{"id":"https://openalex.org/W6964041341","doi":"https://doi.org/10.2312/pg.20241309","title":"Modeling Sketches both Semantically and Structurally for Zero-Shot Sketch-Based Image Retrieval is Better","display_name":"Modeling Sketches both Semantically and Structurally for Zero-Shot Sketch-Based Image Retrieval is Better","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W6964041341","doi":"https://doi.org/10.2312/pg.20241309"},"language":"en","primary_location":{"id":"doi:10.2312/pg.20241309","is_oa":true,"landing_page_url":"https://doi.org/10.2312/pg.20241309","pdf_url":null,"source":{"id":"https://openalex.org/S7407052899","display_name":"Eurographics","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"ConferencePaper"},"type":"conference-paper","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.2312/pg.20241309","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jing, Jiansen","orcid":"https://orcid.org/0009-0005-8811-580X"},"institutions":[{"id":"https://openalex.org/I4210162190","display_name":"China University of Petroleum, East China","ror":"https://ror.org/05gbn2817","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210162190"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing, Jiansen","raw_affiliation_strings":["Qingdao Institute of Software, College of Computer Science and Technology, China University of Petroleum, East China: Qingdao, China, China"],"raw_orcid":"https://orcid.org/0009-0005-8811-580X","affiliations":[{"raw_affiliation_string":"Qingdao Institute of Software, College of Computer Science and Technology, China University of Petroleum, East China: Qingdao, China, China","institution_ids":["https://openalex.org/I4210162190"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Liu, Yujie","orcid":null},"institutions":[{"id":"https://openalex.org/I4210162190","display_name":"China University of Petroleum, East China","ror":"https://ror.org/05gbn2817","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210162190"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu, Yujie","raw_affiliation_strings":["CHINA UNIVERSITY OF PETROLEUM(EAST CHINA), China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CHINA UNIVERSITY OF PETROLEUM(EAST CHINA), China","institution_ids":["https://openalex.org/I4210162190"]}]},{"author_position":"middle","author":{"id":null,"display_name":"LI, MINGYUE","orcid":"https://orcid.org/0009-0008-5348-3129"},"institutions":[{"id":"https://openalex.org/I4210162190","display_name":"China University of Petroleum, East China","ror":"https://ror.org/05gbn2817","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210162190"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"LI, MINGYUE","raw_affiliation_strings":["China University of Petroleum (East China), China"],"raw_orcid":"https://orcid.org/0009-0008-5348-3129","affiliations":[{"raw_affiliation_string":"China University of Petroleum (East China), China","institution_ids":["https://openalex.org/I4210162190"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiao, Qian","orcid":null},"institutions":[{"id":"https://openalex.org/I4210162190","display_name":"China University of Petroleum, East China","ror":"https://ror.org/05gbn2817","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210162190"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao, Qian","raw_affiliation_strings":["China University of Petroleum (East China) , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China University of Petroleum (East China) , China","institution_ids":["https://openalex.org/I4210162190"]}]},{"author_position":"last","author":{"id":null,"display_name":"Chai, Shijie","orcid":"https://orcid.org/0009-0004-6795-405X"},"institutions":[{"id":"https://openalex.org/I4210162190","display_name":"China University of Petroleum, East China","ror":"https://ror.org/05gbn2817","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210162190"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chai, Shijie","raw_affiliation_strings":["China University of Petroleum (East China), China"],"raw_orcid":"https://orcid.org/0009-0004-6795-405X","affiliations":[{"raw_affiliation_string":"China University of Petroleum (East China), China","institution_ids":["https://openalex.org/I4210162190"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210162190"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.63017751,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10017","display_name":"Geology and Paleoclimatology Research","score":0.2533000111579895,"subfield":{"id":"https://openalex.org/subfields/1902","display_name":"Atmospheric Science"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10017","display_name":"Geology and Paleoclimatology Research","score":0.2533000111579895,"subfield":{"id":"https://openalex.org/subfields/1902","display_name":"Atmospheric Science"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10421","display_name":"Pleistocene-Era Hominins and Archaeology","score":0.0502999983727932,"subfield":{"id":"https://openalex.org/subfields/3314","display_name":"Anthropology"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10087","display_name":"Archaeology and ancient environmental studies","score":0.04780000075697899,"subfield":{"id":"https://openalex.org/subfields/1911","display_name":"Paleontology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/sketch","display_name":"Sketch","score":0.5630999803543091},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5060999989509583},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4772000014781952},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.44510000944137573},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.43720000982284546},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.42239999771118164},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.39739999175071716},{"id":"https://openalex.org/keywords/semantic-data-model","display_name":"Semantic