{"id":"https://openalex.org/W4414524409","doi":"https://doi.org/10.1109/tmm.2025.3632637","title":"AesPrompt: Zero-Shot Image Aesthetics Assessment With Multi-Granularity Aesthetic Prompt Learning","display_name":"AesPrompt: Zero-Shot Image Aesthetics Assessment With Multi-Granularity Aesthetic Prompt Learning","publication_year":2025,"publication_date":"2025-11-14","ids":{"openalex":"https://openalex.org/W4414524409","doi":"https://doi.org/10.1109/tmm.2025.3632637"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2025.3632637","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3632637","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://centralesupelec.hal.science/hal-05160413/document","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044278717","display_name":"Xiangfei Sheng","orcid":"https://orcid.org/0009-0004-8468-1970"},"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":"Xiangfei Sheng","raw_affiliation_strings":["School of Artificial Intelligence, Xidian University, Xi’an, China","Xidian University (Xi'an - China)"],"raw_orcid":"https://orcid.org/0009-0004-8468-1970","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"Xidian University (Xi'an - China)","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033615240","display_name":"Leida Li","orcid":"https://orcid.org/0000-0001-9069-8796"},"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":"Leida Li","raw_affiliation_strings":["School of Artificial Intelligence, Xidian University, Xi’an, China","Xidian University (Xi'an - China)"],"raw_orcid":"https://orcid.org/0000-0001-9069-8796","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"Xidian University (Xi'an - China)","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063520709","display_name":"Pengfei Chen","orcid":"https://orcid.org/0000-0002-0509-3782"},"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":"Pengfei Chen","raw_affiliation_strings":["School of Artificial Intelligence, Xidian University, Xi’an, China","Xidian University (Xi'an - China)"],"raw_orcid":"https://orcid.org/0000-0002-0509-3782","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"Xidian University (Xi'an - China)","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057512188","display_name":"Li Cai","orcid":"https://orcid.org/0000-0003-0015-570X"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]},{"id":"https://openalex.org/I161350542","display_name":"China Three Gorges University","ror":"https://ror.org/0419nfc77","country_code":"CN","type":"education","lineage":["https://openalex.org/I161350542"]},{"id":"https://openalex.org/I50180762","display_name":"Chongqing Three Gorges University","ror":"https://ror.org/05rs3pv16","country_code":"CN","type":"education","lineage":["https://openalex.org/I50180762"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Cai","raw_affiliation_strings":["School of Electronic and Information Engineering, Chongqing Three Gorges University, Chongqing, China","China Three Gorges University (China)","Chongqing University [Chongqing] (131 Yubei Rd, Shapingba, Chongqing - China)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, Chongqing Three Gorges University, Chongqing, China","institution_ids":["https://openalex.org/I50180762"]},{"raw_affiliation_string":"China Three Gorges University (China)","institution_ids":["https://openalex.org/I161350542"]},{"raw_affiliation_string":"Chongqing University [Chongqing] (131 Yubei Rd, Shapingba, Chongqing - China)","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034069364","display_name":"Giuseppe Valenzise","orcid":"https://orcid.org/0000-0002-5840-5743"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210097418","display_name":"Laboratoire des signaux et syst\u00e8mes","ror":"https://ror.org/00skw9v43","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I277688954","https://openalex.org/I277688954","https://openalex.org/I4210097418","https://openalex.org/I4210107720"]},{"id":"https://openalex.org/I4210107720","display_name":"CentraleSup\u00e9lec","ror":"https://ror.org/019tcpt25","country_code":"FR","type":"facility","lineage":["https://openalex.org/I277688954","https://openalex.org/I4210107720"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Giuseppe Valenzise","raw_affiliation_strings":["CNRS, CentraleSupelec, Laboratoire des Signaux et Systèmes, Université Paris Saclay, Gif-sur-Yvette, France","L2S - Laboratoire des signaux et syst\u00e8mes (Plateau de Moulon 3 rue Joliot Curie 91192 GIF SUR YVETTE CEDEX - France)"],"raw_orcid":"https://orcid.org/0000-0002-5840-5743","affiliations":[{"raw_affiliation_string":"CNRS, CentraleSupelec, Laboratoire des Signaux et Systèmes, Université Paris Saclay, Gif-sur-Yvette, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210097418","https://openalex.org/I4210107720"]},{"raw_affiliation_string":"L2S - Laboratoire des signaux et syst\u00e8mes (Plateau de Moulon 3 rue Joliot Curie 91192 GIF SUR YVETTE CEDEX - France)","institution_ids":["https://openalex.org/I4210097418"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7508,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.73613395,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"28","issue":null,"first_page":"958","last_page":"971"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12650","display_name":"Aesthetic Perception and Analysis","score":0.996399998664856,"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"}},"topics":[{"id":"https://openalex.org/T12650","display_name":"Aesthetic Perception and Analysis","score":0.996399998664856,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9889000058174133,"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/T11659","display_name":"Advanced Image Fusion Techniques","score":0.9513999819755554,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7976999878883362},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5979999899864197},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.5917999744415283},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.49570000171661377},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.48570001125335693},{"id":"https://openalex.org/keywords/subject","display_name":"Subject (documents)","score":0.4120999872684479},{"id":"https://openalex.org/keywords/aesthetic-experience","display_name":"Aesthetic experience","score":0.3700000047683716}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7976999878883362},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.722000002861023},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5979999899864197},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.5917999744415283},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5909000039100647},{"id":"https://openalex.org/C107038049","wikidata":"https://www.wikidata.org/wiki/Q35986","display_name":"Aesthetics","level":1,"score":0.5285000205039978},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.49570000171661377},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.48570001125335693},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.4120999872684479},{"id":"https://openalex.org/C2983793060","wikidata":"https://www.wikidata.org/wiki/Q35986","display_name":"Aesthetic experience","level":2,"score":0.3700000047683716},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36899998784065247},{"id":"https://openalex.org/C2994152597","wikidata":"https://www.wikidata.org/wiki/Q4688582","display_name":"Aesthetic theory","level":2,"score":0.36480000615119934},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3499999940395355},{"id":"https://openalex.org/C2778449503","wikidata":"https://www.wikidata.org/wiki/Q329777","display_name":"Appeal","level":2,"score":0.34049999713897705},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33320000767707825},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.3188000023365021},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2685999870300293},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.25209999084472656}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tmm.2025.3632637","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3632637","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-05160413v1","is_oa":true,"landing_page_url":"https://centralesupelec.hal.science/hal-05160413","pdf_url":"https://centralesupelec.hal.science/hal-05160413/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Multimedia, 2025, pp.1-15. ⟨10.1109/TMM.2025.3632637⟩","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-05160413v1","is_oa":true,"landing_page_url":"https://centralesupelec.hal.science/hal-05160413","pdf_url":"https://centralesupelec.hal.science/hal-05160413/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Multimedia, 2025, pp.1-15. ⟨10.1109/TMM.2025.3632637⟩","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1143917335","display_name":null,"funder_award_id":"62471349","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2262808377","display_name":null,"funder_award_id":"62301378","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3467900600","display_name":null,"funder_award_id":"YJSJ24012","funder_id":"https://openalex.org/F4320323230","funder_display_name":"Xidian University"},{"id":"https://openalex.org/G6468169989","display_name":null,"funder_award_id":"62171340","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8295620307","display_name":null,"funder_award_id":"QTZX25076","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8462500887","display_name":null,"funder_award_id":"2024M762553","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G8750420762","display_name":null,"funder_award_id":"QTZX25076","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320323230","display_name":"Xidian University","ror":"https://ror.org/05s92vm98"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414524409.pdf","grobid_xml":"https://content.openalex.org/works/W4414524409.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"years":[1],"have":[2],"witnessed":[3],"increasing":[4],"interest":[5],"towards":[6],"image":[7,61,141],"aesthetics":[8,62,145],"assessment":[9,63],"(IAA),":[10],"which":[11,50,78],"predicts":[12],"the":[13,47,106,150,154,173],"aesthetic":[14,40,76,85,108,126],"appeal":[15],"of":[16,39,101,137],"images":[17],"by":[18,58],"simulating":[19],"human":[20,37,107],"perception.":[21],"The":[22,98],"state-of-the-art":[23,174],"IAA":[24,166],"methods,":[25],"despite":[26],"their":[27],"significant":[28],"advancements,":[29],"typically":[30],"rely":[31],"heavily":[32],"on":[33,74,131,164],"time-consuming":[34],"and":[35,144,160,185],"labor-intensive":[36],"annotation":[38],"scores.":[41],"Furthermore,":[42],"they":[43],"are":[44],"subject":[45],"to":[46,67,104],"generalization":[48,71,159],"challenge,":[49],"is":[51,65,93,103,146],"highly":[52],"desired":[53],"in":[54,95,115],"real-world":[55],"applications.":[56],"Motivated":[57],"this,":[59],"zero-shot":[60],"(ZIAA)":[64],"investigated":[66],"achieve":[68],"robust":[69],"model":[70],"without":[72],"relying":[73],"manual":[75],"annotations,":[77],"remains":[79],"largely":[80],"underexplored.":[81],"Specifically,":[82],"a":[83,116,123],"novel":[84],"prompt":[86],"learning":[87,112,149],"framework":[88],"for":[89,111],"ZIAA,":[90],"dubbed":[91],"AesPrompt,":[92],"presented":[94],"this":[96],"paper.":[97],"key":[99],"insight":[100],"AesPrompt":[102,170],"emulate":[105],"perception":[109],"process":[110],"aesthetic-oriented":[113,152],"prompts":[114,139],"multi-granularity":[117,138,151],"manner.":[118],"First,":[119],"we":[120],"first":[121],"develop":[122],"new":[124],"pseudo":[125],"distribution":[127],"generation":[128],"paradigm":[129],"based":[130],"multi-LLM":[132],"ensemble.":[133],"Then,":[134],"external":[135],"knowledge":[136],"encompassing":[140],"themes,":[142],"emotions,":[143],"acquired.":[147],"Through":[148],"prompts,":[153],"proposed":[155],"method":[156],"achieves":[157],"better":[158],"interpretability.":[161],"Extensive":[162],"experiments":[163],"five":[165],"benchmarks":[167],"demonstrate":[168],"that":[169],"consistently":[171],"outperforms":[172],"ZIAA":[175],"methods":[176],"across":[177],"diverse-sourced":[178],"images,":[179,182,184],"covering":[180],"natural":[181],"artistic":[183],"artificial":[186],"intelligence-generated":[187],"images.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-09-26T00:00:00"}