{"id":"https://openalex.org/W4403791656","doi":"https://doi.org/10.1145/3664647.3681011","title":"AesMamba: Universal Image Aesthetic Assessment with State Space Models","display_name":"AesMamba: Universal Image Aesthetic Assessment with State Space Models","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791656","doi":"https://doi.org/10.1145/3664647.3681011"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681011","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681011","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/A5101652488","display_name":"Fei Gao","orcid":"https://orcid.org/0000-0002-8714-0975"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Fei Gao","raw_affiliation_strings":["Xidian University, Xian, China"],"affiliations":[{"raw_affiliation_string":"Xidian University, Xian, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101819880","display_name":"Yuhao Lin","orcid":"https://orcid.org/0009-0001-0328-9626"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhao Lin","raw_affiliation_strings":["Hangzhou Dianzi University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101644215","display_name":"Jian Shi","orcid":"https://orcid.org/0000-0003-1679-4063"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaqi Shi","raw_affiliation_strings":["Xidian University, Xian, China"],"affiliations":[{"raw_affiliation_string":"Xidian University, Xian, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101810682","display_name":"Maoying Qiao","orcid":"https://orcid.org/0000-0002-0990-5506"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Maoying Qiao","raw_affiliation_strings":["The University of Technology, Sydney, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Technology, Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100690630","display_name":"Nannan Wang","orcid":"https://orcid.org/0000-0003-1435-489X"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nannan Wang","raw_affiliation_strings":["Xidian University, Xian, China"],"affiliations":[{"raw_affiliation_string":"Xidian University, Xian, China","institution_ids":["https://openalex.org/I149594827"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101652488"],"corresponding_institution_ids":["https://openalex.org/I149594827"],"apc_list":null,"apc_paid":null,"fwci":1.745,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.86336171,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7444","last_page":"7453"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9995999932289124,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9995999932289124,"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/T12650","display_name":"Aesthetic Perception and Analysis","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9921000003814697,"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/image","display_name":"Image (mathematics)","score":0.6074976325035095},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5818707346916199},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5549901127815247},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5122696757316589},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4776429235935211},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.43859896063804626},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4195120930671692},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2573314309120178},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1613524854183197},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09664243459701538}],"concepts":[{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6074976325035095},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5818707346916199},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5549901127815247},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5122696757316589},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4776429235935211},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.43859896063804626},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4195120930671692},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2573314309120178},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1613524854183197},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09664243459701538},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681011","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681011","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":[{"id":"https://metadata.un.org/sdg/11","score":0.7200000286102295,"display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":75,"referenced_works":["https://openalex.org/W250253301","https://openalex.org/W1511924373","https://openalex.org/W2080754665","https://openalex.org/W2104915826","https://openalex.org/W2194775991","https://openalex.org/W2417288846","https://openalex.org/W2549139847","https://openalex.org/W2779483295","https://openalex.org/W2897926040","https://openalex.org/W2904572228","https://openalex.org/W2931027027","https://openalex.org/W2963204629","https://openalex.org/W2976886057","https://openalex.org/W2980568635","https://openalex.org/W3003957020","https://openalex.org/W3012364787","https://openalex.org/W3016197248","https://openalex.org/W3034776788","https://openalex.org/W3035523707","https://openalex.org/W3037