data model","score":0.3959999978542328},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.39070001244544983},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.37139999866485596}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8176000118255615},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6011000275611877},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.5630999803543091},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5376999974250793},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5060999989509583},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4772000014781952},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44510000944137573},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.43720000982284546},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42239999771118164},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.41530001163482666},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.39739999175071716},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.3959999978542328},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.39070001244544983},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.37139999866485596},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3601999878883362},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.3528999984264374},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3336000144481659},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.3312999904155731},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.32850000262260437},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.3255000114440918},{"id":"https://openalex.org/C511149849","wikidata":"https://www.wikidata.org/wiki/Q7449051","display_name":"Semantic computing","level":3,"score":0.3249000012874603},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.3140000104904175},{"id":"https://openalex.org/C197914299","wikidata":"https://www.wikidata.org/wiki/Q18650","display_name":"Semantic memory","level":3,"score":0.30480000376701355},{"id":"https://openalex.org/C198942812","wikidata":"https://www.wikidata.org/wiki/Q496618","display_name":"Semantic property","level":2,"score":0.2978000044822693},{"id":"https://openalex.org/C85407183","wikidata":"https://www.wikidata.org/wiki/Q1045785","display_name":"Semantic network","level":2,"score":0.28369998931884766},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.2703999876976013},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2587999999523163},{"id":"https://openalex.org/C2777946921","wikidata":"https://www.wikidata.org/wiki/Q7449044","display_name":"Semantic analysis (machine learning)","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.2312/pg.20241309","is_oa":true,"landing_page_url":"https://doi.org/10.2312/pg.20241309","pdf_url":null,"source":{"id":"https://openalex.org/S7407052899","display_name":"Eurographics","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"ConferencePaper"}],"best_oa_location":{"id":"doi:10.2312/pg.20241309","is_oa":true,"landing_page_url":"https://doi.org/10.2312/pg.20241309","pdf_url":null,"source":{"id":"https://openalex.org/S7407052899","display_name":"Eurographics","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"ConferencePaper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Sketch,":[0],"as":[1,16],"a":[2,17,58,71,77,116],"representation":[3],"of":[4,43,104],"human":[5],"thought,":[6],"is":[7,14,28],"abstract":[8],"but":[9],"also":[10,174],"structured":[11],"because":[12],"it":[13,22],"presented":[15],"two-dimensional":[18],"image.":[19],"Therefore,":[20],"modeling":[21,180],"from":[23,181],"semantic":[24,37],"and":[25,30,56,76,93,123,152],"structural":[26],"perspectives":[27],"reasonable":[29],"effective.":[31],"In":[32],"this":[33],"paper,":[34],"for":[35],"the":[36,41,49,102,111,134,153,158,165,182],"capturing,":[38],"we":[39,82,109],"compare":[40],"performance":[42],"two":[44],"mainstream":[45],"pre-trained":[46],"models":[47],"on":[48,65,120,128,164,178],"Zero-Shot":[50],"Sketch-Based":[51],"Image":[52],"Retrieval":[53],"(ZS-SBIR)":[54],"task":[55],"propose":[57,83],"new":[59,159],"model,":[60],"Semantic":[61,78,94,138],"Net":[62,140],"(SNET),":[63],"based":[64,119,127],"Contrastive":[66],"Language-Image":[67],"Pre-training":[68],"(CLIP)":[69],"with":[70,101],"more":[72],"effective":[73],"fine-tuning":[74],"strategy":[75],"Preservation":[79],"Module.":[80],"Furthermore,":[81],"three":[84],"lightweight":[85],"modules,":[86],"Channels":[87],"Fusion":[88,91,96],"(CF),":[89],"Layers":[90],"(LF),":[92],"Structure":[95,139],"(SSF)":[97],"to":[98],"endow":[99],"SNET":[100,151],"ability":[103],"stronger":[105],"structure":[106],"capture.":[107],"Finally,":[108],"supervise":[110],"entire":[112],"training":[113],"process":[114],"by":[115],"classification":[117],"loss":[118,126],"contrastive":[121],"learning":[122],"bidirectional":[124],"triplet":[125],"cosine":[129],"distance":[130],"metric.":[131],"We":[132],"call":[133],"final":[135],"version":[136,155],"model":[137],"(SSNET).":[141],"The":[142,171],"quantitative":[143],"experimental":[144],"results":[145],"show":[146],"that":[147],"both":[148],"our":[149,176],"proposed":[150],"enhanced":[154],"SSNET":[156],"achieve":[157],"SOTA":[160],"(16%":[161],"retrieval":[162],"boost":[163],"most":[166],"difficult":[167],"QuickDraw":[168],"Ext":[169],"dataset).":[170],"visualization":[172],"experiments":[173],"prove":[175],"thinking":[177],"sketch":[179],"side.":[183]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}