{"id":"https://openalex.org/W4310270184","doi":"https://doi.org/10.48550/arxiv.2211.13470","title":"Efficient Zero-shot Visual Search via Target and Context-aware Transformer","display_name":"Efficient Zero-shot Visual Search via Target and Context-aware Transformer","publication_year":2022,"publication_date":"2022-11-24","ids":{"openalex":"https://openalex.org/W4310270184","doi":"https://doi.org/10.48550/arxiv.2211.13470"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2211.13470","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2211.13470","pdf_url":"https://arxiv.org/pdf/2211.13470","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2211.13470","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110769869","display_name":"Zhiwei Ding","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I181547552","display_name":"Baylor College of Medicine","ror":"https://ror.org/02pttbw34","country_code":"US","type":"education","lineage":["https://openalex.org/I181547552","https://openalex.org/I2801539370"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ding, Zhiwei","raw_affiliation_strings":["Center for Neuroscience and Artificial Intelligence , Baylor College of Medicine , Houston , TX , USA,","Department of Neuroscience , Baylor College of Medicine , Houston , TX , USA,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Neuroscience and Artificial Intelligence , Baylor College of Medicine , Houston , TX , USA,","institution_ids":["https://openalex.org/I181547552"]},{"raw_affiliation_string":"Department of Neuroscience , Baylor College of Medicine , Houston , TX , USA,","institution_ids":["https://openalex.org/I181547552"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081675250","display_name":"Xuezhe Ren","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ren, Xuezhe","raw_affiliation_strings":["CFAR and I2R , Agency for Science, Technology and Research , Singapore ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CFAR and I2R , Agency for Science, Technology and Research , Singapore ,","institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050442296","display_name":"Erwan Jo\u00ebl David","orcid":"https://orcid.org/0000-0002-5307-1705","observed_orcids":["https://orcid.org/0000-0002-5307-1705"]},"institutions":[{"id":"https://openalex.org/I114090438","display_name":"Goethe University Frankfurt","ror":"https://ror.org/04cvxnb49","country_code":"DE","type":"education","lineage":["https://openalex.org/I114090438"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"David, Erwan","raw_affiliation_strings":["Department of Psychology , Goethe Univerisity Frankfurt , Frankfurt , Germany,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Psychology , Goethe Univerisity Frankfurt , Frankfurt , Germany,","institution_ids":["https://openalex.org/I114090438"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027755029","display_name":"Melissa L.\u2010H. V\u00f5","orcid":"https://orcid.org/0000-0003-1145-4473","observed_orcids":["https://orcid.org/0000-0003-1145-4473"]},"institutions":[{"id":"https://openalex.org/I114090438","display_name":"Goethe University Frankfurt","ror":"https://ror.org/04cvxnb49","country_code":"DE","type":"education","lineage":["https://openalex.org/I114090438"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Vo, Melissa","raw_affiliation_strings":["Department of Psychology , Goethe Univerisity Frankfurt , Frankfurt , Germany,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Psychology , Goethe Univerisity Frankfurt , Frankfurt , Germany,","institution_ids":["https://openalex.org/I114090438"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081541767","display_name":"Gabriel Kreiman","orcid":"https://orcid.org/0000-0003-3505-8475","observed_orcids":["https://orcid.org/0000-0003-3505-8475"]},"institutions":[{"id":"https://openalex.org/I1288882113","display_name":"Boston Children's Hospital","ror":"https://ror.org/00dvg7y05","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1288882113"]},{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kreiman, Gabriel","raw_affiliation_strings":["Center for Brains, Minds and Machines , Cambridge , MA , USA,","Children's Hospital , Harvard Medical School , Boston , MA , USA,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Brains, Minds and Machines , Cambridge , MA , USA,","institution_ids":[]},{"raw_affiliation_string":"Children's Hospital , Harvard Medical School , Boston , MA , USA,","institution_ids":["https://openalex.org/I1288882113","https://openalex.org/I136199984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043013159","display_name":"Mengmi Zhang","orcid":"https://orcid.org/0000-0002-2694-7097","observed_orcids":["https://orcid.org/0000-0002-2694-7097"]},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhang, Mengmi","raw_affiliation_strings":["CFAR and I2R , Agency for Science, Technology and Research , Singapore ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CFAR