{"id":"https://openalex.org/W4387967874","doi":"https://doi.org/10.1145/3581783.3612523","title":"Zero-Shot Object Detection by Semantics-Aware DETR with Adaptive Contrastive Loss","display_name":"Zero-Shot Object Detection by Semantics-Aware DETR with Adaptive Contrastive Loss","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387967874","doi":"https://doi.org/10.1145/3581783.3612523"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612523","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612523","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-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/A5053550650","display_name":"Huan Liu","orcid":"https://orcid.org/0009-0004-2569-3736"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Huan Liu","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100388587","display_name":"Lu Zhang","orcid":"https://orcid.org/0000-0001-9532-5219"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu Zhang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086316879","display_name":"Jihong Guan","orcid":"https://orcid.org/0000-0003-2313-7635"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jihong Guan","raw_affiliation_strings":["Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017862559","display_name":"Shuigeng Zhou","orcid":"https://orcid.org/0000-0002-1949-2768"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuigeng Zhou","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5053550650"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":0.6087,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.70106934,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4421","last_page":"4430"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9997000098228455,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9947999715805054,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7723035216331482},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.662380039691925},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6469070911407471},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6396909952163696},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.602515697479248},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5429984331130981},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5313924551010132},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5292802453041077},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4561779201030731},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4359038770198822},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.43213921785354614},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41181111335754395},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40769192576408386}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7723035216331482},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.662380039691925},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6469070911407471},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6396909952163696},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.602515697479248},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5429984331130981},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5313924551010132},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5292802453041077},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4561779201030731},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4359038770198822},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.43213921785354614},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41181111335754395},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40769192576408386},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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":1,"locations":[{"id":"doi:10.1145/3581783.3612523","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612523","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7699999809265137}],"awards":[{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6705365387","display_name":null,"funder_award_id":"U1936205","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W569478347","https://openalex.org/W639708223","https://openalex.org/W1901129140","https://openalex.org/W2031489346","https://openalex.org/W2055289854","https://openalex.org/W2141350700","https://openalex.org/W2187089797","https://openalex.org/W2289084343","https://openalex.org/W2405223529","https://openalex.org/W2405686381","https://openalex.org/W2560662850","https://openalex.org/W2592549418","https://openalex.org/W2596142952","https://openalex.org/W2611632661","https://openalex.org/W2724492314","https://openalex.org/W2884561390","https://openalex.org/W2905535961","https://openalex.org/W2924476266","https://openalex.org/W2962766617","https://openalex.org/W2964086552","https://openalex.org/W2964241181","https://openalex.org/W2997795356","https://openalex.org/W2997998901","https://openalex.org/W3010805239","https://openalex.org/W3023742835","https://openalex.org/W3092529717","https://openalex.org/W3096609285","https://openalex.org/W3099554308","https://openalex.org/W3138516171","https://openalex.org/W3143107425","https://openalex.org/W3201221410","https://openalex.org/W3207088217","https://openalex.org/W4212810184","https://openalex.org/W4245551996","https://openalex.org/W4299709053"],"related_works":["https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2378211422","https://openalex.org/W1482209366","https://openalex.org/W2110523656","https://openalex.org/W4287991909","https://openalex.org/W4390721878"],"abstract_inverted_index":{"Zero-shot":[0],"object":[1,157],"detection":[2,112,158],"(ZSD)":[3],"aims":[4],"to":[5,28,53,59,78,86,99,126,138,161,184,190],"localize":[6],"and":[7,119,145,200,209],"recognize":[8],"unseen":[9,34,57,100],"objects":[10,55],"in":[11,152,188],"unconstrained":[12],"images":[13],"by":[14],"leveraging":[15],"semantic":[16,186],"descriptions.":[17],"Existing":[18],"ZSD":[19],"methods":[20],"typically":[21],"suffer":[22],"from":[23,94],"two":[24],"drawbacks:":[25],"1)":[26],"Due":[27],"the":[29,37,40,47,69,88,91,128,140,163,176,207,212],"lack":[30],"of":[31,56,75,96,181,211],"data":[32,74,95],"on":[33,73,115,203],"categories":[35,58,77,98,144,182],"during":[36],"training":[38],"phase,":[39],"model":[41,89],"inevitably":[42],"has":[43],"a":[44,109,116,120,133,153,166],"bias":[45,141],"towards":[46,142],"seen":[48,60,76,97,143],"categories,":[49],"i.e.,":[50],"it":[51,147],"prefers":[52],"subsume":[54],"categories;":[61],"2)":[62],"It":[63],"is":[64,172],"usually":[65],"very":[66],"tricky":[67],"for":[68,194],"feature":[70],"extractor":[71],"trained":[72],"learn":[79,191],"discriminative":[80],"features":[81,193],"that":[82],"are":[83],"good":[84],"enough":[85],"help":[87],"transfer":[90],"knowledge":[92],"learned":[93],"categories.":[101],"To":[102],"tackle":[103],"these":[104],"problems,":[105],"this":[106],"paper":[107],"proposes":[108],"novel":[110,134,167],"zero-shot":[111,156],"method":[113],"based":[114],"semantics-aware":[117,135],"DETR":[118],"class-wise":[121,168],"adaptive":[122,169],"contrastive":[123,170],"loss.":[124],"Concretely,":[125],"address":[127],"first":[129],"problem,":[130,165],"we":[131],"develop":[132],"attention":[136],"mechanism":[137],"mitigate":[139],"integrate":[146],"into":[148],"DETR,":[149],"which":[150,174],"results":[151],"new":[154],"end-to-end":[155],"approach.":[159],"Furthermore,":[160],"handle":[162],"second":[164],"loss":[171],"proposed,":[173],"considers":[175],"relevance":[177],"between":[178],"each":[179],"pair":[180],"according":[183],"their":[185],"description":[187],"order":[189],"separable":[192],"better":[195],"visual-semantic":[196],"alignment.":[197],"Extensive":[198],"experiments":[199],"ablation":[201],"studies":[202],"benchmark":[204],"datasets":[205],"demonstrate":[206],"effectiveness":[208],"superiority":[210],"proposed":[213],"method.":[214]},"counts_by_year":[{"year":2024,"cited_by_count":5}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}