{"id":"https://openalex.org/W4414166040","doi":"https://doi.org/10.1109/tmm.2025.3607729","title":"A Hierarchical Semantic Distillation Framework for Open-Vocabulary Object Detection","display_name":"A Hierarchical Semantic Distillation Framework for Open-Vocabulary Object Detection","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4414166040","doi":"https://doi.org/10.1109/tmm.2025.3607729"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2025.3607729","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3607729","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","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/A5101195451","display_name":"Shenghao Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shenghao Fu","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0008-3456-4193","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102249848","display_name":"Junkai Yan","orcid":"https://orcid.org/0009-0009-6531-0070"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junkai Yan","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0009-6531-0070","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038504160","display_name":"Qize Yang","orcid":"https://orcid.org/0000-0002-8884-7665"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]},{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Qize Yang","raw_affiliation_strings":["Tongyi Lab, Alibaba Group, Hangzhou, China","Tongyi Lab, Alibaba Group, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongyi Lab, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Tongyi Lab, Alibaba Group, China","institution_ids":["https://openalex.org/I45928872","https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111171181","display_name":"Xihan Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]},{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Xihan Wei","raw_affiliation_strings":["Tongyi Lab, Alibaba Group, Hangzhou, China","Tongyi Lab, Alibaba Group, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongyi Lab, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Tongyi Lab, Alibaba Group, China","institution_ids":["https://openalex.org/I45928872","https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018298892","display_name":"Xiaohua Xie","orcid":"https://orcid.org/0000-0002-0310-4679"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaohua Xie","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0002-0310-4679","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108050904","display_name":"Wei\u2010Shi Zheng","orcid":"https://orcid.org/0000-0001-8327-0003"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei-Shi Zheng","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0001-8327-0003","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101195451"],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":4.3465,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.94671174,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"27","issue":null,"first_page":"8835","last_page":"8846"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9810000061988831,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9810000061988831,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.579200029373169},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.5613999962806702},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5062999725341797},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5027999877929688},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5023999810218811},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4821000099182129},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.46230000257492065},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.44699999690055847},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.4372999966144562}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8646000027656555},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6891000270843506},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.579200029373169},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.5613999962806702},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5062999725341797},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5027999877929688},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5023999810218811},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4821000099182129},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.46230000257492065},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46160000562667847},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.44699999690055847},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.4372999966144562},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.4359000027179718},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4271000027656555},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4129999876022339},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40450000762939453},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.37529999017715454},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3734000027179718},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.36970001459121704},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3497999906539917},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.33799999952316284},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3287999927997589},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.30230000615119934},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C2986420190","wikidata":"https://www.wikidata.org/wiki/Q39045939","display_name":"Semantic