{"id":"https://openalex.org/W4385731955","doi":"https://doi.org/10.1109/tip.2023.3302521","title":"Sketch-Segformer: Transformer-Based Segmentation for Figurative and Creative Sketches","display_name":"Sketch-Segformer: Transformer-Based Segmentation for Figurative and Creative Sketches","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4385731955","doi":"https://doi.org/10.1109/tip.2023.3302521","pmid":"https://pubmed.ncbi.nlm.nih.gov/37561619"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2023.3302521","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2023.3302521","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5103180744","display_name":"Yixiao Zheng","orcid":"https://orcid.org/0009-0000-0253-1938"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixiao Zheng","raw_affiliation_strings":["Pattern Recognition and Intelligent System Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","School of Artificial Intelligence, Pattern Recognition and Intelligent System Laboratory, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pattern Recognition and Intelligent System Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"School of Artificial Intelligence, Pattern Recognition and Intelligent System Laboratory, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048826896","display_name":"Jiyang Xie","orcid":"https://orcid.org/0000-0003-3659-9476"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiyang Xie","raw_affiliation_strings":["Pattern Recognition and Intelligent System Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","School of Artificial Intelligence, Pattern Recognition and Intelligent System Laboratory, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3659-9476","affiliations":[{"raw_affiliation_string":"Pattern Recognition and Intelligent System Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"School of Artificial Intelligence, Pattern Recognition and Intelligent System Laboratory, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085178555","display_name":"Aneeshan Sain","orcid":"https://orcid.org/0000-0001-7789-3060"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Aneeshan Sain","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, U.K","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046046128","display_name":"Yi-Zhe Song","orcid":"https://orcid.org/0000-0001-5908-3275"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yi-Zhe Song","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, U.K"],"raw_orcid":"https://orcid.org/0000-0001-5908-3275","affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, U.K","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039812471","display_name":"Zhanyu Ma","orcid":"https://orcid.org/0000-0003-2950-2488"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhanyu Ma","raw_affiliation_strings":["Pattern Recognition and Intelligent System Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","School of Artificial Intelligence, Pattern Recognition and Intelligent System Laboratory, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2950-2488","affiliations":[{"raw_affiliation_string":"Pattern Recognition and Intelligent System Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"School of Artificial Intelligence, Pattern Recognition and Intelligent System Laboratory, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.4349,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.92887316,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"32","issue":null,"first_page":"4595","last_page":"4609"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9972000122070312,"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":0.6723585724830627},{"id":"https://openalex.org/keywords/literal-and-figurative-language","display_name":"Literal and figurative language","score":0.67218416929245},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6200926899909973},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6169493198394775},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5917506217956543},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5889306664466858},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5201531052589417},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.502619743347168},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.43396836519241333},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38363882899284363},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14970353245735168},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13923650979995728},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.08620953559875488}],"concepts":[{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.6723585724830627},{"id":"https://openalex.org/C46182478","wikidata":"https://www.wikidata.org/wiki/Q7363315","display_name":"Literal and figurative language","level":2,"score":0.67218416929245},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6200926899909973},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6169493198394775},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5917506217956543},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5889306664466858},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5201531052589417},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.502619743347168},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.43396836519241333},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38363882899284363},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14970353245735168},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13923650979995728},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.08620953559875488},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2023.3302521","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2023.3302521","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:37561619","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37561619","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6899999976158142}],"awards":[{"id":"https://openalex.org/G1262852264","display_name":null,"funder_award_id":"2023QNTD02","funder_id":"https://openalex.org/F4320321470","funder_display_name":"Beijing University of Posts and