{"id":"https://openalex.org/W4304098568","doi":"https://doi.org/10.1145/3503161.3547993","title":"Sketch Transformer: Asymmetrical Disentanglement Learning from Dynamic Synthesis","display_name":"Sketch Transformer: Asymmetrical Disentanglement Learning from Dynamic Synthesis","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304098568","doi":"https://doi.org/10.1145/3503161.3547993"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3547993","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3547993","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","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/A5073015477","display_name":"Cuiqun Chen","orcid":"https://orcid.org/0000-0002-4133-0028"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Cuiqun Chen","raw_affiliation_strings":["Wuhan University, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008999954","display_name":"Mang Ye","orcid":"https://orcid.org/0000-0003-3989-7655"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mang Ye","raw_affiliation_strings":["Wuhan University & Hubei Luojia Laboratory, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Wuhan University & Hubei Luojia Laboratory, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073550769","display_name":"Meibin Qi","orcid":"https://orcid.org/0000-0001-9074-211X"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meibin Qi","raw_affiliation_strings":["Hefei University of Technology, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060042752","display_name":"Bo Du","orcid":"https://orcid.org/0000-0002-0059-8458"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Du","raw_affiliation_strings":["Wuhan University & Hubei Luojia Laboratory, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Wuhan University & Hubei Luojia Laboratory, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5073015477"],"corresponding_institution_ids":["https://openalex.org/I37461747"],"apc_list":null,"apc_paid":null,"fwci":1.4933,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.88261178,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4012","last_page":"4020"},"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":0.9994999766349792,"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":0.9994999766349792,"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":0.9983999729156494,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9969000220298767,"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":0.9061417579650879},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.793092668056488},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6892514824867249},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5211160778999329},{"id":"https://openalex.org/keywords/sketch-recognition","display_name":"Sketch recognition","score":0.46748632192611694},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4111522138118744}],"concepts":[{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.9061417579650879},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.793092668056488},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6892514824867249},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5211160778999329},{"id":"https://openalex.org/C132900626","wikidata":"https://www.wikidata.org/wiki/Q7534733","display_name":"Sketch recognition","level":4,"score":0.46748632192611694},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4111522138118744},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"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/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3547993","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3547993","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W2054508433","https://openalex.org/W2153288431","https://openalex.org/W2466618734","https://openalex.org/W2467281799","https://openalex.org/W2475287302","https://openalex.org/W2493181180","https://openalex.org/W2511925527","https://openalex.org/W2603777577","https://openalex.org/W2685669664","https://openalex.org/W2746642387","https://openalex.org/W2776402438","https://openalex.org/W2781305742","https://openalex.org/W2789433008","https://openalex.org/W2883672875","https://openalex.org/W2895608766","https://openalex.org/W2896575354","https://openalex.org/W2898571185","https://openalex.org/W2903798738","https://openalex.org/W2912269676","https://openalex.org/W2948085278","https://openalex.org/W2964266708","https://openalex.org/W2981824749","https://openalex.org/W2996878574","https://openalex.org/W3024646777","https://openalex.org/W3034382172","https://openalex.org/W3034603197","https://openalex.org/W3035673257","https://openalex.org/W3042524218","https://openalex.org/W3094502228","https://openalex.org/W3115218903","https://openalex.org/W3128933491","https://openalex.org/W3163101577","https://openalex.org/W3176372702","https://openalex.org/W3176429308","https://openalex.org/W3177343422","https://openalex.org/W3186064588","https://openalex.org/W3204075450","https://openalex.org/W4214736485","https://openalex.org/W4214891830"],"related_works":["https://openalex.org/W2294900353","https://openalex.org/W2151314278","https://openalex.org/W2411243951","https://openalex.org/W1971224820","https://openalex.org/W4297491129","https://openalex.org/W2076631638","https://openalex.org/W3122847369","https://openalex.org/W3194387955","https://openalex.org/W3004250220","https://openalex.org/W3036435328"],"abstract_inverted_index":{"Sketch-photo":[0],"recognition":[1],"is":[2,29,97],"a":[3,67,141,159,163],"cross-modal":[4],"matching":[5],"problem":[6],"whose":[7],"query":[8],"sets":[9],"are":[10],"sketch":[11,113,123,145],"images":[12],"drawn":[13],"by":[14,85],"artists":[15],"or":[16],"amateurs.":[17],"Due":[18],"to":[19,31,44,81,99,126,153],"the":[20,25,77,101,111,116,122,150,155,172,179,198],"significant":[21],"modality":[22,83,124,147,152,170],"difference":[23],"between":[24],"two":[26],"modalities,":[27],"it":[28],"challenging":[30],"extract":[32],"discriminative":[33],"modality-shared":[34,87],"feature":[35],"representations.":[36],"Existing":[37],"works":[38],"focus":[39],"on":[40,186],"exploring":[41],"modality-invariant":[42],"features":[43,103],"discover":[45],"shared":[46],"embedding":[47],"space.":[48],"However,":[49],"they":[50],"discard":[51],"modality-specific":[52,90],"cues,":[53,118],"resulting":[54],"in":[55,76,158],"information":[56,88,136],"loss":[57],"and":[58,71,106,177,195],"diminished":[59],"discriminatory":[60],"power":[61],"of":[62,174],"features.":[63],"This":[64],"paper":[65],"proposes":[66],"novel":[68],"asymmetrical":[69,94,156],"disentanglement":[70,95,157],"dynamic":[72,142],"synthesis":[73],"learning":[74,166],"method":[75],"transformer":[78],"framework":[79],"(SketchTrans)":[80],"handle":[82],"discrepancy":[84],"combining":[86],"with":[89,135],"information.":[91],"Specifically,":[92],"an":[93],"scheme":[96],"introduced":[98],"decompose":[100],"photo":[102,127,151],"into":[104],"sketch-relevant":[105],"sketch-irrelevant":[107,117],"cues":[108],"while":[109],"preserving":[110],"original":[112],"structure.":[114],"Using":[115],"we":[119,139],"further":[120],"translate":[121],"component":[125],"representation":[128],"through":[129],"knowledge":[130],"transfer,":[131],"obtaining":[132],"cross-modality":[133,180],"representations":[134],"symmetry.":[137],"Moreover,":[138],"propose":[140],"updatable":[143],"auxiliary":[144,169],"(A-sketch)":[146],"generated":[148],"from":[149],"guide":[154],"single":[160],"framework.":[161],"Under":[162],"multi-modality":[164],"joint":[165],"framework,":[167],"this":[168],"increases":[171],"diversity":[173],"training":[175],"samples":[176],"narrows":[178],"gap.":[181],"We":[182],"conduct":[183],"extensive":[184],"experiments":[185],"three":[187],"fine-grained":[188],"sketch-based":[189],"retrieval":[190],"datasets,":[191],"i.e.,":[192],"PKU-Sketch,":[193],"QMUL-ChairV2,":[194],"QMUL-ShoeV2,":[196],"outperforming":[197],"state-of-the-arts":[199],"under":[200],"various":[201],"metrics.":[202]},"counts_by_year":[{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":6}],"updated_date":"2026-03-28T08:17:26.163206","created_date":"2025-10-10T00:00:00"}