{"id":"https://openalex.org/W4403863315","doi":"https://doi.org/10.1109/tip.2024.3485518","title":"Exploring Multi-Modal Contextual Knowledge for Open-Vocabulary Object Detection","display_name":"Exploring Multi-Modal Contextual Knowledge for Open-Vocabulary Object Detection","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4403863315","doi":"https://doi.org/10.1109/tip.2024.3485518","pmid":"https://pubmed.ncbi.nlm.nih.gov/39471119"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2024.3485518","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2024.3485518","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5103166791","display_name":"Yifan Xu","orcid":"https://orcid.org/0000-0003-2467-888X"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Xu","raw_affiliation_strings":["MAIS, Institute of Automation, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2467-888X","affiliations":[{"raw_affiliation_string":"MAIS, Institute of Automation, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026072498","display_name":"Mengdan Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengdan Zhang","raw_affiliation_strings":["Tencent Youtu Laboratory, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Youtu Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083991825","display_name":"Xiaoshan Yang","orcid":"https://orcid.org/0000-0001-5453-9755"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoshan Yang","raw_affiliation_strings":["MAIS, Institute of Automation, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5453-9755","affiliations":[{"raw_affiliation_string":"MAIS, Institute of Automation, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022636178","display_name":"Changsheng Xu","orcid":"https://orcid.org/0000-0001-8343-9665"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changsheng Xu","raw_affiliation_strings":["MAIS, Institute of Automation, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8343-9665","affiliations":[{"raw_affiliation_string":"MAIS, Institute of Automation, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1114,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.81784831,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"33","issue":null,"first_page":"6253","last_page":"6267"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9916999936103821,"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":0.9916999936103821,"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":0.9115999937057495,"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":0.7067299485206604},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6168254017829895},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6050221920013428},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5251940488815308},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5156742334365845},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4801428020000458},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4524948298931122},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44342294335365295},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36360496282577515},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2081451416015625}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7067299485206604},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6168254017829895},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6050221920013428},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5251940488815308},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5156742334365845},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4801428020000458},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4524948298931122},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44342294335365295},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36360496282577515},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2081451416015625},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2024.3485518","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2024.3485518","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},{"id":"pmid:39471119","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39471119","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8199999928474426,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1100260481","display_name":null,"funder_award_id":"62072455","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1498893086","display_name":null,"funder_award_id":"62036012","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1692201237","display_name":null,"funder_award_id":"PCL2023A08","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2246614840","display_name":null,"funder_award_id":"2021ZD0112200","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"},{"id":"https://openalex.org/G3087610523","display_name":null,"funder_award_id":"U23A20387","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6544960559","display_name":null,"funder_award_id":"62322212","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"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":102,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W753847829","https://openalex.org/W1821462560","https://openalex.org/W1861492603","https://openalex.org/W1889081078","https://openalex.org/W1933349210","https://openalex.org/W2160709761","https://openalex.org/W2185175083","https://openalex.org/W2250378130","https://openalex.org/W2277195237","https