Telecommunications"},{"id":"https://openalex.org/G172479822","display_name":null,"funder_award_id":"62225601","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3848188706","display_name":null,"funder_award_id":"U19B2036","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7697810044","display_name":null,"funder_award_id":"Z200002","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321470","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59"},{"id":"https://openalex.org/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":77,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1836465849","https://openalex.org/W1895722194","https://openalex.org/W1973212109","https://openalex.org/W1981934656","https://openalex.org/W2079442992","https://openalex.org/W2123557958","https://openalex.org/W2145023731","https://openalex.org/W2194775991","https://openalex.org/W2493181180","https://openalex.org/W2496271548","https://openalex.org/W2606712314","https://openalex.org/W2748769660","https://openalex.org/W2885106698","https://openalex.org/W2895687296","https://openalex.org/W2899102889","https://openalex.org/W2901731046","https://openalex.org/W2913618226","https://openalex.org/W2919115771","https://openalex.org/W2962945761","https://openalex.org/W2963703957","https://openalex.org/W2978100479","https://openalex.org/W2978724125","https://openalex.org/W2983439719","https://openalex.org/W2999249053","https://openalex.org/W3004246880","https://openalex.org/W3011295267","https://openalex.org/W3033210410","https://openalex.org/W3034885317","https://openalex.org/W3035035925","https://openalex.org/W3035058753","https://openalex.org/W3036571173","https://openalex.org/W3048306538","https://openalex.org/W3092054443","https://openalex.org/W3096399879","https://openalex.org/W3096609285","https://openalex.org/W3101364353","https://openalex.org/W3102451174","https://openalex.org/W3111535274","https://openalex.org/W3138516171","https://openalex.org/W3153465022","https://openalex.org/W3166091781","https://openalex.org/W3187403570","https://openalex.org/W3189597199","https://openalex.org/W4210400735","https://openalex.org/W4214582496","https://openalex.org/W4214614183","https://openalex.org/W4214918554","https://openalex.org/W4220726865","https://openalex.org/W4226004329","https://openalex.org/W4226106508","https://openalex.org/W4226266780","https://openalex.org/W4230981054","https://openalex.org/W4281676683","https://openalex.org/W4287126465","https://openalex.org/W4298395628","https://openalex.org/W4300860215","https://openalex.org/W4312769131","https://openalex.org/W4312915164","https://openalex.org/W4316660506","https://openalex.org/W4385245566","https://openalex.org/W6638667902","https://openalex.org/W6736562241","https://openalex.org/W6739901393","https://openalex.org/W6763367864","https://openalex.org/W6768933624","https://openalex.org/W6772581422","https://openalex.org/W6774454812","https://openalex.org/W6778485988","https://openalex.org/W6779248606","https://openalex.org/W6780208309","https://openalex.org/W6780975210","https://openalex.org/W6783884108","https://openalex.org/W6785332027","https://openalex.org/W6796752866","https://openalex.org/W6799531426","https://openalex.org/W6810767136"],"related_works":["https://openalex.org/W2378994405","https://openalex.org/W2385974820","https://openalex.org/W2373478030","https://openalex.org/W2378679551","https://openalex.org/W3149739944","https://openalex.org/W2392363776","https://openalex.org/W2063051341","https://openalex.org/W2591066345","https://openalex.org/W1494563618","https://openalex.org/W1522196789"],"abstract_inverted_index":{"Sketch":[0,11],"is":[1,89,167,192],"a":[2,18,54,72,110,123],"well-researched":[3],"topic":[4],"in":[5,14,64],"the":[6,51,60,83,121,176,246],"vision":[7],"community":[8],"by":[9],"now.":[10],"semantic":[12,128],"segmentation":[13,42,105,129],"particular,":[15,141],"serves":[16],"as":[17,53,109,134,179,181,205],"fundamental":[19],"step":[20],"towards":[21],"finer-level":[22],"sketch":[23,101,127,160,178,232],"interpretation.":[24],"Recent":[25],"works":[26],"use":[27],"various":[28],"means":[29],"of":[30,74,100,112,115,146,230,248],"extracting":[31],"discriminative":[32],"features":[33],"from":[34,175],"sketches":[35,133,203,215],"and":[36,103,237,245],"have":[37],"achieved":[38],"considerable":[39],"improvements":[40],"on":[41,70,200,213],"accuracy.":[43],"Common":[44],"approaches":[45],"for":[46,82,126,227],"this":[47,79],"include":[48],"attending":[49],"to":[50,92,196,220],"sketch-image":[52],"whole,":[55],"its":[56],"stroke-level":[57,183],"representation":[58],"or":[59,161],"sequence":[61],"information":[62,91],"embedded":[63],"it.":[65],"However,":[66],"they":[67],"mostly":[68],"focus":[69],"only":[71,194],"part":[73],"such":[75,113],"multi-facet":[76,231],"information.":[77,117,184,233],"In":[78,140],"paper,":[80],"we":[81,119],"first":[84],"time":[85],"demonstrate":[86],"that":[87,104,130,152,188,216],"there":[88],"complementary":[90],"be":[93],"explored":[94],"across":[95],"all":[96],"these":[97],"three":[98],"facets":[99],"data,":[102],"performance":[106,199],"consequently":[107],"benefits":[108],"result":[111],"exploration":[114],"sketch-specific":[116,190],"Specifically,":[118],"propose":[120],"Sketch-Segformer,":[122],"transformer-based":[124],"framework":[125],"inherently":[131],"treats":[132],"stroke":[135],"sequences":[136],"other":[137],"than":[138],"pixel-maps.":[139],"Sketch-Segformer":[142],"introduces":[143],"two":[144],"types":[145],"self-attention":[147],"modules":[148],"having":[149],"similar":[150],"structures":[151],"work":[153],"with":[154,171],"different":[155],"receptive":[156],"fields":[157],"(i.e.,":[158],"whole":[159],"individual":[162],"stroke).":[163],"The":[164],"order":[165],"embedding":[166],"then":[168],"further":[169,240],"synergized":[170],"spatial":[172],"embeddings":[173],"learned":[174],"entire":[177],"well":[180,212],"localized":[182],"Extensive":[185],"experiments":[186],"show":[187],"our":[189,228,242],"design":[191,243],"not":[193,218],"able":[195],"obtain":[197],"state-of-the-art":[198],"traditional":[201],"figurative":[202],"(such":[204],"SPG,":[206],"SketchSeg-150K":[207],"datasets),":[208],"but":[209],"also":[210],"performs":[211],"creative":[214],"do":[217],"conform":[219],"conventional":[221],"object":[222],"semantics":[223],"(CreativeSketch":[224],"dataset)":[225],"thanks":[226],"usage":[229],"Ablation":[234],"studies,":[235],"visualizations,":[236],"invariance":[238],"tests":[239],"justifies":[241],"choice":[244],"effectiveness":[247],"Sketch-Segformer.":[249],"Codes":[250],"are":[251],"available":[252],"at":[253],"https://github.com/PRIS-CV/Sketch-SF.":[254]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}