{"id":"https://openalex.org/W7126016292","doi":"https://doi.org/10.26599/cvm.2025.9450456","title":"Sketchformer++: A Hierarchical Transformer Architecture for Vector Sketch Representation","display_name":"Sketchformer++: A Hierarchical Transformer Architecture for Vector Sketch Representation","publication_year":2026,"publication_date":"2026-01-29","ids":{"openalex":"https://openalex.org/W7126016292","doi":"https://doi.org/10.26599/cvm.2025.9450456"},"language":null,"primary_location":{"id":"doi:10.26599/cvm.2025.9450456","is_oa":true,"landing_page_url":"https://doi.org/10.26599/cvm.2025.9450456","pdf_url":null,"source":{"id":"https://openalex.org/S2487656537","display_name":"Computational Visual Media","issn_l":"2096-0433","issn":["2096-0433","2096-0662"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Visual Media","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.26599/cvm.2025.9450456","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101774415","display_name":"Pengfei Xu","orcid":"https://orcid.org/0000-0003-4770-4374"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengfei Xu","raw_affiliation_strings":["College of Computer Science and Software Engineering, Shenzhen University,Shenzhen,China,518060"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University,Shenzhen,China,518060","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113155269","display_name":"Banhuai Ruan","orcid":null},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Banhuai Ruan","raw_affiliation_strings":["College of Computer Science and Software Engineering, Shenzhen University,Shenzhen,China,518060"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University,Shenzhen,China,518060","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008766810","display_name":"Youyi Zheng","orcid":"https://orcid.org/0000-0002-9120-9592"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Youyi Zheng","raw_affiliation_strings":["Zhejiang University,State Key Lab of CAD &#x0026; CG,Hangzhou,China,310058"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,State Key Lab of CAD &#x0026; CG,Hangzhou,China,310058","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124210791","display_name":"Hui Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Huang","raw_affiliation_strings":["College of Computer Science and Software Engineering, Shenzhen University,Shenzhen,China,518060"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University,Shenzhen,China,518060","institution_ids":["https://openalex.org/I180726961"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09423722,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"12","issue":"1","first_page":"173","last_page":"188"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10789","display_name":"Interactive and Immersive Displays","score":0.44769999384880066,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T10789","display_name":"Interactive and Immersive Displays","score":0.44769999384880066,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T11448","display_name":"Face recognition and analysis","score":0.19220000505447388,"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":0.027899999171495438,"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/sketch","display_name":"Sketch","score":0.9625999927520752},{"id":"https://openalex.org/keywords/sketch-recognition","display_name":"Sketch recognition","score":0.6687999963760376},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5771999955177307},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5494999885559082},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5447999835014343},{"id":"https://openalex.org/keywords/vector-graphics","display_name":"Vector graphics","score":0.45239999890327454},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4180999994277954},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.3928000032901764}],"concepts":[{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.9625999927520752},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7806000113487244},{"id":"https://openalex.org/C132900626","wikidata":"https://www.wikidata.org/wiki/Q7534733","display_name":"Sketch recognition","level":4,"score":0.6687999963760376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.616100013256073},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5771999955177307},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5494999885559082},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5447999835014343},{"id":"https://openalex.org/C59662460","wikidata":"https://www.wikidata.org/wiki/Q170130","display_name":"Vector graphics","level":3,"score":0.45239999890327454},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4180999994277954},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.3928000032901764},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3869999945163727},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.35839998722076416},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3456000089645386},{"id":"https://openalex.org/C77660652","wikidata":"https://www.wikidata.org/wiki/Q150971","display_name":"Computer