space","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C2777946921","wikidata":"https://www.wikidata.org/wiki/Q7449044","display_name":"Semantic analysis (machine learning)","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25459998846054077},{"id":"https://openalex.org/C197914299","wikidata":"https://www.wikidata.org/wiki/Q18650","display_name":"Semantic memory","level":3,"score":0.2533999979496002}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2025.3607729","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3607729","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1702828313","display_name":null,"funder_award_id":"U21A20471","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1951972270","display_name":null,"funder_award_id":"U22A2095","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8949795292","display_name":null,"funder_award_id":"92470202","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":48,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2565639579","https://openalex.org/W2886641317","https://openalex.org/W2948672349","https://openalex.org/W2963351448","https://openalex.org/W2983943451","https://openalex.org/W3035524453","https://openalex.org/W3092663126","https://openalex.org/W3096609285","https://openalex.org/W3138516171","https://openalex.org/W3173859428","https://openalex.org/W3216939881","https://openalex.org/W4205334590","https://openalex.org/W4233467483","https://openalex.org/W4310557340","https://openalex.org/W4312424618","https://openalex.org/W4312559104","https://openalex.org/W4312563428","https://openalex.org/W4312692509","https://openalex.org/W4312747482","https://openalex.org/W4312773012","https://openalex.org/W4312890493","https://openalex.org/W4312925417","https://openalex.org/W4312956471","https://openalex.org/W4319663728","https://openalex.org/W4386066010","https://openalex.org/W4386071855","https://openalex.org/W4386076029","https://openalex.org/W4386076396","https://openalex.org/W4390590999","https://openalex.org/W4390872357","https://openalex.org/W4390872587","https://openalex.org/W4390872844","https://openalex.org/W4390872928","https://openalex.org/W4391547487","https://openalex.org/W4393150063","https://openalex.org/W4393159141","https://openalex.org/W4393207154","https://openalex.org/W4394625787","https://openalex.org/W4402660130","https://openalex.org/W4402716321","https://openalex.org/W4402727167","https://openalex.org/W4402727806","https://openalex.org/W4404612908","https://openalex.org/W4405632022"],"related_works":[],"abstract_inverted_index":{"Open-vocabulary":[0],"object":[1],"detection":[2],"(OVD)":[3],"aims":[4],"to":[5,17,24,51,69,122,195,214],"detect":[6],"objects":[7,110],"beyond":[8],"the":[9,44,53,80,87,92,101,112,124,127,135,140,164,188,192],"training":[10],"annotations,":[11],"where":[12],"detectors":[13,32],"are":[14,154],"usually":[15],"aligned":[16],"a":[18,62,71,198,205],"pre-trained":[19],"vision-language":[20],"model,":[21],"e.g.,":[22],"CLIP,":[23],"inherit":[25],"its":[26],"generalizable":[27,77,129,174],"recognition":[28,175],"ability":[29,176],"so":[30],"that":[31],"can":[33],"recognize":[34],"new":[35],"or":[36],"novel":[37,189],"objects.":[38],"However,":[39],"previous":[40],"works":[41],"directly":[42],"align":[43],"feature":[45],"space":[46,119],"with":[47,197],"CLIP":[48,81,102,136,178],"and":[49,151,182],"fail":[50],"learn":[52],"semantic":[54,64,166],"knowledge":[55,78],"effectively.":[56],"In":[57,86],"this":[58],"work,":[59],"we":[60,116,186],"propose":[61],"hierarchical":[63],"distillation":[65,73,167],"framework":[66],"named":[67],"HD-OVD":[68,172],"construct":[70],"comprehensive":[72],"process,":[74],"which":[75,201],"exploits":[76],"from":[79,100,134,163,177],"model":[82],"in":[83,111,168,179],"three":[84],"aspects.":[85],"first":[88],"hierarchy":[89],"of":[90],"HD-OVD,":[91],"detector":[93,125],"learns":[94],"fine-grained":[95],"<italic":[96,130,145],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[97,131,146],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">instance-wise":[98],"semantics</i>":[99,133,148],"image":[103,183],"encoder":[104],"by":[105,157,204],"modeling":[106],"relations":[107],"among":[108],"single":[109],"visual":[113],"space.":[114],"Besides,":[115],"introduce":[117],"text":[118,137],"novel-class-aware":[120],"classification":[121],"help":[123],"assimilate":[126],"highly":[128],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">class-wise":[132],"encoder,":[138],"representing":[139],"second":[141],"hierarchy.":[142],"Lastly,":[143],"abundant":[144],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">image-wise":[147],"containing":[149],"multi-object":[150],"their":[152],"contexts":[153],"also":[155,209],"distilled":[156],"an":[158],"image-wise":[159],"contrastive":[160],"distillation.":[161],"Benefiting":[162],"elaborated":[165],"triple":[169],"hierarchies,":[170],"our":[171],"inherits":[173],"instance,":[180],"class,":[181],"levels.":[184],"Thus,":[185],"boost":[187],"AP":[190],"on":[191],"OV-COCO":[193],"dataset":[194],"46.4%":[196],"ResNet50":[199],"backbone,":[200],"outperforms":[202],"others":[203],"clear":[206],"margin.":[207],"We":[208],"conduct":[210],"extensive":[211],"ablation":[212],"studies":[213],"analyze":[215],"how":[216],"each":[217],"component":[218],"works.":[219]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}