{"id":"https://openalex.org/W4403791469","doi":"https://doi.org/10.1145/3664647.3680702","title":"Dr. CLIP: CLIP-Driven Universal Framework for Zero-Shot Sketch Image Retrieval","display_name":"Dr. CLIP: CLIP-Driven Universal Framework for Zero-Shot Sketch Image Retrieval","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791469","doi":"https://doi.org/10.1145/3664647.3680702"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680702","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680702","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100677774","display_name":"Xue Li","orcid":"https://orcid.org/0000-0002-8553-994X"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xue Li","raw_affiliation_strings":["Xinjiang University, Urumqi, China"],"raw_orcid":"https://orcid.org/0000-0002-8553-994X","affiliations":[{"raw_affiliation_string":"Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020873493","display_name":"Jiong Yu","orcid":"https://orcid.org/0000-0002-9181-6720"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiong Yu","raw_affiliation_strings":["Xinjiang University, Urumqi, China"],"raw_orcid":"https://orcid.org/0000-0002-9181-6720","affiliations":[{"raw_affiliation_string":"Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100422864","display_name":"Ziyang Li","orcid":"https://orcid.org/0000-0003-2419-2548"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyang Li","raw_affiliation_strings":["Xinjiang University, Urumqi, China"],"raw_orcid":"https://orcid.org/0000-0003-2419-2548","affiliations":[{"raw_affiliation_string":"Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043916192","display_name":"Hongchun Lu","orcid":"https://orcid.org/0000-0002-2087-3496"},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongchun Lu","raw_affiliation_strings":["Southwest Jiaotong University, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-2087-3496","affiliations":[{"raw_affiliation_string":"Southwest Jiaotong University, Chengdu, China","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"last","author":{"id":null,"display_name":"Ruifeng Yuan","orcid":"https://orcid.org/0009-0003-4664-4426"},"institutions":[{"id":"https://openalex.org/I4210156165","display_name":"Lenovo (China)","ror":"https://ror.org/04srd9d93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156165"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruifeng Yuan","raw_affiliation_strings":["Lenovo Reseach, Tianjin, China"],"raw_orcid":"https://orcid.org/0009-0003-4664-4426","affiliations":[{"raw_affiliation_string":"Lenovo Reseach, Tianjin, China","institution_ids":["https://openalex.org/I4210156165"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9554","last_page":"9562"},"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":0.9997000098228455,"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":0.9997000098228455,"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":0.9984999895095825,"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":0.9975000023841858,"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":0.8290453553199768},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6966820955276489},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.6412793397903442},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5940948724746704},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5157399773597717},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.507569432258606},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.49271252751350403},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4198056757450104},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32474255561828613},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.15669164061546326}],"concepts":[{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.8290453553199768},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6966820955276489},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6412793397903442},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5940948724746704},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5157399773597717},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.507569432258606},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.49271252751350403},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4198056757450104},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32474255561828613},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15669164061546326},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3680702","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