{"id":"https://openalex.org/W4411631903","doi":"https://doi.org/10.1145/3731715.3734580","title":"Visual Content Generation in the Era of Large Foundation Models","display_name":"Visual Content Generation in the Era of Large Foundation Models","publication_year":2025,"publication_date":"2025-06-25","ids":{"openalex":"https://openalex.org/W4411631903","doi":"https://doi.org/10.1145/3731715.3734580"},"language":"en","primary_location":{"id":"doi:10.1145/3731715.3734580","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731715.3734580","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International Conference on Multimedia Retrieval","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/A5010816782","display_name":"Leigang Qu","orcid":"https://orcid.org/0009-0004-6555-3834"},"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":true,"raw_author_name":"Leigang Qu","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0004-6555-3834","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001530752","display_name":"Fei Shen","orcid":"https://orcid.org/0000-0002-8073-9168"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Shen","raw_affiliation_strings":["Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-8073-9168","affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114751938","display_name":"Zhenglin Zhou","orcid":"https://orcid.org/0000-0002-5886-0906"},"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":"Zhenglin Zhou","raw_affiliation_strings":["Zhejiang University, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0002-5886-0906","affiliations":[{"raw_affiliation_string":"Zhejiang University, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080699546","display_name":"Jiayi Lyu","orcid":"https://orcid.org/0000-0001-8517-3346"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayi Lyu","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8517-3346","affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100368524","display_name":"Wenjie Wang","orcid":"https://orcid.org/0000-0002-5199-1428"},"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":"Wenjie Wang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-5199-1428","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090730336","display_name":"Lu Jiang","orcid":"https://orcid.org/0000-0003-0286-8439"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu Jiang","raw_affiliation_strings":["ByteDance, San Jose, USA"],"raw_orcid":"https://orcid.org/0000-0003-0286-8439","affiliations":[{"raw_affiliation_string":"ByteDance, San Jose, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5010816782"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25129162,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2140","last_page":"2142"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9868999719619751,"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":0.9868999719619751,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9776999950408936,"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/T10799","display_name":"Data Visualization and Analytics","score":0.975600004196167,"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/foundation","display_name":"Foundation (evidence)","score":0.765549898147583},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.6543735861778259},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5369666814804077},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09854075312614441},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.08968052268028259},{"id":"https://openalex.org/keywords/law","display_name":"Law","score":0.08156928420066833}],"concepts":[{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.765549898147583},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.6543735861778259},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5369666814804077},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09854075312614441},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.08968052268028259},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.08156928420066833},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3731715.3734580","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731715.3734580","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International Conference on Multimedia Retrieval","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":35,"referenced_works":["https://openalex.org/W3104300620","https://openalex.org/W3109585842","https://openalex.org/W4312697499","https://openalex.org/W4312708649","https://openalex.org/W4312933868","https://openalex.org/W4385275714","https://openalex.org/W4385318467","https://openalex.org/W4386072021","https://openalex.org/W4386075859","https://openalex.org/W4388187930","https://openalex.org/W4390871720","https://openalex.org/W4390872748","https://openalex.org/W4390872769","https://openalex.org/W4390872834","https://openalex.org/W4393154048","https://openalex.org/W4394593186","https://openalex.org/W4396633982","https://openalex.org/W4399695531","https://openalex.org/W4400822286","https://openalex.org/W4402727642","https://openalex.org/W4402733585","https://openalex.org/W4402753785","https://openalex.org/W4402980725","https://openalex.org/W4402982696","https://openalex.org/W4403364748","https://openalex.org/W4403780582","https://openalex.org/W4403792529","https://openalex.org/W4409366412","https://openalex.org/W4409367143","https://openalex.org/W4415286410","https://openalex.org/W6600018615","https://openalex.org/W6600120041","https://openalex.org/W6600424091","https://openalex.org/W6601076540","https://openalex.org/W6826373343"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2381393187","https://openalex.org/W2332779545","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W2358060160","https://openalex.org/W2035483685"],"abstract_inverted_index":{"The":[0,52],"rapid":[1],"advancements":[2],"in":[3,41,97,138],"large":[4,77],"foundation":[5],"models":[6,137],"have":[7],"significantly":[8],"transformed":[9],"the":[10,35,46,90,109,112,132],"field":[11],"of":[12,34,48,92,111,120],"visual":[13,42,122],"content":[14,43,123],"generation,":[15,23,44],"impacting":[16],"domains":[17],"such":[18],"as":[19],"image":[20],"synthesis,":[21],"video":[22],"and":[24,38,62,76,83,95,105,126,141],"3D":[25],"modeling.":[26],"This":[27],"tutorial":[28,53],"will":[29,54,66,87,115],"provide":[30],"an":[31],"in-depth":[32],"exploration":[33],"state-of-the-art":[36],"techniques":[37,125],"methodologies":[39],"used":[40],"emphasizing":[45],"role":[47],"large-scale":[49],"generative":[50,69],"models.":[51],"cover":[55],"fundamental":[56],"principles,":[57],"model":[58],"architectures,":[59],"recent":[60],"breakthroughs,":[61],"practical":[63],"applications.":[64],"We":[65],"discuss":[67],"various":[68],"paradigms,":[70],"including":[71],"diffusion":[72],"models,":[73,75,79],"autoregressive":[74],"multimodal":[78],"highlighting":[80],"their":[81,127,139],"strengths":[82],"limitations.":[84],"Additionally,":[85],"we":[86],"delve":[88],"into":[89],"challenges":[91],"controllability,":[93],"personalization,":[94],"realism":[96],"generated":[98],"content,":[99],"along":[100],"with":[101,131],"open":[102],"research":[103,140],"problems":[104],"future":[106],"directions.":[107],"By":[108],"end":[110],"tutorial,":[113],"attendees":[114],"gain":[116],"a":[117],"comprehensive":[118],"understanding":[119],"contemporary":[121],"generation":[124],"applications,":[128],"equipping":[129],"them":[130],"knowledge":[133],"to":[134],"leverage":[135],"these":[136],"projects.":[142]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
