{"id":"https://openalex.org/W4408345617","doi":"https://doi.org/10.1109/icassp49660.2025.10888442","title":"Boosting Open-Vocabulary Object Detection Performance via Class-Agnostic Pseudo-Labels and MultiModal Hybrid Knowledge","display_name":"Boosting Open-Vocabulary Object Detection Performance via Class-Agnostic Pseudo-Labels and MultiModal Hybrid Knowledge","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345617","doi":"https://doi.org/10.1109/icassp49660.2025.10888442"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888442","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888442","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100324482","display_name":"Ziyang Chen","orcid":"https://orcid.org/0000-0002-1714-0304"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyang Chen","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108137799","display_name":"Dongqin Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongqin Liu","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031794241","display_name":"Jiao Dai","orcid":"https://orcid.org/0000-0003-3559-8009"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiao Dai","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102820325","display_name":"Songlin Hu","orcid":"https://orcid.org/0000-0001-8559-1740"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Songlin Hu","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.673,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.78970081,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9778000116348267,"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":0.9778000116348267,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.916700005531311,"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/boosting","display_name":"Boosting (machine learning)","score":0.894527792930603},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7548931241035461},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5956783890724182},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5831727385520935},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5155353546142578},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4908328950405121},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3752024173736572},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3533087968826294},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.320456326007843},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09221220016479492}],"concepts":[{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.894527792930603},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7548931241035461},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5956783890724182},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5831727385520935},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5155353546142578},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4908328950405121},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3752024173736572},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3533087968826294},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.320456326007843},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09221220016479492},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888442","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888442","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W2948672349","https://openalex.org/W2963037989","https://openalex.org/W3096609285","https://openalex.org/W3173859428","https://openalex.org/W4312424618","https://openalex.org/W4312563428","https://openalex.org/W4312747482","https://openalex.org/W4312773012","https://openalex.org/W4312890493","https://openalex.org/W4386076029","https://openalex.org/W4386076396","https://openalex.org/W4387855642","https://openalex.org/W4390874575","https://openalex.org/W4402727672","https://openalex.org/W4402727806","https://openalex.org/W4404612908","https://openalex.org/W6750462345","https://openalex.org/W6778883912","https://openalex.org/W6791353385","https://openalex.org/W6794713401","https://openalex.org/W6802517928","https://openalex.org/W6809885388","https://openalex.org/W6845484831","https://openalex.org/W6846977184","https://openalex.org/W6849177959","https://openalex.org/W6853690301","https://openalex.org/W6855629020","https://openalex.org/W6869351093"],"related_works":["https://openalex.org/W2125652721","https://openalex.org/W1540371141","https://openalex.org/W1549363203","https://openalex.org/W2147697413","https://openalex.org/W2154063878","https://openalex.org/W4231274751","https://openalex.org/W2556012038","https://openalex.org/W1489772951","https://openalex.org/W1538046993","https://openalex.org/W2963610131"],"abstract_inverted_index":{"Open-vocabulary":[0],"object":[1],"detection":[2],"(OVD)":[3],"is":[4],"a":[5],"significant":[6],"task":[7],"identifying":[8],"objects":[9],"from":[10],"categories":[11,36],"not":[12],"included":[13],"in":[14],"the":[15,76],"training":[16,83],"set.":[17],"Our":[18],"comprehensive":[19],"analysis":[20],"reveals":[21],"two":[22,47],"main":[23],"issues":[24],"with":[25],"existing":[26,77],"OVD":[27,78],"models:":[28],"poor":[29,38],"generalization":[30],"of":[31,40],"localization":[32],"network":[33],"to":[34,73],"novel":[35],"and":[37,57,84,92,95],"quality":[39],"class":[41],"embedding":[42],"impacting":[43],"accuracy.":[44],"We":[45],"propose":[46],"solutions:":[48],"Localization":[49],"Network":[50],"Enhancement":[51,60],"based":[52,61],"on":[53,62],"Class-Agnostic":[54],"Pseudo-Labels":[55],"(LNE-CAPL)":[56],"Class":[58],"Embedding":[59],"MultiModal":[63],"Hybrid":[64],"Knowledge":[65],"(CEE-MMHK).":[66],"These":[67],"methods":[68],"can":[69],"be":[70,99],"used":[71],"offline":[72],"significantly":[74],"improve":[75],"models":[79,96],"without":[80],"affecting":[81],"their":[82,90],"inference":[85],"efficiency.":[86],"Extensive":[87],"experiments":[88],"confirm":[89],"effectiveness":[91],"universality.":[93],"Code":[94],"will":[97],"soon":[98],"open-sourced.":[100]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}