{"id":"https://openalex.org/W4417073386","doi":"https://doi.org/10.1145/3743093.3770999","title":"Unifying Generative Self-Supervised Paradigms with Diffusion Models","display_name":"Unifying Generative Self-Supervised Paradigms with Diffusion Models","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W4417073386","doi":"https://doi.org/10.1145/3743093.3770999"},"language":null,"primary_location":{"id":"doi:10.1145/3743093.3770999","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3743093.3770999","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3770999","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3770999","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100643784","display_name":"Luping Zhou","orcid":"https://orcid.org/0000-0001-8762-2424"},"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":true,"raw_author_name":"Luping Zhou","raw_affiliation_strings":["The University of Sydney, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068378871","display_name":"Xiaoyu Yue","orcid":"https://orcid.org/0000-0001-7023-0264"},"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":"Xiaoyu Yue","raw_affiliation_strings":["The University of Sydney, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100643784"],"corresponding_institution_ids":["https://openalex.org/I129604602"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.41820671,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.7565000057220459,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.7565000057220459,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.1200999990105629,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.027499999850988388,"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/generative-grammar","display_name":"Generative grammar","score":0.7687000036239624},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5260999798774719},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4867999851703644},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4636000096797943},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4392000138759613},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4092999994754791}],"concepts":[{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.7687000036239624},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7537999749183655},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6061999797821045},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5260999798774719},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4867999851703644},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4636000096797943},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4392000138759613},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4092999994754791},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3831999897956848},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3382999897003174},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3075000047683716},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2809000015258789},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2621999979019165}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3743093.3770999","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3743093.3770999","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3770999","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3743093.3770999","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3743093.3770999","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3770999","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4417073386.pdf"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W2245625259","https://openalex.org/W2326925005","https://openalex.org/W2331143823","https://openalex.org/W3034838697","https://openalex.org/W3035524453","https://openalex.org/W3132401450","https://openalex.org/W3145450063","https://openalex.org/W3159481202","https://openalex.org/W3212516020","https://openalex.org/W4312783155","https://openalex.org/W4312804044","https://openalex.org/W4312891522","https://openalex.org/W4312898263","https://openalex.org/W4312933868","https://openalex.org/W4313156423","https://openalex.org/W4386221015","https://openalex.org/W4390872010","https://openalex.org/W4390872297","https://openalex.org/W4390874529"],"related_works":[],"abstract_inverted_index":{"Learning":[0],"semantic":[1,58,79],"representations":[2,55],"with":[3,70],"generative":[4,116,141],"self-supervised":[5,146],"pre-training":[6],"has":[7,22],"demonstrated":[8],"immense":[9],"potential":[10],"in":[11,27],"the":[12,123,132],"field":[13],"of":[14],"Natural":[15],"Language":[16],"Processing":[17],"(NLP).":[18],"However,":[19],"this":[20,120],"success":[21],"not":[23],"been":[24],"fully":[25],"replicated":[26],"computer":[28],"vision,":[29],"primarily":[30],"due":[31],"to":[32,42,77,101,153,164],"two":[33],"key":[34],"challenges:":[35],"(1)":[36],"visual":[37,54,107,145],"generation":[38,88,166,182],"tasks":[39,52,89,155,167,179,196],"are":[40],"difficult":[41],"formalize":[43],"into":[44,114,129],"a":[45,66,71,91,115],"unified":[46],"task,":[47],"and":[48,84,109,171,180,184],"(2)":[49],"different":[50,82,106],"downstream":[51,154,177],"require":[53],"at":[56,81,105],"varying":[57],"levels.":[59],"To":[60,118],"address":[61],"these":[62,111],"challenges,":[63],"we":[64],"propose":[65],"novel":[67],"Generative":[68],"framework":[69],"UNified":[72],"Self-supervised":[73],"training":[74,103,112],"paradigm":[75],"(GUNS)":[76],"learn":[78],"information":[80],"granularities":[83],"unify":[85],"multiple":[86],"image":[87,133,165,181],"within":[90],"denoising":[92,124],"diffusion":[93,125],"model.":[94,142],"Specifically,":[95],"GUNS":[96,130,137,159,175,189],"employs":[97],"various":[98],"data":[99],"augmentations":[100],"construct":[102],"objectives":[104,113],"levels":[108],"unifies":[110],"paradigm.":[117],"facilitate":[119],"multi-task":[121],"pre-training,":[122],"model":[126],"is":[127],"introduced":[128],"as":[131,169],"decoder,":[134],"thereby":[135],"making":[136],"also":[138],"an":[139],"image-conditional":[140],"Unlike":[143],"other":[144],"methods":[147],"that":[148,188],"can":[149,160,190],"only":[150],"be":[151,161],"applied":[152,163],"via":[156],"transfer":[157],"learning,":[158],"directly":[162],"such":[168],"colorization":[170],"out-painting.":[172],"We":[173],"evaluate":[174],"on":[176,194],"recognition":[178],"tasks,":[183],"experimental":[185],"results":[186],"demonstrate":[187],"achieve":[191],"competitive":[192],"performance":[193],"both":[195],"simultaneously.":[197]},"counts_by_year":[],"updated_date":"2026-03-11T06:11:40.159057","created_date":"2025-12-06T00:00:00"}