{"id":"https://openalex.org/W7124448353","doi":"https://doi.org/10.1109/tmm.2026.3654420","title":"COP: CrOss-View Attention Prompt for Zero-Shot Sketch-Based Image Retrieval","display_name":"COP: CrOss-View Attention Prompt for Zero-Shot Sketch-Based Image Retrieval","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7124448353","doi":"https://doi.org/10.1109/tmm.2026.3654420"},"language":null,"primary_location":{"id":"doi:10.1109/tmm.2026.3654420","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3654420","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","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/A5103108979","display_name":"Jiahao Zheng","orcid":"https://orcid.org/0000-0001-5169-3183"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jiahao Zheng","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Hong Kong, SAR, China"],"raw_orcid":"https://orcid.org/0000-0001-5169-3183","affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101969498","display_name":"Yu Tang","orcid":"https://orcid.org/0009-0001-4914-1440"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Tang","raw_affiliation_strings":["Shanghai University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0001-4914-1440","affiliations":[{"raw_affiliation_string":"Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047499718","display_name":"Yongcan Luo","orcid":"https://orcid.org/0009-0002-8957-1020"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yongcan Luo","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Hong Kong, SAR, China"],"raw_orcid":"https://orcid.org/0009-0002-8957-1020","affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122906063","display_name":"Ning Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ning Chen","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Hong Kong, SAR, China"],"raw_orcid":"https://orcid.org/0000-0001-6806-4287","affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Dan Zeng","orcid":"https://orcid.org/0000-0003-1300-1769"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Zeng","raw_affiliation_strings":["Shanghai University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-1300-1769","affiliations":[{"raw_affiliation_string":"Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123187002","display_name":"Dapeng Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Dapeng Wu","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Hong Kong, SAR, China"],"raw_orcid":"https://orcid.org/0000-0003-1755-0183","affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I168719708"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06669059,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":null,"first_page":"3880","last_page":"3892"},"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":0.2935999929904938,"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":0.2935999929904938,"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":0.13379999995231628,"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":0.0966000035405159,"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/encoder","display_name":"Encoder","score":0.6812000274658203},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.5577999949455261},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.5551999807357788},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3984000086784363},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.39419999718666077},{"id":"https://openalex.org/keywords/visual-attention","display_name":"Visual attention","score":0.38999998569488525}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8809999823570251},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6812000274658203},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.642300009727478},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.5577999949455261},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.5551999807357788},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.45829999446868896},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3984000086784363},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.39419999718666077},{"id":"https://openalex.org/C2986089797","wikidata":"https://www.wikidata.org/wiki/Q6501338","display_name":"Visual attention","level":3,"score":0.38999998569488525},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.3596000075340271},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.32739999890327454},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30219998955726624},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.27810001373291016},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.2599000036716461},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2531999945640564},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2026.3654420","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3654420","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Zero-shot":[0],"Sketch-based":[1],"Image":[2],"Retrieval":[3],"(ZS-SBIR)":[4],"is":[5,80,152,182],"a":[6,38,88,98,103],"challenging":[7],"yet":[8],"rewarding":[9],"task,":[10],"as":[11,35,97],"it":[12,181],"demands":[13],"models":[14],"to":[15,116,123],"possess":[16],"both":[17],"brain-":[18],"like":[19],"zero-shot":[20,53,119],"learning":[21,54,120],"and":[22,56,87,106,154,174],"cross-view":[23,57,127,137],"alignment":[24,58,128],"capabilities.":[25],"Recent":[26],"advances":[27],"suggest":[28],"that":[29,165],"powerful":[30],"pre-trained":[31,61,187,193],"vision":[32,62,156,188,194],"encoders,":[33],"such":[34],"CLIP,":[36],"offer":[37],"promising":[39],"alternative":[40],"for":[41],"addressing":[42],"the":[43,47,52,73,118,145,185,191],"ZS-SBIR":[44,176],"task.":[45],"However,":[46],"problem":[48,100],"of":[49,60,82,179],"simultaneously":[50],"evoking":[51],"capability":[55,59],"encoders":[63,157],"has":[64],"barely":[65],"been":[66],"discussed.":[67],"To":[68],"this":[69],"end,":[70],"we":[71,93,130],"propose":[72],"CrOss-view":[74],"Attention":[75,84,146],"Prompt":[76,85,147],"(COP)":[77],"framework,":[78],"which":[79,139],"composed":[81],"an":[83],"module":[86],"Cross-view":[89],"Query":[90],"module.":[91,148],"Specifically,":[92],"formulate":[94],"prompt":[95,104],"construction":[96],"retrieval":[99],"by":[101],"introducing":[102],"pool":[105],"attention":[107,111],"mechanism,":[108],"thereby":[109],"constructing":[110],"prompts":[112],"with":[113,126,134,158],"fine":[114],"granularity":[115],"enhance":[117],"capability.":[121],"Furthermore,":[122],"endow":[124],"COP":[125,151,166],"capabilities,":[129],"replace":[131],"single-view":[132],"queries":[133],"carefully":[135],"designed":[136],"queries,":[138],"can":[140],"be":[141],"smoothly":[142],"inserted":[143],"into":[144],"The":[149],"proposed":[150],"scenario-agnostic":[153],"supports":[155],"diverse":[159],"pre-training":[160],"schemes.":[161],"Comprehensive":[162],"experiments":[163],"show":[164],"achieves":[167],"competitive":[168],"performance":[169],"in":[170],"ZS-SBIR,":[171,173],"Generalized":[172],"Cross-data":[175],"scenarios,":[177],"regardless":[178],"whether":[180],"based":[183],"on":[184],"ImageNet":[186],"encoder":[189],"or":[190],"CLIP":[192],"encoder.":[195]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-01-17T00:00:00"}