{"id":"https://openalex.org/W4415538717","doi":"https://doi.org/10.1145/3746027.3755840","title":"CADQ: Attribute-Consistent Face Cartoonization with Cross-modal Aligned and Deformable Quantization","display_name":"CADQ: Attribute-Consistent Face Cartoonization with Cross-modal Aligned and Deformable Quantization","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538717","doi":"https://doi.org/10.1145/3746027.3755840"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755840","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755840","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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/A5005017325","display_name":"Yongjie Hu","orcid":null},"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":"Yongjie Hu","raw_affiliation_strings":["Xidian University, Xi'an, China"],"raw_orcid":"https://orcid.org/0009-0003-8554-3177","affiliations":[{"raw_affiliation_string":"Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yifan Jiang","orcid":"https://orcid.org/0009-0008-6267-7187"},"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":"Yifan Jiang","raw_affiliation_strings":["Xidian University, Xi'an, China"],"raw_orcid":"https://orcid.org/0009-0008-6267-7187","affiliations":[{"raw_affiliation_string":"Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100780892","display_name":"Ziyun Li","orcid":"https://orcid.org/0000-0003-4286-9030"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Ziyun Li","raw_affiliation_strings":["KTH Royal Institute of Technology, Stockholm, Sweden"],"raw_orcid":"https://orcid.org/0000-0003-4286-9030","affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101652488","display_name":"Fei Gao","orcid":"https://orcid.org/0000-0002-8714-0975"},"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":"Fei Gao","raw_affiliation_strings":["Xidian University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-8714-0975","affiliations":[{"raw_affiliation_string":"Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033008105","display_name":"Henrik Bostr\u00f6m","orcid":"https://orcid.org/0000-0001-8382-0300"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Henrik Bostr\u00f6m","raw_affiliation_strings":["KTH Royal Institute of Technology, Stockholm, Sweden"],"raw_orcid":"https://orcid.org/0000-0001-8382-0300","affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100690630","display_name":"Nannan Wang","orcid":"https://orcid.org/0000-0003-1435-489X"},"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":"Nannan Wang","raw_affiliation_strings":["Xidian University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0003-1435-489X","affiliations":[{"raw_affiliation_string":"Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]}],"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":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10681","last_page":"10689"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9998000264167786,"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/T11448","display_name":"Face recognition and analysis","score":0.9998000264167786,"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":0.9975000023841858,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9966999888420105,"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/geometric-transformation","display_name":"Geometric transformation","score":0.6435999870300293},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.5496000051498413},{"id":"https://openalex.org/keywords/codebook","display_name":"Codebook","score":0.532800018787384},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.49410000443458557},{"id":"https://openalex.org/keywords/active-appearance-model","display_name":"Active appearance model","score":0.4027000069618225},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3984000086784363},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.3970000147819519},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.38029998540878296},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.37619999051094055}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7384999990463257},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7203999757766724},{"id":"https://openalex.org/C56435381","wikidata":"https://www.wikidata.org/wiki/Q1196371","display_name":"Geometric transformation","level":3,"score":0.6435999870300293},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.5496000051498413},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.532800018787384},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5037999749183655},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.49410000443458557},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.4027000069618225},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3984000086784363},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.3970000147819519},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.38029998540878296},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.37619999051094055},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3621000051498413},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.36090001463890076},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.3237000107765198},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3046000003814697},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.29510000348091125},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.28790000081062317},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2678000032901764},{"id":"https://openalex.org/C126795593","wikidata":"https://www.wikidata.org/wiki/Q7333813","display_name":"Rigid transformation","level":2,"score":0.2632000148296356}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755840","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755840","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2603777577","https://openalex.org/W2798729263","https://openalex.org/W2959891120","https://openalex.org/W2962793481","https://openalex.org/W2998700848","https://openalex.org/W3034491749","https://openalex.org/W3035524453","https://openalex.org/W3180355996","https://openalex.org/W3204682594","https://openalex.org/W4281253515","https://openalex.org/W4312881242","https://openalex.org/W4313029666","https://openalex.org/W4386071613","https://openalex.org/W4402667886"],"related_works":[],"abstract_inverted_index":{"Face":[0],"cartoonization":[1,49],"remains":[2],"a":[3,97],"challenging":[4],"task":[5],"due":[6],"to":[7,31,119,152],"significant":[8],"geometric":[9,122],"deformations":[10],"between":[11,85],"facial":[12,48,66,133],"photos":[13,134],"and":[14,55,72,89],"cartoons,":[15],"as":[16,18],"well":[17],"the":[19,106,128,146],"absence":[20],"of":[21,156],"paired":[22],"training":[23],"data":[24],"for":[25,68],"supervised":[26],"learning.":[27],"Existing":[28],"methods":[29],"struggle":[30],"generate":[32],"high-quality":[33,136],"cartoonized":[34],"avatars":[35],"with":[36,65,100,138],"attribute":[37,139],"consistency.":[38],"To":[39],"address":[40],"this":[41,43],"challenge,":[42],"paper":[44],"proposes":[45],"an":[46],"unsupervised":[47,153],"method":[50,130,147],"based":[51,115],"on":[52,116],"cross-domain":[53,121,154],"aligned":[54],"deformable":[56,98],"vector":[57],"quantization":[58],"(CADQ).":[59],"Firstly,":[60],"we":[61],"construct":[62],"textual":[63],"descriptions":[64],"attributes":[67],"both":[69],"photo":[70],"datasets":[71],"cartoon":[73,112],"collections.":[74],"Attribute":[75],"consistency":[76],"during":[77,105],"transformation":[78,107],"is":[79,103],"enforced":[80],"through":[81],"individually":[82],"contrastive":[83],"learning":[84],"image-text":[86],"cross-modal":[87],"features":[88,118],"globally":[90],"distribution":[91],"alignment":[92],"across":[93],"photo-cartoon":[94],"domains.":[95],"Secondly,":[96],"Transformer":[99],"dual":[101],"attention":[102],"introduced":[104],"process,":[108],"which":[109],"queries":[110],"corresponding":[111],"codebook":[113],"entries":[114],"image":[117],"simulate":[120],"deformations.":[123],"Experimental":[124],"results":[125],"demonstrate":[126],"that":[127],"proposed":[129],"can":[131,148],"convert":[132],"into":[135],"cartoons":[137],"consistency,":[140],"outperforming":[141],"existing":[142],"state-of-the-art":[143],"approaches.":[144],"Furthermore,":[145],"be":[149],"effectively":[150],"extended":[151],"generation":[155],"other":[157],"artistic":[158],"portrait":[159],"styles,":[160],"achieving":[161],"superior":[162],"or":[163],"highly":[164],"competitive":[165],"performance.":[166],"Our":[167],"code":[168],"has":[169],"been":[170],"released":[171],"at:":[172],"https://github.com/IIP-Lab-XDU/CADQ.":[173]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}