{"id":"https://openalex.org/W4414140673","doi":"https://doi.org/10.1109/icmew68306.2025.11152049","title":"Prompt-Guided Aesthetic Assessment with Cross-Modal Semantic Alignment","display_name":"Prompt-Guided Aesthetic Assessment with Cross-Modal Semantic Alignment","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4414140673","doi":"https://doi.org/10.1109/icmew68306.2025.11152049"},"language":"en","primary_location":{"id":"doi:10.1109/icmew68306.2025.11152049","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmew68306.2025.11152049","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","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/A5101963202","display_name":"Hongtao Yang","orcid":"https://orcid.org/0000-0002-4029-0255"},"institutions":[{"id":"https://openalex.org/I4210152042","display_name":"Beijing Polytechnic","ror":"https://ror.org/03xgzn792","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152042"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hongtao Yang","raw_affiliation_strings":["Beijing Polytechnic College,School of Information Engineering,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing Polytechnic College,School of Information Engineering,Beijing,China","institution_ids":["https://openalex.org/I4210152042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063421145","display_name":"Yehui Liu","orcid":"https://orcid.org/0000-0002-3543-4525"},"institutions":[{"id":"https://openalex.org/I4210152042","display_name":"Beijing Polytechnic","ror":"https://ror.org/03xgzn792","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yehui Liu","raw_affiliation_strings":["Beijing Polytechnic College,School of Information Engineering,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing Polytechnic College,School of Information Engineering,Beijing,China","institution_ids":["https://openalex.org/I4210152042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100553175","display_name":"Shi Ping","orcid":"https://orcid.org/0009-0003-7744-6246"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ping Shi","raw_affiliation_strings":["Communication University of China,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Communication University of China,Beijing,China","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100641350","display_name":"Xin Jin","orcid":"https://orcid.org/0000-0003-2211-2006"},"institutions":[{"id":"https://openalex.org/I202334528","display_name":"Beijing Electronic Science and Technology Institute","ror":"https://ror.org/01xdzh226","country_code":"CN","type":"education","lineage":["https://openalex.org/I202334528"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Jin","raw_affiliation_strings":["Beijing Electronic Science and Technology Institute,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing Electronic Science and Technology Institute,Beijing,China","institution_ids":["https://openalex.org/I202334528"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110340542","display_name":"Shuiping Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152042","display_name":"Beijing Polytechnic","ror":"https://ror.org/03xgzn792","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuiping Fang","raw_affiliation_strings":["Beijing Polytechnic College,School of Information Engineering,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing Polytechnic College,School of Information Engineering,Beijing,China","institution_ids":["https://openalex.org/I4210152042"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036107022","display_name":"Shujiang Xie","orcid":"https://orcid.org/0009-0009-3228-817X"},"institutions":[{"id":"https://openalex.org/I118803816","display_name":"Liaoning University","ror":"https://ror.org/03xpwj629","country_code":"CN","type":"education","lineage":["https://openalex.org/I118803816"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shujiang Xie","raw_affiliation_strings":["Liaoning University,China Business Development Institute(Beijing),Beijing,China"],"affiliations":[{"raw_affiliation_string":"Liaoning University,China Business Development Institute(Beijing),Beijing,China","institution_ids":["https://openalex.org/I118803816"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101963202"],"corresponding_institution_ids":["https://openalex.org/I4210152042"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2301622,"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":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9997000098228455,"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":0.9997000098228455,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9976000189781189,"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":0.9950000047683716,"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/ambiguity","display_name":"Ambiguity","score":0.7749999761581421},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.574400007724762},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5611000061035156},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5115000009536743},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4715000092983246},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.43630000948905945},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.38659998774528503},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.37709999084472656}],"concepts":[{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.7749999761581421},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7401000261306763},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6796000003814697},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.574400007724762},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5611000061035156},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5115000009536743},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4862000048160553},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4715000092983246},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.43630000948905945},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.38659998774528503},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.37709999084472656},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.3741999864578247},{"id":"https://openalex.org/C3020001037","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assessment","level":3,"score":0.33889999985694885},{"id":"https://openalex.org/C199579030","wikidata":"https://www.wikidata.org/wiki/Q2851778","display_name":"Automatic image annotation","level":4,"score":0.33559998869895935},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3230000138282776},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.32260000705718994},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2865999937057495},{"id":"https://openalex.org/C119657128","wikidata":"https://www.wikidata.org/wiki/Q11633","display_name":"Photography","level":2,"score":0.28130000829696655},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2773999869823456},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2757999897003174},{"id":"https://openalex.org/C168820333","wikidata":"https://www.wikidata.org/wiki/Q448889","display_name":"Visual inspection","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.258899986743927},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.2563999891281128}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmew68306.2025.11152049","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmew68306.2025.11152049","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320327285","display_name":"Beijing Polytechnic College","ror":null},{"id":"https://openalex.org/F4320334111","display_name":"Innovation Fund","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2078807908","https://openalex.org/W2417288846","https://openalex.org/W2604528050","https://openalex.org/W2754213847","https://openalex.org/W2931027027","https://openalex.org/W2970231061","https://openalex.org/W2976886057","https://openalex.org/W3003957020","https://openalex.org/W3094502228","https://openalex.org/W3103635814","https://openalex.org/W3174770825","https://openalex.org/W3198377975","https://openalex.org/W4214745154","https://openalex.org/W4285606417","https://openalex.org/W4293057409","https://openalex.org/W4293519076","https://openalex.org/W4302335910","https://openalex.org/W4312310776","https://openalex.org/W4382462760","https://openalex.org/W4386065622","https://openalex.org/W4386076227","https://openalex.org/W4386790226","https://openalex.org/W4387969352","https://openalex.org/W4394593151","https://openalex.org/W4401023526","https://openalex.org/W4403713306"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"The":[0],"rapid":[1],"proliferation":[2],"of":[3,18,32,57],"digital":[4],"technology":[5],"has":[6],"led":[7],"to":[8],"an":[9,71,92],"unprecedented":[10],"surge":[11],"in":[12,43],"visual":[13],"creations,":[14],"making":[15],"the":[16,29,54,96,106,114,142],"automation":[17],"image":[19,72],"aesthetic":[20,73],"quality":[21,74],"assessment":[22,75],"increasingly":[23],"imperative.":[24],"However,":[25],"challenges":[26],"such":[27],"as":[28],"limited":[30],"scale":[31],"dataset":[33,116],"samples,":[34],"subjective":[35],"annotation":[36,86],"biases,":[37],"and":[38,117,137],"semantic":[39],"ambiguity":[40,87],"hinder":[41],"progress":[42],"this":[44,68],"domain.":[45],"Moreover,":[46],"traditional":[47],"supervised":[48],"learning":[49],"paradigms":[50],"rely":[51],"excessively":[52],"on":[53,78,113,134],"feature":[55],"distributions":[56],"specific":[58],"datasets,":[59,125],"thereby":[60],"compromising":[61],"model":[62],"generalization.":[63],"To":[64],"address":[65],"these":[66],"limitations,":[67],"paper":[69],"proposes":[70],"strategy":[76],"based":[77],"prompt":[79,84,94],"learning.":[80],"By":[81],"employing":[82],"antonymous":[83],"text,":[85],"is":[88],"effectively":[89],"mitigated,":[90],"while":[91],"ensemble":[93],"reduces":[95],"bias":[97],"introduced":[98],"by":[99],"individual":[100],"prompts.":[101],"Experimental":[102],"results":[103],"demonstrate":[104],"that":[105],"proposed":[107],"method":[108],"achieves":[109],"state-of-the-art":[110],"EMD":[111],"metrics":[112],"AVA":[115],"delivers":[118],"exceptional":[119],"performance":[120],"across":[121],"multiple":[122],"publicly":[123],"available":[124],"significantly":[126],"outperforming":[127],"existing":[128],"methods.":[129],"Furthermore,":[130],"cross-domain":[131],"experiments":[132],"conducted":[133],"diverse":[135],"photography":[136],"fine":[138],"art":[139],"datasets":[140],"underscore":[141],"model\u2019s":[143],"remarkable":[144],"generalization":[145],"capability.":[146]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}