{"id":"https://openalex.org/W4402980487","doi":"https://doi.org/10.1109/icme57554.2024.10687472","title":"Multi-modal Learnable Queries for Image Aesthetics Assessment","display_name":"Multi-modal Learnable Queries for Image Aesthetics Assessment","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402980487","doi":"https://doi.org/10.1109/icme57554.2024.10687472"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10687472","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687472","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5008612863","display_name":"Zhiwei Xiong","orcid":"https://orcid.org/0000-0002-9787-7460"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhiwei Xiong","raw_affiliation_strings":["Nanyang Technological University,College of Computing and Data Science,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,College of Computing and Data Science,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119962963","display_name":"Yunfan Zhang","orcid":"https://orcid.org/0009-0004-4101-2507"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yunfan Zhang","raw_affiliation_strings":["Nanyang Technological University,College of Computing and Data Science,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,College of Computing and Data Science,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101789458","display_name":"Zhiqi Shen","orcid":"https://orcid.org/0000-0001-7626-7295"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhiqi Shen","raw_affiliation_strings":["Nanyang Technological University,College of Computing and Data Science,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,College of Computing and Data Science,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081147881","display_name":"Peiran Ren","orcid":"https://orcid.org/0000-0002-9111-055X"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peiran Ren","raw_affiliation_strings":["Alibaba Group,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Hangzhou,China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064069283","display_name":"Han Yu","orcid":"https://orcid.org/0000-0001-6893-8650"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Han Yu","raw_affiliation_strings":["Nanyang Technological University,College of Computing and Data Science,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,College of Computing and Data Science,Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9951000213623047,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9951000213623047,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9912999868392944,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9884999990463257,"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/modal","display_name":"Modal","score":0.7971612215042114},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6178740859031677},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5044821500778198},{"id":"https://openalex.org/keywords/aesthetics","display_name":"Aesthetics","score":0.4695499539375305},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4555862545967102},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4186943769454956},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.1431545913219452},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.11511081457138062},{"id":"https://openalex.org/keywords/composite-material","display_name":"Composite material","score":0.057668209075927734}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7971612215042114},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6178740859031677},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5044821500778198},{"id":"https://openalex.org/C107038049","wikidata":"https://www.wikidata.org/wiki/Q35986","display_name":"Aesthetics","level":1,"score":0.4695499539375305},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4555862545967102},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4186943769454956},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.1431545913219452},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.11511081457138062},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.057668209075927734}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10687472","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687472","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1511924373","https://openalex.org/W2009678853","https://openalex.org/W2078807908","https://openalex.org/W2170658603","https://openalex.org/W2524036617","https://openalex.org/W2754213847","https://openalex.org/W2931027027","https://openalex.org/W3035523707","https://openalex.org/W3171472210","https://openalex.org/W3185341429","https://openalex.org/W4281846337","https://openalex.org/W4285606417","https://openalex.org/W4372037384","https://openalex.org/W4385764562","https://openalex.org/W4386076522","https://openalex.org/W4386159014","https://openalex.org/W4386160444","https://openalex.org/W4386280974","https://openalex.org/W4392902675","https://openalex.org/W4392904322","https://openalex.org/W6791353385"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Image":[0],"aesthetics":[1],"assessment":[2],"(IAA)":[3],"is":[4,16,47],"attracting":[5],"wide":[6],"interest":[7],"with":[8,38],"the":[9,33,79],"prevalence":[10],"of":[11,26,125],"social":[12],"media.":[13],"The":[14],"problem":[15],"challenging":[17],"due":[18],"to":[19,71,95],"its":[20],"subjective":[21],"and":[22,64,121,127],"ambiguous":[23],"nature.":[24],"Instead":[25],"directly":[27],"extracting":[28,60,75],"aesthetic":[29],"features":[30,77,98],"solely":[31],"from":[32,78,99],"image,":[34],"user":[35],"comments":[36],"associated":[37],"an":[39],"image":[40],"could":[41],"potentially":[42],"provide":[43],"complementary":[44],"knowledge":[45],"that":[46,107],"useful":[48,76],"for":[49],"IAA.":[50],"With":[51],"existing":[52],"large-scale":[53],"pre-trained":[54,80,101],"models":[55],"demonstrating":[56],"strong":[57],"capabilities":[58],"in":[59,74,84,123],"high-quality":[61],"transferable":[62],"visual":[63,81],"textual":[65],"features,":[66],"learnable":[67,93],"queries":[68,94],"are":[69],"shown":[70],"be":[72],"effective":[73],"features.":[82,102],"Therefore,":[83],"this":[85],"paper,":[86],"we":[87],"propose":[88],"MMLQ,":[89],"which":[90],"utilizes":[91],"multi-modal":[92,100],"extract":[96],"aesthetics-related":[97],"Extensive":[103],"experimental":[104],"results":[105],"demonstrate":[106],"MMLQ":[108],"achieves":[109],"new":[110],"state-of-the-art":[111],"performance":[112],"on":[113],"multimodal":[114],"IAA,":[115],"beating":[116],"previous":[117],"methods":[118],"by":[119],"7.7%":[120],"8.3%":[122],"terms":[124],"SRCC":[126],"PLCC,":[128],"respectively.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}