graphics","level":2,"score":0.32120001316070557},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3188000023365021},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31690001487731934},{"id":"https://openalex.org/C118965365","wikidata":"https://www.wikidata.org/wiki/Q44528","display_name":"Euclidean vector","level":2,"score":0.3003999888896942},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.2759000062942505},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2750000059604645},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.26089999079704285}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.26599/cvm.2025.9450456","is_oa":true,"landing_page_url":"https://doi.org/10.26599/cvm.2025.9450456","pdf_url":null,"source":{"id":"https://openalex.org/S2487656537","display_name":"Computational Visual Media","issn_l":"2096-0433","issn":["2096-0433","2096-0662"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Visual Media","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.26599/cvm.2025.9450456","is_oa":true,"landing_page_url":"https://doi.org/10.26599/cvm.2025.9450456","pdf_url":null,"source":{"id":"https://openalex.org/S2487656537","display_name":"Computational Visual Media","issn_l":"2096-0433","issn":["2096-0433","2096-0662"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Visual Media","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2266531271","display_name":null,"funder_award_id":"62472287,62072316,62172363,U21B2023","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2765886049","display_name":null,"funder_award_id":"JCYJ20250604181519025","funder_id":"https://openalex.org/F4320316880","funder_display_name":"Natural Science Foundation of Shenzhen City"}],"funders":[{"id":"https://openalex.org/F4320316880","display_name":"Natural Science Foundation of Shenzhen City","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1981934656","https://openalex.org/W1983556963","https://openalex.org/W2053251013","https://openalex.org/W2064675550","https://openalex.org/W2112796928","https://openalex.org/W2128543433","https://openalex.org/W2143668817","https://openalex.org/W2466618734","https://openalex.org/W2493181180","https://openalex.org/W2560722161","https://openalex.org/W2787091153","https://openalex.org/W2885106698","https://openalex.org/W2899102889","https://openalex.org/W2913618226","https://openalex.org/W2962721615","https://openalex.org/W2979750740","https://openalex.org/W2983439719","https://openalex.org/W2998660469","https://openalex.org/W3004246880","https://openalex.org/W3011295267","https://openalex.org/W3034832575","https://openalex.org/W3034962518","https://openalex.org/W3035035925","https://openalex.org/W3045735302","https://openalex.org/W3087797123","https://openalex.org/W3150584131","https://openalex.org/W3181089721","https://openalex.org/W3187403570","https://openalex.org/W3194134402","https://openalex.org/W4225158858","https://openalex.org/W4226106508","https://openalex.org/W4286611322","https://openalex.org/W4316660506","https://openalex.org/W4382318892","https://openalex.org/W4385731955","https://openalex.org/W4386076124"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,42,71,76],"rising":[2],"ubiquity":[3],"of":[4,18,45,81,94,129],"digital":[5],"touch":[6],"devices":[7],"and":[8,26,62,118,124],"sketch-based":[9],"interfaces,":[10],"freehand":[11],"sketching":[12],"has":[13],"become":[14],"an":[15],"essential":[16],"mode":[17],"visual":[19],"communication.":[20],"Nevertheless,":[21],"interpreting":[22],"these":[23],"often":[24],"ambiguous":[25],"sparse":[27],"sketches":[28,82],"poses":[29],"challenges":[30],"for":[31,41],"computers.":[32],"This":[33],"paper":[34],"presents":[35],"Sketchformer++,":[36],"a":[37,50,54,127],"hierarchical":[38],"transformer":[39],"architecture":[40],"neural":[43,92],"representation":[44],"vector":[46,51],"sketches.":[47,95],"It":[48],"treats":[49],"sketch":[52,58,77,111,113,115,119,130],"as":[53,126],"three-level":[55],"structure,":[56],"at":[57,135],"level,":[59,61],"stroke":[60],"segment":[63],"level.":[64],"Three":[65],"self-attention":[66],"modules":[67],"are":[68,83],"adopted":[69],"in":[70,91,106],"network":[72],"architecture,":[73],"corresponding":[74],"to":[75,87,102],"hierarchy.":[78],"The":[79],"semantics":[80],"aggregated":[84],"from":[85],"local":[86],"global":[88],"levels,":[89],"resulting":[90],"representations":[93],"Extensive":[96],"experiments":[97],"show":[98],"that":[99],"Sketchformer++":[100],"helps":[101],"achieve":[103],"superior":[104],"performance":[105],"various":[107],"downstream":[108],"tasks,":[109],"including":[110],"reconstruction,":[112],"recog-nition,":[114],"semantic":[116],"segmentation,":[117],"retrieval,":[120],"demonstrating":[121],"its":[122],"robustness":[123],"effectiveness":[125],"means":[128],"representation.":[131],"Code":[132],"is":[133],"available":[134],"https://github.com/BHR7/SketchformerPlus.":[136]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-01-30T00:00:00"}
