{"id":"https://openalex.org/W4361791079","doi":"https://doi.org/10.1145/3577530.3577550","title":"Cross-Modal Relation and Sketch Prototype Learning for Zero-Shot Sketch-Based Image Retrieval","display_name":"Cross-Modal Relation and Sketch Prototype Learning for Zero-Shot Sketch-Based Image Retrieval","publication_year":2022,"publication_date":"2022-12-09","ids":{"openalex":"https://openalex.org/W4361791079","doi":"https://doi.org/10.1145/3577530.3577550"},"language":"en","primary_location":{"id":"doi:10.1145/3577530.3577550","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3577530.3577550","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 6th International Conference on Computer Science and Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","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/A5051036873","display_name":"Yuanping Song","orcid":"https://orcid.org/0000-0002-7296-3717"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuanping Song","raw_affiliation_strings":["School of Software Engineering, University Of Science And Technology Of China, China"],"affiliations":[{"raw_affiliation_string":"School of Software Engineering, University Of Science And Technology Of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046340187","display_name":"Yanwei Yu","orcid":"https://orcid.org/0000-0002-3307-8846"},"institutions":[{"id":"https://openalex.org/I308837","display_name":"Suzhou University of Science and Technology","ror":"https://ror.org/04en8wb91","country_code":"CN","type":"education","lineage":["https://openalex.org/I308837"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanwei Yu","raw_affiliation_strings":["School of Software Engineering, Suzhou Institute for Advanced Research, University Of Science And Technology Of China, China"],"affiliations":[{"raw_affiliation_string":"School of Software Engineering, Suzhou Institute for Advanced Research, University Of Science And Technology Of China, China","institution_ids":["https://openalex.org/I308837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063397335","display_name":"Hao Tang","orcid":"https://orcid.org/0000-0002-5135-6344"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Tang","raw_affiliation_strings":["School of Software Engineering, University Of Science And Technology Of China, China"],"affiliations":[{"raw_affiliation_string":"School of Software Engineering, University Of Science And Technology Of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052151300","display_name":"Junyuan Guo","orcid":"https://orcid.org/0000-0003-1833-0692"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junyuan Guo","raw_affiliation_strings":["School of Software Engineering, University Of Science And Technology Of China, China"],"affiliations":[{"raw_affiliation_string":"School of Software Engineering, University Of Science And Technology Of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067092388","display_name":"Yibo Wang","orcid":"https://orcid.org/0000-0001-5636-4485"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yibo Wang","raw_affiliation_strings":["School of Software Engineering, University Of Science And Technology Of China, China"],"affiliations":[{"raw_affiliation_string":"School of Software Engineering, University Of Science And Technology Of China, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5051036873"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.1006,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.42333209,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"121","last_page":"128"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9995999932289124,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9995999932289124,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.996999979019165,"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":0.9962999820709229,"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":0.8517181873321533},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7078731060028076},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6251283884048462},{"id":"https://openalex.org/keywords/sketch-recognition","display_name":"Sketch recognition","score":0.6185660362243652},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.556178092956543},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.541476309299469},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5068591237068176},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48978710174560547},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4674715995788574},{"id":"https://openalex.org/keywords/cross-entropy","display_name":"Cross entropy","score":0.41234320402145386},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.35797402262687683},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35394924879074097},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.26220136880874634}],"concepts":[{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.8517181873321533},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7078731060028076},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6251283884048462},{"id":"https://openalex.org/C132900626","wikidata":"https://www.wikidata.org/wiki/Q7534733","display_name":"Sketch recognition","level":4,"score":0.6185660362243652},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.556178092956543},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.541476309299469},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5068591237068176},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48978710174560547},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4674715995788574},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.41234320402145386},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.35797402262687683},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35394924879074097},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26220136880874634},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3577530.3577550","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3577530.3577550","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 6th International Conference on Computer Science and Artificial Intelligence","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":26,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1974647172","https://openalex.org/W2108598243","https://openalex.org/W2466618734","https://openalex.org/W2603445054","https://openalex.org/W2885402090","https://openalex.org/W2891409152","https://openalex.org/W2895347732","https://openalex.org/W2962898354","https://openalex.org/W2962945761","https://openalex.org/W2962990451","https://openalex.org/W2963988212","https://openalex.org/W2964271799","https://openalex.org/W2988772405","https://openalex.org/W2991234496","https://openalex.org/W3034106423","https://openalex.org/W3034603197","https://openalex.org/W3035705029","https://openalex.org/W3085694362","https://openalex.org/W3093048820","https://openalex.org/W3096609285","https://openalex.org/W3137228985","https://openalex.org/W3174320978","https://openalex.org/W3183887783","https://openalex.org/W4226379819","https://openalex.org/W4239025696"],"related_works":["https://openalex.org/W2294900353","https://openalex.org/W2151314278","https://openalex.org/W2411243951","https://openalex.org/W1971224820","https://openalex.org/W13629514","https://openalex.org/W2963977451","https://openalex.org/W2098836165","https://openalex.org/W1976890290","https://openalex.org/W1573697454","https://openalex.org/W2966897482"],"abstract_inverted_index":{"Zero-Shot":[0],"Sketch-Based":[1],"Image":[2],"Retrieval":[3],"(ZS-SBIR)":[4],"is":[5,83,116],"an":[6],"innovative":[7],"cross-modal":[8,88],"task":[9],"that":[10,137],"utilizes":[11],"a":[12,30,61,78,111],"sketch":[13,120,129],"to":[14,44,85,98,105,118,122,142],"retrieve":[15],"corresponding":[16],"images":[17,54,91],"in":[18,128,146],"the":[19,49,71,87,107,124,143],"zero-shot":[20],"learning":[21],"scene.":[22],"At":[23],"present,":[24],"most":[25],"algorithms":[26,145],"treat":[27],"ZS-SBIR":[28,69],"as":[29],"typical":[31],"image":[32],"classification":[33],"problem,":[34],"using":[35],"image-level":[36],"features":[37],"with":[38,94],"triplet":[39],"or":[40],"cross":[41],"entropy":[42],"loss":[43],"achieve":[45],"retrieval,":[46],"while":[47],"ignore":[48],"correspondence":[50],"between":[51,90],"sketches":[52,93],"and":[53,92,149],"on":[55],"local":[56,79],"features.":[57],"Therefore,":[58],"we":[59],"propose":[60],"new":[62],"Local":[63],"Feature":[64],"Contrastive":[65],"Network":[66],"(LFCN)":[67],"for":[68],"from":[70,102],"perspective":[72],"of":[73,134],"contrastive":[74,81],"learning.":[75],"More":[76],"specifically,":[77],"feature":[80,112],"method":[82,139],"proposed":[84],"establish":[86],"relationships":[89],"creatively":[95],"applying":[96],"transformers":[97],"extract":[99],"similarity":[100],"representation":[101],"sketch-image":[103],"pairs":[104],"narrow":[106],"domain":[108],"gap.":[109],"Furthermore,":[110],"prototype":[113],"memory":[114],"bank":[115],"designed":[117],"learn":[119],"prototypes":[121],"address":[123],"in-class":[125],"diversity":[126],"problem":[127],"domain.":[130],"A":[131],"large":[132],"number":[133],"experiments":[135],"show":[136],"our":[138],"notably":[140],"superior":[141],"state-of-the-art":[144],"both":[147],"TU-Berlin":[148],"Sketchy":[150],"datasets.":[151]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}