789293","https://openalex.org/W3093501041","https://openalex.org/W3095157576","https://openalex.org/W3103635814","https://openalex.org/W3138516171","https://openalex.org/W3171472210","https://openalex.org/W3182485714","https://openalex.org/W3208314443","https://openalex.org/W3208678646","https://openalex.org/W3208827570","https://openalex.org/W3212492847","https://openalex.org/W3216672656","https://openalex.org/W4214745154","https://openalex.org/W4221145950","https://openalex.org/W4283461773","https://openalex.org/W4285216607","https://openalex.org/W4285606417","https://openalex.org/W4285787548","https://openalex.org/W4292779060","https://openalex.org/W4293057409","https://openalex.org/W4293519076","https://openalex.org/W4304142045","https://openalex.org/W4306820534","https://openalex.org/W4308872605","https://openalex.org/W4312327698","https://openalex.org/W4312353506","https://openalex.org/W4312443924","https://openalex.org/W4312574244","https://openalex.org/W4319316596","https://openalex.org/W4322576760","https://openalex.org/W4322766882","https://openalex.org/W4362471799","https://openalex.org/W4372037384","https://openalex.org/W4379469552","https://openalex.org/W4382203002","https://openalex.org/W4382240262","https://openalex.org/W4382567941","https://openalex.org/W4385245566","https://openalex.org/W4386065622","https://openalex.org/W4386076227","https://openalex.org/W4386076553","https://openalex.org/W4386160444","https://openalex.org/W4386280974","https://openalex.org/W4386590638","https://openalex.org/W4387968024","https://openalex.org/W4387969352","https://openalex.org/W4387969606","https://openalex.org/W4390350546","https://openalex.org/W4390457875","https://openalex.org/W4390576755","https://openalex.org/W4390871938","https://openalex.org/W4391759565","https://openalex.org/W4393148714","https://openalex.org/W4403233724","https://openalex.org/W6739901393","https://openalex.org/W6778883912"],"related_works":["https://openalex.org/W2755342338","https://openalex.org/W2779427294","https://openalex.org/W2775347418","https://openalex.org/W2625805835","https://openalex.org/W2079911747","https://openalex.org/W3116076068","https://openalex.org/W3003936178","https://openalex.org/W2145652935","https://openalex.org/W2563206327","https://openalex.org/W2069885731"],"abstract_inverted_index":{"Image":[0],"Aesthetic":[1],"Assessment":[2],"(IAA)":[3],"aims":[4],"to":[5,45,87,112,136,165,188],"objectively":[6],"predict":[7],"the":[8,14,53,76,115,120,125,143,149,174],"generic":[9],"or":[10,16,22,85,209],"personalized":[11,150],"evaluations,":[12],"of":[13,83,91,122,176,195],"aesthetic":[15],"fine-grained":[17],"multi-attributes,":[18],"based":[19,37],"on":[20,38,119,142,200,212],"visual":[21],"multimodal":[23,155],"inputs.":[24],"Previously,":[25],"researchers":[26],"have":[27],"designed":[28],"diverse":[29,189],"and":[30,65,101],"specialized":[31],"methods,":[32],"for":[33,52,180],"specific":[34],"IAA":[35,49,55,69,151,190,214],"tasks,":[36,191,215],"different":[39],"input-output":[40],"situations.":[41],"Is":[42],"it":[43],"possible":[44],"design":[46],"a":[47,67,107,130,154,160,166],"universal":[48],"framework":[50],"applicable":[51],"whole":[54],"task":[56,152],"taxonomy?":[57],"In":[58,124],"this":[59,63],"paper,":[60],"we":[61,74,128,147],"explore":[62],"issue,":[64],"propose":[66,129],"modular":[68],"framework,":[70],"dubbed":[71],"AesMamba.":[72],"Specially,":[73],"use":[75],"Visual":[77],"State":[78],"Space":[79],"Model":[80],"(VMamba),":[81],"instead":[82],"CNNs":[84],"ViTs,":[86],"learn":[88],"comprehensive":[89],"representations":[90],"aesthetic-related":[92],"attributes;":[93],"because":[94],"VMamba":[95],"can":[96,185],"efficiently":[97],"achieve":[98],"both":[99],"global":[100],"local":[102],"effective":[103],"receptive":[104],"fields.":[105],"Afterward,":[106],"modal-adaptive":[108],"module":[109],"is":[110],"used":[111],"automatically":[113],"produce":[114],"integrated":[116],"representations,":[117],"conditioned":[118],"type":[121],"input.":[123],"prediction":[126],"module,":[127,135],"Multitask":[131],"Balanced":[132],"Adaptation":[133],"(MBA)":[134],"boost":[137],"task-specific":[138],"features,":[139],"with":[140,218],"emphasis":[141],"tail":[144],"instances.":[145],"Finally,":[146],"formulate":[148],"as":[153],"learning":[156],"problem,":[157],"by":[158],"converting":[159],"user's":[161],"anonymous":[162],"subject":[163],"characters":[164],"text":[167],"prompt.":[168],"This":[169],"prompting":[170],"strategy":[171],"effectively":[172],"employs":[173],"semantics":[175],"flexibly":[177],"selected":[178],"characters,":[179],"inferring":[181],"individual":[182],"preferences.":[183],"AesMamba":[184,205],"be":[186],"applied":[187],"through":[192],"flexible":[193],"combination":[194],"these":[196],"modules.":[197],"Extensive":[198],"experiments":[199],"numerous":[201],"datasets,":[202],"demonstrate":[203],"that":[204],"consistently":[206],"achieves":[207],"superior":[208],"competitive":[210],"performance,":[211],"all":[213],"in":[216],"comparison":[217],"previous":[219],"SOTA":[220],"methods.":[221],"The":[222],"code":[223],"has":[224],"been":[225],"released":[226],"at":[227],"https://github.com/AiArt-Gao/AesMamba":[228],"Github.":[229]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}