{"id":"https://openalex.org/W4417052011","doi":"https://doi.org/10.1109/tcsvt.2025.3640868","title":"Triple-Way Visual Modulation for Zero-Shot Sketch-Based Image Retrieval","display_name":"Triple-Way Visual Modulation for Zero-Shot Sketch-Based Image Retrieval","publication_year":2025,"publication_date":"2025-12-05","ids":{"openalex":"https://openalex.org/W4417052011","doi":"https://doi.org/10.1109/tcsvt.2025.3640868"},"language":null,"primary_location":{"id":"doi:10.1109/tcsvt.2025.3640868","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3640868","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","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/A5009549753","display_name":"Haoxiang Zhang","orcid":"https://orcid.org/0000-0001-9249-4615"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoxiang Zhang","raw_affiliation_strings":["School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-9249-4615","affiliations":[{"raw_affiliation_string":"School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051269393","display_name":"Qiqi Kou","orcid":"https://orcid.org/0000-0003-2873-2636"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiqi Kou","raw_affiliation_strings":["School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-2873-2636","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037836004","display_name":"He Jiang","orcid":"https://orcid.org/0000-0002-3345-9665"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"He Jiang","raw_affiliation_strings":["School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-3345-9665","affiliations":[{"raw_affiliation_string":"School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082518848","display_name":"Tianshu Song","orcid":"https://orcid.org/0000-0003-3592-0651"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianshu Song","raw_affiliation_strings":["School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-3592-0651","affiliations":[{"raw_affiliation_string":"School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100729603","display_name":"Liangliang Chen","orcid":"https://orcid.org/0000-0001-9097-0657"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liangliang Chen","raw_affiliation_strings":["School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-9097-0657","affiliations":[{"raw_affiliation_string":"School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044684024","display_name":"Deqiang Cheng","orcid":"https://orcid.org/0000-0001-8831-1994"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deqiang Cheng","raw_affiliation_strings":["School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-8831-1994","affiliations":[{"raw_affiliation_string":"School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I25757504"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35473344,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"4","first_page":"4419","last_page":"4432"},"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":0.4934000074863434,"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":0.4934000074863434,"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":0.41589999198913574,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.04540000110864639,"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/focus","display_name":"Focus (optics)","score":0.5781000256538391},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5486999750137329},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.5347999930381775},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5006999969482422},{"id":"https://openalex.org/keywords/visual-word","display_name":"Visual Word","score":0.4738999903202057},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4699999988079071},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.42289999127388}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8133999705314636},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.689300000667572},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5910000205039978},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5781000256538391},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5486999750137329},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.5347999930381775},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5006999969482422},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.4738999903202057},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4699999988079071},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.42289999127388},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4072999954223633},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.4016000032424927},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.39489999413490295},{"id":"https://openalex.org/C123079801","wikidata":"https://www.wikidata.org/wiki/Q750240","display_name":"Modulation (music)","level":2,"score":0.362199991941452},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.35989999771118164},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3440000116825104},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C105842133","wikidata":"https://www.wikidata.org/wiki/Q1899679","display_name":"Visual communication","level":2,"score":0.2549000084400177}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2025.3640868","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3640868","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1104977003","display_name":null,"funder_award_id":"2024ZDPYCH1001","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"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],"seeks":[5],"to":[6,74,94,132,153,167],"correlate":[7],"unseen":[8,12],"hand-drawn":[9],"sketches":[10],"with":[11,66],"real":[13],"images":[14],"by":[15,111],"leveraging":[16],"trained":[17],"models":[18],"on":[19,28,126,180],"visible":[20],"categories.":[21],"Recent":[22],"CLIP-based":[23],"models,":[24],"which":[25],"primarily":[26],"focus":[27],"visual-textual":[29],"interaction,":[30],"have":[31],"demonstrated":[32],"strong":[33],"competitiveness":[34],"in":[35,42,50,158],"ZS-SBIR.":[36],"However,":[37],"they":[38],"still":[39],"fall":[40],"short":[41],"the":[43,61,76,87,96,117,155,172,181,191,196],"exploration":[44],"of":[45,52,78,99,174],"cross-modal":[46,53],"visual":[47,54,71,79,90,100],"representations,":[48],"especially":[49],"terms":[51],"shared":[55,101,135],"and":[56,69,102,129,136,149,171,187],"specific":[57,103,137],"information.":[58,104],"Differing":[59],"from":[60],"aforementioned":[62],"researches,":[63],"we":[64,85,106,140],"start":[65],"class-level,":[67],"prompt-level,":[68],"patch-level":[70],"information,":[72],"committed":[73],"unlocking":[75],"potential":[77],"feature":[80],"representation.":[81],"On":[82],"this":[83],"foundation,":[84],"introduce":[86],"vision-centric":[88],"Triple-way":[89],"modulATion":[91],"(TAT)":[92],"framework":[93],"enhance":[95],"model\u2019s":[97,156],"perception":[98,110],"Specifically,":[105],"establish":[107],"unified":[108],"multi-modal":[109],"integrating":[112],"visual-level":[113],"modality":[114],"prompter":[115],"into":[116],"CLIP":[118],"architecture.":[119],"We":[120,162],"then":[121],"conduct":[122],"triple-way":[123],"modulation":[124],"modeling":[125],"prompt,":[127],"token,":[128],"patch":[130],"levels":[131],"effectively":[133],"mine":[134],"features.":[138,161],"Lastly,":[139],"develop":[141],"an":[142],"enhanced":[143],"calibration":[144],"strategy":[145],"incorporating":[146],"prompt-aware,":[147],"token-aware,":[148],"logit-aware":[150],"alignment":[151],"modules":[152],"amplify":[154],"proficiency":[157],"probing":[159],"shared-specific":[160],"thoroughly":[163],"test":[164],"our":[165],"approach":[166],"confirm":[168],"its":[169],"excellence":[170],"efficacy":[173],"individual":[175],"components.":[176],"The":[177],"comparison":[178],"results":[179],"popular":[182],"datasets":[183],"Sketchy,":[184],"Sketchyv2,":[185],"Tuberlin,":[186],"QuickDraw":[188],"show":[189],"that":[190],"developed":[192],"algorithm":[193],"significantly":[194],"surpasses":[195],"current":[197],"state-of-the-art":[198],"technologies.":[199]},"counts_by_year":[],"updated_date":"2026-04-07T06:01:17.266235","created_date":"2025-12-05T00:00:00"}
