{"id":"https://openalex.org/W4401965896","doi":"https://doi.org/10.1007/s11263-024-02199-0","title":"Learning General and Specific Embedding with Transformer for Few-Shot Object Detection","display_name":"Learning General and Specific Embedding with Transformer for Few-Shot Object Detection","publication_year":2024,"publication_date":"2024-08-28","ids":{"openalex":"https://openalex.org/W4401965896","doi":"https://doi.org/10.1007/s11263-024-02199-0"},"language":"en","primary_location":{"id":"doi:10.1007/s11263-024-02199-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-024-02199-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-024-02199-0.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11263-024-02199-0.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100437208","display_name":"Xu Zhang","orcid":"https://orcid.org/0000-0002-1882-736X"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xu Zhang","raw_affiliation_strings":["School of Computer Science, Faculty of Engineering, The University of Sydney, Darlington, Sydney, NSW, 2008, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Faculty of Engineering, The University of Sydney, Darlington, Sydney, NSW, 2008, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011356697","display_name":"Zhe Chen","orcid":"https://orcid.org/0000-0001-7579-1968"},"institutions":[{"id":"https://openalex.org/I196829312","display_name":"La Trobe University","ror":"https://ror.org/01rxfrp27","country_code":"AU","type":"education","lineage":["https://openalex.org/I196829312"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zhe Chen","raw_affiliation_strings":["Cisco-La Trobe Centre for AI and IoT, School of Computing, Engineering, and Mathematical Sciences, La Trobe University, Bendigo, VIC, 3552, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cisco-La Trobe Centre for AI and IoT, School of Computing, Engineering, and Mathematical Sciences, La Trobe University, Bendigo, VIC, 3552, Australia","institution_ids":["https://openalex.org/I196829312"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101994917","display_name":"Jing Zhang","orcid":"https://orcid.org/0000-0003-2494-8077"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Jing Zhang","raw_affiliation_strings":["School of Computer Science, Faculty of Engineering, The University of Sydney, Darlington, Sydney, NSW, 2008, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Faculty of Engineering, The University of Sydney, Darlington, Sydney, NSW, 2008, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065250332","display_name":"Tongliang Liu","orcid":"https://orcid.org/0000-0002-9640-6472"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Tongliang Liu","raw_affiliation_strings":["School of Computer Science, Faculty of Engineering, The University of Sydney, Darlington, Sydney, NSW, 2008, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Faculty of Engineering, The University of Sydney, Darlington, Sydney, NSW, 2008, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074103823","display_name":"Dacheng Tao","orcid":"https://orcid.org/0000-0001-7225-5449"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Dacheng Tao","raw_affiliation_strings":["School of Computer Science, Faculty of Engineering, The University of Sydney, Darlington, Sydney, NSW, 2008, Australia"],"raw_orcid":"https://orcid.org/0000-0001-7225-5449","affiliations":[{"raw_affiliation_string":"School of Computer Science, Faculty of Engineering, The University of Sydney, Darlington, Sydney, NSW, 2008, Australia","institution_ids":["https://openalex.org/I129604602"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5074103823","https://openalex.org/A5101994917"],"corresponding_institution_ids":["https://openalex.org/I129604602"],"apc_list":{"value":2890,"currency":"EUR","value_usd":3690},"apc_paid":{"value":2890,"currency":"EUR","value_usd":3690},"fwci":2.3297,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.89795075,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"133","issue":"2","first_page":"968","last_page":"984"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9994999766349792,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9994999766349792,"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":0.9952999949455261,"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"}},{"id":"https://openalex.org/T12549","display_name":"Image and Object Detection Techniques","score":0.9932000041007996,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.7307042479515076},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6834093332290649},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6254162192344666},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5698210597038269},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5451589822769165},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5190144777297974},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.47352859377861023},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10535687208175659}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7307042479515076},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6834093332290649},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6254162192344666},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5698210597038269},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5451589822769165},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5190144777297974},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.47352859377861023},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10535687208175659},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11263-024-02199-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-024-02199-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-024-02199-0.