and I2R , Agency for Science, Technology and Research , Singapore ,","institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3005327000"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.823199987411499,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.823199987411499,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.11789999902248383,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.052299998700618744,"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/contextual-modulation","display_name":"contextual modulation","score":0.8349999785423279},{"id":"https://openalex.org/keywords/vision-transformer","display_name":"vision transformer","score":0.9039999842643738},{"id":"https://openalex.org/keywords/search-efficiency","display_name":"search efficiency","score":0.5509999990463257},{"id":"https://openalex.org/keywords/generalization-to-novel-objects","display_name":"novel object generalization","score":0.765999972820282}],"concepts":[{"id":"https://openalex.org/C158495155","wikidata":"https://www.wikidata.org/wiki/Q2369151","display_name":"Visual search","level":2,"score":0.8221865892410278},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7664090394973755},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.621088981628418},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.41636529564857483},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39986452460289},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3674008250236511},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2211.13470","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2211.13470","pdf_url":"https://arxiv.org/pdf/2211.13470","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2211.13470","doi":"https://doi.org/10.48550/arxiv.2211.13470","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2211.13470","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2211.13470","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2211.13470","pdf_url":"https://arxiv.org/pdf/2211.13470","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7153407949","https://openalex.org/W2801144650","https://openalex.org/W7164863004","https://openalex.org/W4402916414","https://openalex.org/W4312617935","https://openalex.org/W4415398809","https://openalex.org/W2996840863","https://openalex.org/W7161103027","https://openalex.org/W3204801262","https://openalex.org/W4403878467"],"abstract_inverted_index":{"Visual":[0],"search":[1,61,66,82,117,131,145,153,172,182,210,217],"is":[2,43,121,136],"a":[3,15,18,23,26,49,88,139,201],"ubiquitous":[4],"challenge":[5],"in":[6,17,25,52,80,102,138,169,179],"natural":[7,157],"vision,":[8],"including":[9],"daily":[10],"tasks":[11],"such":[12],"as":[13,55,123],"finding":[14],"friend":[16],"crowd":[19],"or":[20,195],"searching":[21],"for":[22,47,207],"car":[24],"parking":[27],"lot.":[28],"Human":[29],"rely":[30],"heavily":[31],"on":[32,147,155],"relevant":[33,110],"target":[34,50,76,107,129,220],"features":[35],"to":[36,112,204,216],"perform":[37],"goal-directed":[38],"visual":[39,81,116,144,152,181,209],"search.":[40],"Meanwhile,":[41],"context":[42,78,222],"of":[44,163,171],"critical":[45],"importance":[46],"locating":[48],"object":[51],"complex":[53],"scenes":[54],"it":[56],"helps":[57],"narrow":[58],"down":[59],"the":[60,65,103,128,176],"area":[62],"and":[63,77,95,108,130,149,174,221],"makes":[64],"process":[67],"more":[68],"efficient.":[69],"However,":[70],"few":[71],"works":[72],"have":[73],"combined":[74],"both":[75],"information":[79,111],"computational":[83],"models.":[84],"Here":[85],"we":[86,198],"propose":[87],"zero-shot":[89,115],"deep":[90],"learning":[91],"architecture,":[92],"TCT":[93,148,165,185,214],"(Target":[94],"Context-aware":[96],"Transformer),":[97],"that":[98],"modulates":[99],"self":[100],"attention":[101],"Vision":[104],"Transformer":[105],"with":[106,160,190],"contextual":[109,134],"enable":[113],"human-like":[114,167],"performance.":[118],"Target":[119],"modulation":[120,135],"computed":[122],"patch-wise":[124],"local":[125],"relevance":[126],"between":[127],"images,":[132],"whereas":[133],"applied":[137],"global":[140],"fashion.":[141],"We":[142],"conduct":[143],"experiments":[146],"other":[150],"competitive":[151],"models":[154,178,206],"three":[156],"scene":[158],"datasets":[159,189],"varying":[161],"levels":[162],"difficulty.":[164],"demonstrates":[166],"performance":[168],"terms":[170],"efficiency":[173],"beats":[175],"SOTA":[177],"challenging":[180],"tasks.":[183],"Importantly,":[184],"generalizes":[186],"well":[187],"across":[188],"novel":[191],"objects":[192],"without":[193],"retraining":[194],"fine-tuning.":[196],"Furthermore,":[197],"also":[199],"introduce":[200],"new":[202],"dataset":[203],"benchmark":[205],"invariant":[208],"under":[211,225],"incongruent":[212,226],"contexts.":[213,227],"manages":[215],"flexibly":[218],"via":[219],"modulation,":[223],"even":[224]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2022-11-30T00:00:00"}