{"id":"https://openalex.org/W4308915925","doi":"https://doi.org/10.1142/s0219691322500540","title":"WAD-CMSN: Wasserstein distance-based cross-modal semantic network for zero-shot sketch-based image retrieval","display_name":"WAD-CMSN: Wasserstein distance-based cross-modal semantic network for zero-shot sketch-based image retrieval","publication_year":2022,"publication_date":"2022-11-11","ids":{"openalex":"https://openalex.org/W4308915925","doi":"https://doi.org/10.1142/s0219691322500540"},"language":"en","primary_location":{"id":"doi:10.1142/s0219691322500540","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219691322500540","pdf_url":null,"source":{"id":"https://openalex.org/S56986848","display_name":"International Journal of Wavelets Multiresolution and Information Processing","issn_l":"0219-6913","issn":["0219-6913","1793-690X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Wavelets, Multiresolution and Information Processing","raw_type":"journal-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/A5079050408","display_name":"Guanglong Xu","orcid":"https://orcid.org/0000-0002-5367-7918"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanglong Xu","raw_affiliation_strings":["School of Economics and Finance, South China University of Technology, Guangzhou 510006, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Economics and Finance, South China University of Technology, Guangzhou 510006, P. R. China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082376167","display_name":"Zhensheng Hu","orcid":"https://orcid.org/0009-0009-7255-1518"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhensheng Hu","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-Sen University, Guangzhou 510006, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-Sen University, Guangzhou 510006, P. R. China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033196884","display_name":"Jia Cai","orcid":"https://orcid.org/0000-0001-8942-8668"},"institutions":[{"id":"https://openalex.org/I201459984","display_name":"Guangdong University Of Finances and Economics","ror":"https://ror.org/0459pv085","country_code":"CN","type":"education","lineage":["https://openalex.org/I201459984"]},{"id":"https://openalex.org/I4210149618","display_name":"Guangdong University of Finance","ror":"https://ror.org/04grzdh47","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210149618"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jia Cai","raw_affiliation_strings":["School of Digital Economics, Guangdong University of Finance and Economics, Guangzhou 510320, P. R. China"],"raw_orcid":"https://orcid.org/0000-0001-8942-8668","affiliations":[{"raw_affiliation_string":"School of Digital Economics, Guangdong University of Finance and Economics, Guangzhou 510320, P. R. China","institution_ids":["https://openalex.org/I201459984","https://openalex.org/I4210149618"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5033196884"],"corresponding_institution_ids":["https://openalex.org/I201459984","https://openalex.org/I4210149618"],"apc_list":null,"apc_paid":null,"fwci":0.5102,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.6470642,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"21","issue":"02","first_page":null,"last_page":null},"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":0.9998000264167786,"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":0.9998000264167786,"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":0.9987999796867371,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.7940305471420288},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7687175869941711},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6009156107902527},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.5954116582870483},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5703233480453491},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4841938316822052},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4826369881629944},{"id":"https://openalex.org/keywords/semantic-matching","display_name":"Semantic matching","score":0.4371565282344818},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38730892539024353},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21549421548843384},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18071895837783813}],"concepts":[{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.7940305471420288},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7687175869941711},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6009156107902527},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.5954116582870483},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5703233480453491},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4841938316822052},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4826369881629944},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.4371565282344818},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38730892539024353},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21549421548843384},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18071895837783813},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0219691322500540","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219691322500540","pdf_url":null,"source":{"id":"https://openalex.org/S56986848","display_name":"International Journal of Wavelets Multiresolution and Information Processing","issn_l":"0219-6913","issn":["0219-6913","1793-690X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Wavelets, Multiresolution and Information Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6809843809","display_name":null,"funder_award_id":"12271111","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6972202030","display_name":null,"funder_award_id":"2022A1515011726","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G7011941881","display_name":null,"funder_award_id":"11871167","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1951304353","https://openalex.org/W1974647172","https://openalex.org/W2044913453","https://openalex.org/W2081580037","https://openalex.org/W2108598243","https://openalex.org/W2128543433","https://openalex.org/W2171061940","https://openalex.org/W2334493732","https://openalex.org/W2398118205","https://openalex.org/W2405223529","https://openalex.org/W2466618734","https://openalex.org/W2467281799","https://openalex.org/W2493181180","https://openalex.org/W2511925527","https://openalex.org/W2789667050","https://openalex.org/W2887567284","https://openalex.org/W2947711868","https://openalex.org/W3057906563","https://openalex.org/W3085694362","https://openalex.org/W3098623295","https://openalex.org/W3207288552"],"related_works":["https://openalex.org/W2617036512","https://openalex.org/W2016349419","https://openalex.org/W2543161807","https://openalex.org/W2420702882","https://openalex.org/W2321141263","https://openalex.org/W2159633528","https://openalex.org/W2164844972","https://openalex.org/W1998938004","https://openalex.org/W2157903613","https://openalex.org/W2119875513"],"abstract_inverted_index":{"Zero-shot":[0],"sketch-based":[1],"image":[2],"retrieval":[3],"(ZSSBIR)":[4],"aims":[5],"at":[6],"retrieving":[7],"natural":[8],"images":[9],"given":[10],"free":[11],"hand-drawn":[12],"sketches":[13],"that":[14],"may":[15,57],"not":[16,124],"appear":[17],"during":[18],"training.":[19],"Previous":[20],"approaches":[21],"used":[22],"semantic":[23,79,100,128],"aligned":[24],"sketch-image":[25],"pairs":[26],"or":[27],"utilized":[28],"memory":[29],"expensive":[30],"fusion":[31],"layer":[32],"for":[33,82],"projecting":[34],"the":[35,44,62,88,133,138,144,153,156],"visual":[36,89],"information":[37,90],"to":[38,96,118],"a":[39,75,97,111],"low-dimensional":[40,99],"subspace,":[41],"which":[42,122],"ignores":[43],"significant":[45],"heterogeneous":[46],"cross-domain":[47],"discrepancy":[48],"between":[49],"highly":[50],"abstract":[51],"sketch":[52],"and":[53,69,148],"relevant":[54],"image.":[55],"This":[56],"yield":[58],"poor":[59],"performance":[60],"in":[61,105],"training":[63,108],"phase.":[64],"To":[65],"tackle":[66],"this":[67,71],"issue":[68],"overcome":[70],"drawback,":[72],"we":[73],"propose":[74],"Wasserstein":[76,103],"distance-based":[77],"cross-modal":[78],"network":[80],"(WAD-CMSN)":[81],"ZSSBIR.":[83],"Specifically,":[84],"it":[85],"first":[86],"projects":[87],"of":[91,155],"each":[92],"branch":[93],"(sketch,":[94],"image)":[95],"common":[98],"subspace":[101],"via":[102],"distance":[104],"an":[106],"adversarial":[107],"manner.":[109],"Furthermore,":[110],"novel":[112],"identity":[113],"matching":[114],"loss":[115],"is":[116],"employed":[117],"select":[119],"useful":[120],"features,":[121],"can":[123],"only":[125],"capture":[126],"complete":[127],"knowledge,":[129],"but":[130],"also":[131],"alleviate":[132],"over-fitting":[134],"phenomenon":[135],"caused":[136],"by":[137],"WAD-CMSN":[139,158],"model.":[140],"Experimental":[141],"results":[142],"on":[143],"challenging":[145],"Sketchy":[146],"(Extended)":[147,150],"TU-Berlin":[149],"datasets":[151],"indicate":[152],"effectiveness":[154],"proposed":[157],"model":[159],"over":[160],"several":[161],"competitors.":[162]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}