-0329"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zicheng Wang","raw_affiliation_strings":["University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102874282","display_name":"Sifan Long","orcid":"https://orcid.org/0000-0001-7060-1133"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sifan Long","raw_affiliation_strings":["Jilin University, Changchun, Jilin, China"],"affiliations":[{"raw_affiliation_string":"Jilin University, Changchun, Jilin, China","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101490743","display_name":"Yiming Wu","orcid":"https://orcid.org/0000-0002-9866-669X"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yiming Wu","raw_affiliation_strings":["University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101397422","display_name":"Wei Ji","orcid":"https://orcid.org/0000-0002-8106-9768"},"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":"Wei Ji","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101954843","display_name":"Haoran Liang","orcid":"https://orcid.org/0000-0002-5906-1380"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoran Liang","raw_affiliation_strings":["Zhejiang University of Technology, Hangzhou, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University of Technology, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001531117","display_name":"Ronghua Liang","orcid":"https://orcid.org/0000-0003-2077-9608"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ronghua Liang","raw_affiliation_strings":["Zhejiang University of Technology, Hangzhou, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University of Technology, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I55712492"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5101355242"],"corresponding_institution_ids":["https://openalex.org/I55712492"],"apc_list":null,"apc_paid":null,"fwci":0.4254,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.58564659,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3257","last_page":"3265"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9925000071525574,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9925000071525574,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11407","display_name":"Innovative Microfluidic and Catalytic Techniques Innovation","score":0.9735999703407288,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9419000148773193,"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/computer-science","display_name":"Computer science","score":0.8040732145309448},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7514686584472656},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6881867051124573},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5678462982177734},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4816790521144867},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4758847951889038},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.06197994947433472},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.06057903170585632}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8040732145309448},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7514686584472656},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6881867051124573},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5678462982177734},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4816790521144867},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4758847951889038},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.06197994947433472},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.06057903170585632},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3680896","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680896","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd 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":23,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2963966654","https://openalex.org/W2966792645","https://openalex.org/W3174525637","https://openalex.org/W3212516020","https://openalex.org/W3216352822","https://openalex.org/W4288083516","https://openalex.org/W4312740349","https://openalex.org/W4312933868","https://openalex.org/W4312977351","https://openalex.org/W4385270985","https://openalex.org/W4385271281","https://openalex.org/W4386057725","https://openalex.org/W4386071604","https://openalex.org/W4386076027","https://openalex.org/W4386076215","https://openalex.org/W4386076532","https://openalex.org/W4390872387","https://openalex.org/W4390873054","https://openalex.org/W4390873211","https://openalex.org/W4390873319","https://openalex.org/W4393148714","https://openalex.org/W4394625750"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W4394050964","https://openalex.org/W2551249631"],"abstract_inverted_index":{"A":[0],"plethora":[1],"of":[2,16,27,138,149,165],"text-guided":[3],"image":[4,183],"editing":[5],"methods":[6],"has":[7,40],"recently":[8],"been":[9,41],"developed":[10],"by":[11],"leveraging":[12],"the":[13,25,75,90,136,145,163],"impressive":[14],"capabilities":[15],"large-scale":[17],"diffusion-based":[18],"generative":[19],"models":[20,29],"especially":[21],"Stable":[22],"Diffusion.":[23],"Despite":[24],"success":[26],"diffusion":[28],"in":[30,46,83,92,144,178],"producing":[31],"high-quality":[32],"images,":[33],"their":[34],"application":[35],"to":[36,44,78,154,162],"small":[37,81,125,150],"object":[38,126,151],"generation":[39,100,127,152,184],"limited":[42],"due":[43],"difficulties":[45],"aligning":[47],"cross-modal":[48],"attention":[49,72],"maps":[50],"between":[51],"text":[52],"and":[53,70,102,131,147,167],"these":[54],"objects.":[55],"Our":[56],"approach":[57],"offers":[58],"a":[59,118],"training-free":[60],"method":[61],"that":[62,110],"significantly":[63],"mitigates":[64],"this":[65],"alignment":[66],"issue":[67],"with":[68,85],"local":[69],"global":[71],"guidance,":[73],"enhancing":[74],"model's":[76],"ability":[77],"accurately":[79],"render":[80],"objects":[82],"accordance":[84],"textual":[86],"descriptions.":[87],"We":[88],"detail":[89],"methodology":[91],"our":[93,139,189,192],"approach,":[94],"emphasizing":[95],"its":[96,104],"divergence":[97],"from":[98,129],"traditional":[99],"techniques":[101],"highlighting":[103],"advantages.":[105],"What's":[106],"more":[107],"important":[108],"is":[109,185],"we":[111],"also":[112,171],"provide":[113],"SOEBench":[114],"(Small":[115],"Object":[116],"Editing),":[117],"standardized":[119],"benchmark":[120],"for":[121,176],"quantitatively":[122],"evaluating":[123],"text-based":[124],"collected":[128],"MSCOCO[22]":[130],"OpenImage[18].":[132],"Preliminary":[133],"results":[134],"demonstrate":[135],"effectiveness":[137],"method,":[140],"showing":[141],"marked":[142],"improvements":[143],"fidelity":[146],"accuracy":[148],"compared":[153],"existing":[155],"models.":[156],"This":[157],"advancement":[158],"not":[159],"only":[160],"contributes":[161],"field":[164],"AI":[166],"computer":[168],"vision":[169],"but":[170],"opens":[172],"up":[173],"new":[174],"possibilities":[175],"applications":[177],"various":[179],"industries":[180],"where":[181],"precise":[182],"critical.We":[186],"will":[187],"release":[188],"dataset":[190],"on":[191],"project":[193],"page:":[194],"https://soebench.github.io/":[195]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}