{"id":"https://openalex.org/W4408353350","doi":"https://doi.org/10.1109/icassp49660.2025.10890109","title":"Confusion-Aware Prototypical Contrastive Learning for Open-Vocabulary Object Detection","display_name":"Confusion-Aware Prototypical Contrastive Learning for Open-Vocabulary Object Detection","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353350","doi":"https://doi.org/10.1109/icassp49660.2025.10890109"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890109","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890109","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/A5088448322","display_name":"Hongqiang Cheng","orcid":"https://orcid.org/0000-0001-9662-1570"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongqiang Cheng","raw_affiliation_strings":["AsiaInfo Technologies (China), Inc.,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AsiaInfo Technologies (China), Inc.,Beijing,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101697560","display_name":"Le Jiang","orcid":"https://orcid.org/0000-0002-4283-2302"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Le Jiang","raw_affiliation_strings":["AsiaInfo Technologies (China), Inc.,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AsiaInfo Technologies (China), Inc.,Beijing,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100752569","display_name":"Guoming Li","orcid":"https://orcid.org/0000-0001-7624-8051"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guoming Li","raw_affiliation_strings":["AsiaInfo Technologies (China), Inc.,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AsiaInfo Technologies (China), Inc.,Beijing,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107230366","display_name":"Xiaozhou Ye","orcid":"https://orcid.org/0000-0002-4925-5907"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaozhou Ye","raw_affiliation_strings":["AsiaInfo Technologies (China), Inc.,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AsiaInfo Technologies (China), Inc.,Beijing,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016317255","display_name":"Ye Ouyang","orcid":"https://orcid.org/0000-0002-6195-6415"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye Ouyang","raw_affiliation_strings":["AsiaInfo Technologies (China), Inc. & AsiaInfo Technologies (China, Guangzhou),Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AsiaInfo Technologies (China), Inc. & AsiaInfo Technologies (China, Guangzhou),Beijing,China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.346,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.903352,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":97},"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":0.9987000226974487,"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":0.9987000226974487,"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/T10028","display_name":"Topic Modeling","score":0.9897000193595886,"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/T12031","display_name":"Speech and dialogue systems","score":0.9745000004768372,"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/computer-science","display_name":"Computer science","score":0.7829521894454956},{"id":"https://openalex.org/keywords/confusion","display_name":"Confusion","score":0.7257418036460876},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.587652862071991},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5490050315856934},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5098916292190552},{"id":"https://openalex.org/keywords/vocabulary-learning","display_name":"Vocabulary learning","score":0.48717185854911804},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.47553467750549316},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4710747301578522},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2806616425514221},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.15823328495025635},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.1376563012599945}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7829521894454956},{"id":"https://openalex.org/C2781140086","wikidata":"https://www.wikidata.org/wiki/Q557945","display_name":"Confusion","level":2,"score":0.7257418036460876},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.587652862071991},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5490050315856934},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5098916292190552},{"id":"https://openalex.org/C2984601542","wikidata":"https://www.wikidata.org/wiki/Q48842322","display_name":"Vocabulary learning","level":3,"score":0.48717185854911804},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.47553467750549316},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4710747301578522},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2806616425514221},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.15823328495025635},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.1376563012599945},{"id":"https://openalex.org/C11171543","wikidata":"https://www.wikidata.org/wiki/Q41630","display_name":"Psychoanalysis","level":1,"score":0.0},{"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/icassp49660.2025.10890109","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890109","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2150593711","https://openalex.org/W2194775991","https://openalex.org/W2948672349","https://openalex.org/W2962766617","https://openalex.org/W2962966271","https://openalex.org/W2963037989","https://openalex.org/W2963351448","https://openalex.org/W3035524453","https://openalex.org/W3096609285","https://openalex.org/W3173859428","https://openalex.org/W3176709420","https://openalex.org/W3194038966","https://openalex.org/W4312563428","https://openalex.org/W4312773012","https://openalex.org/W4312890493","https://openalex.org/W4386076029","https://openalex.org/W4392904725","https://openalex.org/W4392910520","https://openalex.org/W4402727672","https://openalex.org/W4402727806","https://openalex.org/W4404582597","https://openalex.org/W4409367135","https://openalex.org/W4409883014","https://openalex.org/W6620707391","https://openalex.org/W6751420435","https://openalex.org/W6777265123","https://openalex.org/W6790019176","https://openalex.org/W6791353385","https://openalex.org/W6802517928","https://openalex.org/W6845484831","https://openalex.org/W6856826615","https://openalex.org/W6859113653"],"related_works":["https://openalex.org/W3019875293","https://openalex.org/W2351746492","https://openalex.org/W2367621846","https://openalex.org/W2394096350","https://openalex.org/W2091742426","https://openalex.org/W2365662948","https://openalex.org/W1988910916","https://openalex.org/W2380430606","https://openalex.org/W4360597343","https://openalex.org/W4287151890"],"abstract_inverted_index":{"Pre-trained":[0],"vision-language":[1],"models":[2],"(PVLMs)":[3],"and":[4,38,79,135,146,149],"pseudo-labeling":[5],"have":[6],"proven":[7],"effective":[8],"in":[9,34,111],"open-vocabulary":[10],"object":[11],"detection":[12,40,125,152],"(OVD).":[13],"However,":[14],"when":[15],"PVLMs":[16,68],"trained":[17],"on":[18,132],"image-text":[19],"data":[20],"are":[21,69,108],"adapted":[22],"for":[23,127],"OVD":[24],"tasks,":[25],"they":[26,72],"often":[27],"encounter":[28],"challenges":[29],"with":[30],"region-text":[31],"misalignment,":[32],"resulting":[33],"low-quality":[35],"pseudo-labels":[36,90],"(PLs)":[37],"suboptimal":[39],"performance.":[41,153],"In":[42],"this":[43],"paper,":[44],"we":[45,87],"introduce":[46],"a":[47,81],"Confusion-aware":[48],"Prototypical":[49],"Contrastive":[50],"Learning":[51],"(CPCL)":[52],"method":[53,141],"to":[54,94,116,123],"address":[55],"these":[56],"issues.":[57],"Our":[58],"key":[59],"observation":[60],"is":[61],"that":[62,139],"while":[63],"most":[64],"PLs":[65],"generated":[66],"by":[67],"correctly":[70],"classified,":[71],"still":[73],"suffer":[74],"from":[75],"low":[76],"inter-class":[77,144],"separability":[78,145],"contain":[80],"small":[82],"amount":[83],"of":[84,101],"noise.":[85],"Therefore,":[86],"first":[88],"cluster":[89],"within":[91],"each":[92],"category":[93,96,106],"obtain":[95],"prototypes,":[97],"reducing":[98],"the":[99,133],"impact":[100],"noise":[102],"during":[103],"training.":[104],"These":[105],"prototypes":[107],"then":[109],"used":[110],"confusion-aware":[112],"prototypical":[113],"contrastive":[114],"learning":[115],"effectively":[117],"decrease":[118],"inference":[119],"confusion":[120],"probabilities,":[121],"leading":[122],"improved":[124],"accuracy":[126],"novel":[128],"categories.":[129],"Extensive":[130],"experiments":[131],"COCO":[134],"LVIS-v1":[136],"benchmarks":[137],"demonstrate":[138],"our":[140],"significantly":[142],"enhances":[143],"achieves":[147],"competitive,":[148],"even":[150],"state-of-the-art":[151]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}