{"id":"https://openalex.org/W4413147156","doi":"https://doi.org/10.1109/cvpr52734.2025.00732","title":"Charm: The Missing Piece in ViT fine-tuning for Image Aesthetic Assessment","display_name":"Charm: The Missing Piece in ViT fine-tuning for Image Aesthetic Assessment","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413147156","doi":"https://doi.org/10.1109/cvpr52734.2025.00732"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.00732","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00732","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://lirias.kuleuven.be/retrieve/4e41d1f8-b4e2-4362-8274-4053f7c7d7f8","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085824073","display_name":"Fatemeh Behrad","orcid":"https://orcid.org/0000-0003-2629-0854"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Fatemeh Behrad","raw_affiliation_strings":["KU Leuven University,Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KU Leuven University,Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074816094","display_name":"Tinne Tuytelaars","orcid":"https://orcid.org/0000-0003-3307-9723"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Tinne Tuytelaars","raw_affiliation_strings":["KU Leuven University,Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KU Leuven University,Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014055174","display_name":"Johan Wagemans","orcid":"https://orcid.org/0000-0002-7970-1541"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Johan Wagemans","raw_affiliation_strings":["KU Leuven University,Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KU Leuven University,Belgium","institution_ids":["https://openalex.org/I99464096"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99464096"],"apc_list":null,"apc_paid":null,"fwci":2.3075,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.89328225,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"7815","last_page":"7824"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.994700014591217,"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":0.994700014591217,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9394000172615051,"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/T11165","display_name":"Image and Video Quality Assessment","score":0.9215999841690063,"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/charm","display_name":"Charm (quantum number)","score":0.7120141983032227},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5764274001121521},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4481564462184906},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.407815158367157},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3789646625518799},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.33624935150146484},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.21944072842597961},{"id":"https://openalex.org/keywords/particle-physics","display_name":"Particle physics","score":0.1253969669342041}],"concepts":[{"id":"https://openalex.org/C2781339351","wikidata":"https://www.wikidata.org/wiki/Q2639620","display_name":"Charm (quantum number)","level":2,"score":0.7120141983032227},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5764274001121521},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4481564462184906},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.407815158367157},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3789646625518799},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.33624935150146484},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.21944072842597961},{"id":"https://openalex.org/C109214941","wikidata":"https://www.wikidata.org/wiki/Q18334","display_name":"Particle physics","level":1,"score":0.1253969669342041}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cvpr52734.2025.00732","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00732","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},{"id":"pmh:oai:lirias2repo.kuleuven.be:20.500.12942/780163","is_oa":true,"landing_page_url":"https://lirias.kuleuven.be/handle/20.500.12942/780163","pdf_url":"https://lirias.kuleuven.be/retrieve/4e41d1f8-b4e2-4362-8274-4053f7c7d7f8","source":{"id":"https://openalex.org/S7407055369","display_name":"Lirias","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"2025 Conference on Computer Vision and Pattern Recognition-CVPR-Annual, TN, Nashville, 10-17 June 2025","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:lirias2repo.kuleuven.be:20.500.12942/780163","is_oa":true,"landing_page_url":"https://lirias.kuleuven.be/handle/20.500.12942/780163","pdf_url":"https://lirias.kuleuven.be/retrieve/4e41d1f8-b4e2-4362-8274-4053f7c7d7f8","source":{"id":"https://openalex.org/S7407055369","display_name":"Lirias","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"2025 Conference on Computer Vision and Pattern Recognition-CVPR-Annual, TN, Nashville, 10-17 June 2025","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.44999998807907104}],"awards":[{"id":"https://openalex.org/G5556518555","display_name":"The Art of Perception: Empowering Neural Networks to See Beauty Like Humans","funder_award_id":"1159925N","funder_id":"https://openalex.org/F4320321730","funder_display_name":"Fonds Wetenschappelijk Onderzoek"},{"id":"https://openalex.org/G7918671780","display_name":null,"funder_award_id":"101053925","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321730","display_name":"Fonds Wetenschappelijk Onderzoek","ror":"https://ror.org/03qtxy027"},{"id":"https://openalex.org/F4320327336","display_name":"Vlaamse regering","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413147156.pdf","grobid_xml":"https://content.openalex.org/works/W4413147156.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","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":{"The":[0],"capacity":[1],"of":[2],"Vision":[3],"transformers":[4],"(ViTs)":[5],"to":[6,93,111,132,151],"handle":[7],"variable-sized":[8],"inputs":[9],"is":[10,91],"often":[11],"constrained":[12],"by":[13],"computational":[14,36],"complexity":[15],"and":[16,65,99,108,118,146,160],"batch":[17],"processing":[18],"limitations.":[19],"Consequently,":[20],"ViTs":[21,85,98],"are":[22,163],"typically":[23],"trained":[24],"on":[25,142],"small,":[26],"fixed-size":[27,81],"images":[28],"obtained":[29],"through":[30],"downscaling":[31,77],"or":[32,127],"cropping.":[33],"While":[34],"reducing":[35],"burden,":[37],"these":[38],"methods":[39],"result":[40],"in":[41,73],"significant":[42,139],"information":[43,67],"loss,":[44],"negatively":[45],"affecting":[46],"tasks":[47],"like":[48],"image":[49,121,144],"aesthetic":[50,122,145],"assessment.":[51,123],"We":[52,124],"introduce":[53],"Charm,":[54],"a":[55,155],"novel":[56],"tokenization":[57],"approach":[58],"that":[59],"preserves":[60],"Composition,":[61],"High-resolution,":[62],"Aspect":[63],"Ratio,":[64],"Multi-scale":[66],"simultaneously.":[68],"Charm":[69,90,114],"prioritizes":[70],"high-resolution":[71],"details":[72],"specific":[74],"regions":[75],"while":[76,86],"others,":[78],"enabling":[79],"shorter":[80],"input":[82,107,112],"sequences":[83],"for":[84,120],"incorporating":[87],"essential":[88],"information.":[89,135],"designed":[92],"be":[94],"compatible":[95],"with":[96],"pre-trained":[97,161],"their":[100],"learned":[101],"positional":[102],"embeddings.":[103],"By":[104],"providing":[105],"multiscale":[106],"introducing":[109],"variety":[110],"tokens,":[113],"improves":[115],"ViT":[116,157],"performance":[117,140],"generalizability":[119],"avoid":[125],"cropping":[126],"changing":[128],"the":[129],"aspect":[130],"ratio":[131],"further":[133],"preserve":[134],"Extensive":[136],"experiments":[137],"demonstrate":[138],"improvements":[141],"various":[143],"quality":[147],"assessment":[148],"datasets":[149],"(up":[150],"8.1":[152],"%)":[153],"using":[154],"lightweight":[156],"backbone.":[158],"Code":[159],"models":[162],"available":[164],"at":[165],"https://github.com/FBehrad/Charm.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-29T07:29:34.045763","created_date":"2025-10-10T00:00:00"}