680702","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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":37,"referenced_works":["https://openalex.org/W1972420097","https://openalex.org/W2466618734","https://openalex.org/W2467281799","https://openalex.org/W2471581439","https://openalex.org/W2603445054","https://openalex.org/W2885402090","https://openalex.org/W2948085278","https://openalex.org/W2962747232","https://openalex.org/W2964266708","https://openalex.org/W2988772405","https://openalex.org/W2997645545","https://openalex.org/W3034382172","https://openalex.org/W3034603197","https://openalex.org/W3035705029","https://openalex.org/W3045735302","https://openalex.org/W3046926727","https://openalex.org/W3057906563","https://openalex.org/W3142124201","https://openalex.org/W3177343422","https://openalex.org/W3177525997","https://openalex.org/W3211258519","https://openalex.org/W4213052788","https://openalex.org/W4280652284","https://openalex.org/W4281838252","https://openalex.org/W4283815156","https://openalex.org/W4304091961","https://openalex.org/W4312960937","https://openalex.org/W4321770427","https://openalex.org/W4382239170","https://openalex.org/W4382466812","https://openalex.org/W4384615906","https://openalex.org/W4385731829","https://openalex.org/W4386065553","https://openalex.org/W4386076063","https://openalex.org/W4386101359","https://openalex.org/W4386790226","https://openalex.org/W4390872642"],"related_works":["https://openalex.org/W2378994405","https://openalex.org/W2385974820","https://openalex.org/W2373478030","https://openalex.org/W2378679551","https://openalex.org/W3149739944","https://openalex.org/W2392363776","https://openalex.org/W2063051341","https://openalex.org/W2591066345","https://openalex.org/W1494563618","https://openalex.org/W2357022711"],"abstract_inverted_index":{"The":[0,184,208],"field":[1],"of":[2,27,38,72,120],"Zero-Shot":[3],"Sketch-Based":[4],"Image":[5],"Retrieval":[6],"(ZS-SBIR)":[7],"is":[8,109,132,150,210],"undergoing":[9],"a":[10,47,105,128,147,196],"paradigm":[11],"shift,":[12],"transitioning":[13],"from":[14],"specialized":[15,30],"models":[16,25],"designed":[17],"for":[18,180],"individual":[19],"tasks":[20,74],"to":[21,57,100,111,134,152,175],"more":[22],"general":[23],"retrieval":[24],"capable":[26],"managing":[28],"various":[29],"scenarios.":[31],"Inspired":[32],"by":[33,195],"the":[34,39,59,83,117,121,177,191],"impressive":[35],"generalization":[36],"ability":[37],"Contrastive":[40],"Language-Image":[41],"Pretraining":[42],"(CLIP)":[43],"model,":[44],"we":[45,81,164],"propose":[46],"CLIP-driven":[48],"universal":[49],"framework":[50],"(Dr.":[51],"CLIP),":[52],"which":[53],"leverages":[54],"prompt":[55],"learning":[56,102],"guide":[58],"synergy":[60,84],"between":[61,158],"CLIP":[62,66],"and":[63,78,90,115,138,155,166,171,206],"ZS-SBIR.":[64],"Dr.":[65],"can":[67],"perfectly":[68],"cover":[69],"four":[70,181],"variants":[71],"ZS-SBIR":[73,182],"(inter-category,":[75],"intra-category,":[76],"cross-datasets,":[77],"generalization).":[79],"Moreover,":[80],"decompose":[82],"into":[85],"classification":[86,125],"learning,":[87,89,92],"metric":[88,144],"ranking":[91,156,161],"as":[93,95],"well":[94],"introduce":[96],"three":[97,168],"key":[98],"components":[99],"enhance":[101],"effectiveness.":[103],"i)":[104],"forgetting":[106,114],"suppression":[107],"idea":[108],"applied":[110],"prevent":[112],"catastrophic":[113],"constrains":[116],"feature":[118],"distribution":[119],"new":[122],"categories":[123],"in":[124,143,160],"learning.":[126,145,162],"ii)":[127],"domain":[129],"balanced":[130],"loss":[131],"proposed":[133],"address":[135],"sample":[136],"imbalance":[137],"establish":[139],"effective":[140],"cross-domain":[141],"correlations":[142],"iii)":[146],"pair-relation":[148],"strategy":[149],"introduced":[151],"capture":[153],"relevance":[154],"relationships":[157],"instances":[159],"Eventually,":[163],"reorganize":[165],"redivide":[167],"coarse-grained":[169],"datasets":[170,174],"two":[172],"fine-grained":[173],"accommodate":[176],"training":[178],"settings":[179],"tasks.":[183],"comparison":[185],"experiments":[186],"confirmed":[187],"our":[188],"method":[189],"surpassed":[190],"state-of-the-art":[192],"(SOTA)":[193],"methods":[194],"significant":[197],"margin":[198],"(1.95%":[199],"~":[200],"19.14,%":[201],"mAP),":[202],"highlighting":[203],"its":[204],"generality":[205],"superiority.":[207],"code":[209],"available":[211],"at":[212],"https://github.com/x-28/CDUF.git.":[213]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}