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s11263-024-02199-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-024-02199-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-024-02199-0.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6899999976158142,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320966","display_name":"University of Sydney","ror":"https://ror.org/0384j8v12"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401965896.pdf","grobid_xml":"https://content.openalex.org/works/W4401965896.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W2031489346","https://openalex.org/W2037227137","https://openalex.org/W2102605133","https://openalex.org/W2108598243","https://openalex.org/W2144172034","https://openalex.org/W2194775991","https://openalex.org/W2565639579","https://openalex.org/W2604763608","https://openalex.org/W2788210750","https://openalex.org/W2962837320","https://openalex.org/W2962898354","https://openalex.org/W2963150697","https://openalex.org/W2963943197","https://openalex.org/W2969985801","https://openalex.org/W2983156430","https://openalex.org/W2996583130","https://openalex.org/W2997616671","https://openalex.org/W3009213340","https://openalex.org/W3034974675","https://openalex.org/W3054755450","https://openalex.org/W3096609285","https://openalex.org/W3097651496","https://openalex.org/W3110528336","https://openalex.org/W3165924482","https://openalex.org/W3169708801","https://openalex.org/W3175373796","https://openalex.org/W3194193742","https://openalex.org/W3203974803","https://openalex.org/W4214627427","https://openalex.org/W4214724741","https://openalex.org/W4312702383","https://openalex.org/W4312755049","https://openalex.org/W4313039766","https://openalex.org/W4386075634","https://openalex.org/W6600339963","https://openalex.org/W6600459194","https://openalex.org/W6628991556","https://openalex.org/W6739901393","https://openalex.org/W6817527648"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2345479200","https://openalex.org/W2183306018","https://openalex.org/W2849310602","https://openalex.org/W3006008237","https://openalex.org/W2419146053","https://openalex.org/W4388890789","https://openalex.org/W2088247287","https://openalex.org/W2963903416","https://openalex.org/W4313153715"],"abstract_inverted_index":{"Abstract":[0],"Few-shot":[1],"object":[2,48,125,181],"detection":[3],"(FSOD)":[4],"studies":[5],"how":[6],"to":[7,34,61,73,88,95,111,119,122,170,179,189,205,240],"detect":[8],"novel":[9,77],"objects":[10,75],"with":[11,211,265],"few":[12],"annotated":[13],"examples":[14],"effectively.":[15],"Recently,":[16],"it":[17],"has":[18],"been":[19],"demonstrated":[20],"that":[21,30,42,247],"decent":[22],"feature":[23,28,40,67,102,152,219,229],"embeddings,":[24],"including":[25],"the":[26,38,123,173,176,186,191],"general":[27,99,132,155],"embeddings":[29,41,68,103,153,201,220],"are":[31,43,50,145],"more":[32,44,90],"invariant":[33],"visual":[35],"changes":[36],"and":[37,100,107,133,159,183,209,217,224,260],"specific":[39,101,134,160,218],"discriminative":[45],"for":[46,53,139,228],"different":[47,203],"classes,":[49,78],"both":[51,64,98,257],"important":[52],"FSOD.":[54,140,232],"However,":[55],"current":[56],"methods":[57],"lack":[58],"appropriate":[59],"mechanisms":[60],"sensibly":[62],"cooperate":[63,210],"types":[65],"of":[66,76,175,202],"based":[69],"on":[70,256],"their":[71,120],"importance":[72],"detecting":[74],"which":[79],"may":[80],"result":[81],"in":[82,116,147,154,231],"sub-optimal":[83],"performance.":[84],"In":[85,141,163,233],"this":[86],"paper,":[87],"achieve":[89],"effective":[91],"FSOD,":[92],"we":[93,166,195],"attempt":[94],"explicitly":[96],"encode":[97],"using":[104],"learnable":[105,143],"tensors":[106,144],"apply":[108,167,185],"a":[109,130,148,168,235],"Transformer":[110,169],"help":[112],"better":[113],"incorporate":[114],"them":[115,207,226],"FSOD":[117,254],"according":[118],"relations":[121,174,188],"input":[124,180,192],"features.":[126,193],"We":[127],"thus":[128],"propose":[129],"Transformer-based":[131],"embedding":[135,178],"learning":[136],"(T-GSEL)":[137],"method":[138,251],"T-GSEL,":[142],"employed":[146],"three-stage":[149],"pipeline,":[150],"encoding":[151],"level,":[156,158,161],"intermediate":[157],"respectively.":[162],"each":[164,212],"stage,":[165],"first":[171],"model":[172],"corresponding":[177],"features":[182],"then":[184],"estimated":[187],"refine":[190],"Meanwhile,":[194],"further":[196,245],"introduce":[197],"cross-stage":[198],"connections":[199],"between":[200],"stages":[204],"make":[206],"complement":[208],"other,":[213],"delivering":[214],"general,":[215],"intermediate,":[216],"stage":[221,223],"by":[222],"utilizing":[225],"together":[227],"refinement":[230],"practice,":[234],"T-GSEL":[236,250],"module":[237],"is":[238],"easy":[239],"inject.":[241],"Extensive":[242],"empirical":[243],"results":[244],"show":[246],"our":[248],"proposed":[249],"achieves":[252],"compelling":[253],"performance":[255],"PASCAL":[258],"VOC":[259],"MS":[261],"COCO":[262],"datasets":[263],"compared":[264],"other":[266],"state-of-the-art":[267],"approaches.":[268]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":8}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}