{"id":"https://openalex.org/W4403792529","doi":"https://doi.org/10.1145/3664647","title":"Proceedings of the 32nd ACM International Conference on Multimedia","display_name":"Proceedings of the 32nd ACM International Conference on Multimedia","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403792529","doi":"https://doi.org/10.1145/3664647"},"language":"en","primary_location":{"id":"doi:10.1145/3664647","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"proceedings"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2411.01545","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101355242","display_name":"Qihe Pan","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Pan, Qihe","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072694516","display_name":"Zhen Zhao","orcid":"https://orcid.org/0000-0002-0796-4078"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Zhen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100347960","display_name":"Zicheng Wang","orcid":"https://orcid.org/0000-0002-1291-2168"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zicheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113210471","display_name":"Sifan Long","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Long, Sifan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109714717","display_name":"Yiming Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Yiming","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075066245","display_name":"Wei Ji","orcid":"https://orcid.org/0000-0002-9642-6983"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ji, Wei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101954843","display_name":"Haoran Liang","orcid":"https://orcid.org/0000-0002-5906-1380"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang, Haoran","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5001531117","display_name":"Ronghua Liang","orcid":"https://orcid.org/0000-0003-2077-9608"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang, Ronghua","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5101355242"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":287,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":true,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.6297000050544739,"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/T11439","display_name":"Video Analysis and Summarization","score":0.6297000050544739,"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/T12720","display_name":"Multimedia Communication and Technology","score":0.6121000051498413,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.6057000160217285,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.6957473754882812},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.6233063340187073},{"id":"https://openalex.org/keywords/library-science","display_name":"Library science","score":0.42269569635391235},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.32322800159454346}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6957473754882812},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.6233063340187073},{"id":"https://openalex.org/C161191863","wikidata":"https://www.wikidata.org/wiki/Q199655","display_name":"Library science","level":1,"score":0.42269569635391235},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.32322800159454346}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3664647","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"proceedings"},{"id":"pmh:oai:arXiv.org:2411.01545","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.01545","pdf_url":"https://arxiv.org/pdf/2411.01545","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2411.01545","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.01545","pdf_url":"https://arxiv.org/pdf/2411.01545","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2959300817","https://openalex.org/W2963966654","https://openalex.org/W2966792645","https://openalex.org/W3036167779","https://openalex.org/W3105013723","https://openalex.org/W3110257065","https://openalex.org/W3121370741","https://openalex.org/W3121480429","https://openalex.org/W3153469116","https://openalex.org/W3166396011","https://openalex.org/W3174525637","https://openalex.org/W3212516020","https://openalex.org/W3216352822","https://openalex.org/W4226125322","https://openalex.org/W4226182655","https://openalex.org/W4289785045","https://openalex.org/W4307076412","https://openalex.org/W4312740349","https://openalex.org/W4312933868","https://openalex.org/W4312977351","https://openalex.org/W4320013936","https://openalex.org/W4320831569","https://openalex.org/W4321277285","https://openalex.org/W4363671612","https://openalex.org/W4375958874","https://openalex.org/W4383472654","https://openalex.org/W4385004666","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/W4387389729","https://openalex.org/W4390873211","https://openalex.org/W4391602018","https://openalex.org/W4392271277","https://openalex.org/W4402733577"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"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":[13,25,76,91,136,145,163],"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":[30,46,84,93,144,178],"producing":[31],"high-quality":[32],"images,":[33],"their":[34],"application":[35],"to":[36,44,79,154,162],"small":[37,82,125,150],"object":[38,126,151],"generation":[39,101,127,152,184],"limited":[42],"due":[43],"difficulties":[45],"aligning":[47],"cross-modal":[48],"attention":[49,72],"maps":[50],"between":[51],"text":[52],"and":[53,70,103,131,147,167],"these":[54],"objects.":[55],"Our":[56],"approach":[57],"offers":[58],"a":[59,118],"training-free":[60],"method":[61],"that":[62,111],"significantly":[63],"mitigates":[64],"this":[65],"alignment":[66],"issue":[67],"with":[68,86],"local":[69],"global":[71],"guidance":[73],",":[74],"enhancing":[75],"model's":[77],"ability":[78],"accurately":[80],"render":[81],"objects":[83],"accordance":[85],"textual":[87],"descriptions.":[88],"We":[89,187],"detail":[90],"methodology":[92],"our":[94,139,190,193],"approach,":[95],"emphasizing":[96],"its":[97,105],"divergence":[98],"from":[99,129],"traditional":[100],"techniques":[102],"highlighting":[104],"advantages.":[106],"What's":[107],"more":[108],"important":[109],"is":[110,185],"we":[112],"also":[113,171],"provide~\\textit{SOEBench}":[114],"(Small":[115],"Object":[116],"Editing),":[117],"standardized":[119],"benchmark":[120],"for":[121,176],"quantitatively":[122],"evaluating":[123],"text-based":[124],"collected":[128],"\\textit{MSCOCO}":[130],"\\textit{OpenImage}.":[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.":[186],"will":[188],"release":[189],"dataset":[191],"on":[192],"project":[194],"page:":[195],"\\href{https://soebench.github.io/}{https://soebench.github.io/}.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":254},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":6},{"year":2017,"cited_by_count":8}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2024-10-27T00:00:00"}
