{"id":"https://openalex.org/W4408345879","doi":"https://doi.org/10.1109/icassp49660.2025.10889477","title":"Aesthetic Perception Prompting for Interpretable Image Aesthetics Assessment with MLLMs","display_name":"Aesthetic Perception Prompting for Interpretable Image Aesthetics Assessment with MLLMs","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345879","doi":"https://doi.org/10.1109/icassp49660.2025.10889477"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889477","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889477","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5025153128","display_name":"Lanjun Wang","orcid":"https://orcid.org/0000-0002-7696-5330"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lanjun Wang","raw_affiliation_strings":["Tianjin University,Tianjin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zheyu Qiao","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheyu Qiao","raw_affiliation_strings":["Tianjin University,Tianjin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101893410","display_name":"Ruidong Chen","orcid":"https://orcid.org/0000-0002-1970-5743"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruidong Chen","raw_affiliation_strings":["Tianjin University,Tianjin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010868615","display_name":"Jingqiu Li","orcid":"https://orcid.org/0009-0007-3867-9855"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingqiu Li","raw_affiliation_strings":["Tianjin University,Tianjin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100368517","display_name":"Wenjie Wang","orcid":"https://orcid.org/0000-0002-0614-1723"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenjie Wang","raw_affiliation_strings":["Meituan Group,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meituan Group,Beijing,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101435861","display_name":"Xiaoqiong Wang","orcid":"https://orcid.org/0000-0001-6555-7529"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoqiong Wang","raw_affiliation_strings":["Meituan Group,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meituan Group,Beijing,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013535253","display_name":"Wei Rao","orcid":"https://orcid.org/0000-0002-5738-0759"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Rao","raw_affiliation_strings":["Meituan Group,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meituan Group,Beijing,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100396681","display_name":"Shuai Chen","orcid":"https://orcid.org/0000-0002-6964-3755"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuai Chen","raw_affiliation_strings":["Meituan Group,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meituan Group,Beijing,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101956376","display_name":"An\u2010An Liu","orcid":"https://orcid.org/0000-0002-3563-6290"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"An-An Liu","raw_affiliation_strings":["Tianjin University,Tianjin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8699,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.84123646,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.991599977016449,"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":0.991599977016449,"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":0.9653000235557556,"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"}},{"id":"https://openalex.org/T12650","display_name":"Aesthetic Perception and Analysis","score":0.961899995803833,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.7552328109741211},{"id":"https://openalex.org/keywords/aesthetics","display_name":"Aesthetics","score":0.6994805335998535},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4928283989429474},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.48698219656944275},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.43163448572158813},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.4309675991535187},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4123561382293701},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.4041050374507904},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.26502862572669983}],"concepts":[{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.7552328109741211},{"id":"https://openalex.org/C107038049","wikidata":"https://www.wikidata.org/wiki/Q35986","display_name":"Aesthetics","level":1,"score":0.6994805335998535},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4928283989429474},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48698219656944275},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.43163448572158813},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4309675991535187},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4123561382293701},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.4041050374507904},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.26502862572669983},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889477","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889477","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2078807908","https://openalex.org/W2080754665","https://openalex.org/W2417288846","https://openalex.org/W2524036617","https://openalex.org/W2780162533","https://openalex.org/W2981671251","https://openalex.org/W3002992380","https://openalex.org/W3035595647","https://openalex.org/W3193689960","https://openalex.org/W4235652592","https://openalex.org/W4283212088","https://openalex.org/W4312353506","https://openalex.org/W4322576760","https://openalex.org/W4382240262","https://openalex.org/W4387969352","https://openalex.org/W4390535310","https://openalex.org/W4390871938","https://openalex.org/W4391999016","https://openalex.org/W4392904100","https://openalex.org/W4393156011","https://openalex.org/W4394862887","https://openalex.org/W4396828492","https://openalex.org/W4398174088","https://openalex.org/W4401039537","https://openalex.org/W4401125130","https://openalex.org/W4403791977","https://openalex.org/W4403792379","https://openalex.org/W4411245182","https://openalex.org/W6791353385","https://openalex.org/W6851592950","https://openalex.org/W6860729003","https://openalex.org/W6866643551"],"related_works":["https://openalex.org/W2628861693","https://openalex.org/W3203087560","https://openalex.org/W4361279463","https://openalex.org/W4232814730","https://openalex.org/W2975814312","https://openalex.org/W4387697615","https://openalex.org/W2568121504","https://openalex.org/W2483836897","https://openalex.org/W2049668268","https://openalex.org/W2087303720"],"abstract_inverted_index":{"Image":[0],"Aesthetic":[1],"Assessment":[2],"(IAA)":[3],"aims":[4],"to":[5,29,43,58,60,106,120,145,149],"rate":[6],"the":[7,45,50,63,85,122,126,147,165],"aesthetic":[8,80,87,95,127,173],"quality":[9],"of":[10,125,139,167],"images":[11],"and":[12,99,152,157,176],"has":[13],"many":[14],"practical":[15],"applications.":[16],"However,":[17],"existing":[18],"methods":[19],"typically":[20],"rely":[21],"on":[22],"limited":[23],"annotated":[24],"data":[25],"for":[26,41,77,154,180],"training,":[27],"leading":[28],"two":[30,92,141],"key":[31,93],"issues:":[32],"1)":[33],"score-only":[34],"predictions":[35],"lack":[36],"interpretability,":[37],"making":[38],"it":[39],"hard":[40],"users":[42],"understand":[44],"reasoning":[46],"behind":[47],"ratings;":[48],"2)":[49],"assessment":[51,97],"ability":[52,175],"learned":[53],"through":[54],"supervised":[55],"training":[56,64],"struggles":[57],"generalize":[59],"scenarios":[61],"beyond":[62],"data.":[65],"To":[66],"address":[67],"these":[68,140],"challenges,":[69],"we":[70,90],"leverage":[71],"Multi-Modal":[72],"Large":[73],"Language":[74],"Models":[75],"(MLLMs)":[76],"interpretable":[78,181],"image":[79],"assessment.":[81],"Drawing":[82],"inspiration":[83],"from":[84],"human":[86],"perception":[88,174],"process,":[89],"propose":[91],"components:":[94],"attribute":[96],"(AAA)":[98],"scene-aware":[100,117],"in-context":[101],"learning":[102],"(ICL).":[103],"AAA":[104],"is":[105,119,143],"provide":[107,150],"detailed":[108],"attribute-based":[109],"analysis":[110],"by":[111],"prompting":[112],"with":[113,133],"evaluation":[114],"criteria.":[115],"Meanwhile,":[116],"ICL":[118],"improve":[121],"model\u2019s":[123],"understanding":[124],"scoring":[128],"principles":[129],"across":[130,161],"different":[131],"scenes":[132],"given":[134],"corresponding":[135],"references.":[136],"The":[137],"output":[138],"components":[142],"used":[144],"guide":[146],"model":[148],"ratings":[151],"interpretations":[153],"more":[155],"reliable":[156],"understandable":[158],"results.":[159],"Experiments":[160],"multiple":[162],"datasets":[163],"show":[164],"effectiveness":[166],"our":[168],"framework":[169],"in":[170],"enhancing":[171],"MLLM\u2019s":[172],"underscore":[177],"its":[178],"potential":[179],"IAA.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}