://openalex.org/W2543539599","https://openalex.org/W2560730294","https://openalex.org/W2886641317","https://openalex.org/W2896457183","https://openalex.org/W2948672349","https://openalex.org/W2963115613","https://openalex.org/W2963518342","https://openalex.org/W2963603913","https://openalex.org/W2963936013","https://openalex.org/W2968124245","https://openalex.org/W2969876226","https://openalex.org/W2970454332","https://openalex.org/W2983943451","https://openalex.org/W2988823324","https://openalex.org/W2998356391","https://openalex.org/W3035323998","https://openalex.org/W3138006590","https://openalex.org/W3159619744","https://openalex.org/W3173859428","https://openalex.org/W3188427387","https://openalex.org/W3206072662","https://openalex.org/W3209859545","https://openalex.org/W4205581758","https://openalex.org/W4221138453","https://openalex.org/W4224304134","https://openalex.org/W4225385394","https://openalex.org/W4283397426","https://openalex.org/W4284961860","https://openalex.org/W4286837396","https://openalex.org/W4288083516","https://openalex.org/W4293390340","https://openalex.org/W4295036294","https://openalex.org/W4295751877","https://openalex.org/W4296605949","https://openalex.org/W4298331175","https://openalex.org/W4306168147","https://openalex.org/W4310418579","https://openalex.org/W4310557340","https://openalex.org/W4312424618","https://openalex.org/W4312559104","https://openalex.org/W4312563428","https://openalex.org/W4312691946","https://openalex.org/W4312747482","https://openalex.org/W4312764321","https://openalex.org/W4312773012","https://openalex.org/W4312804044","https://openalex.org/W4312877428","https://openalex.org/W4312890493","https://openalex.org/W4312925417","https://openalex.org/W4312956471","https://openalex.org/W4313139298","https://openalex.org/W4313156423","https://openalex.org/W4313350245","https://openalex.org/W4313506322","https://openalex.org/W4378945335","https://openalex.org/W4383337770","https://openalex.org/W4384080288","https://openalex.org/W4385245566","https://openalex.org/W4385696173","https://openalex.org/W4386066010","https://openalex.org/W4386071855","https://openalex.org/W4386076029","https://openalex.org/W4386076396","https://openalex.org/W4392873856","https://openalex.org/W4402727200","https://openalex.org/W4402727806","https://openalex.org/W4402727842","https://openalex.org/W6639432524","https://openalex.org/W6691815588","https://openalex.org/W6755207826","https://openalex.org/W6766904570","https://openalex.org/W6767211374","https://openalex.org/W6767279747","https://openalex.org/W6789753369","https://openalex.org/W6790019176","https://openalex.org/W6791353385","https://openalex.org/W6792148081","https://openalex.org/W6796792687","https://openalex.org/W6798805250","https://openalex.org/W6802517928","https://openalex.org/W6838901828","https://openalex.org/W6839632867","https://openalex.org/W6839701648","https://openalex.org/W6842874653","https://openalex.org/W6844432065","https://openalex.org/W6845484831","https://openalex.org/W6846977184","https://openalex.org/W6852789546","https://openalex.org/W6853781193","https://openalex.org/W6853887002","https://openalex.org/W6857911570","https://openalex.org/W6863011114"],"related_works":["https://openalex.org/W2349784553","https://openalex.org/W3022596247","https://openalex.org/W2601444686","https://openalex.org/W4307058054","https://openalex.org/W4292238148","https://openalex.org/W4323660495","https://openalex.org/W2385319785","https://openalex.org/W2900827440","https://openalex.org/W4292830139","https://openalex.org/W4319309705"],"abstract_inverted_index":{"We":[0],"explore":[1],"multi-modal":[2,7,64,101,153],"contextual":[3,65,126],"knowledge":[4,66],"learned":[5],"through":[6],"masked":[8,30,82,102],"language":[9,103],"modeling":[10,104,115],"to":[11,70,128],"provide":[12],"explicit":[13],"localization":[14],"guidance":[15,127],"for":[16],"novel":[17],"classes":[18],"in":[19,85,116],"open-vocabulary":[20],"object":[21],"detection":[22,146],"(OVD).":[23],"Intuitively,":[24],"a":[25,63,73,86],"well-modeled":[26],"and":[27,41,47],"correctly":[28],"predicted":[29],"concept":[31,83],"word":[32],"should":[33],"effectively":[34],"capture":[35],"the":[36,42,77,81,110,117,129,133,138,149],"textual":[37],"contexts,":[38,40],"visual":[39,113],"cross-modal":[43],"correspondence":[44],"between":[45],"texts":[46],"regions,":[48],"thereby":[49,135],"automatically":[50],"activating":[51],"high":[52],"attention":[53,79],"on":[54],"corresponding":[55],"regions.":[56],"In":[57],"light":[58],"of":[59,80,132,151],"this,":[60],"we":[61],"propose":[62],"distillation":[67,122],"framework,":[68],"MMC-Det,":[69],"explicitly":[71],"supervise":[72],"student":[74],"detector":[75],"with":[76,96],"context-aware":[78],"words":[84],"teacher":[87,91],"fusion":[88,92,118],"transformer.":[89,119],"The":[90,120],"transformer":[93],"is":[94],"trained":[95],"our":[97,152],"newly":[98],"proposed":[99,121],"diverse":[100],"(D-MLM)":[105],"strategy,":[106],"which":[107],"significantly":[108],"enhances":[109],"fine-grained":[111],"region-level":[112],"context":[114,154],"process":[123],"provides":[124],"additional":[125],"concept-region":[130],"matching":[131],"detector,":[134],"further":[136],"improving":[137],"OVD":[139],"performance.":[140],"Extensive":[141],"experiments":[142],"performed":[143],"upon":[144],"various":[145],"datasets":[147],"show":[148],"effectiveness":[150],"learning":[155],"strategy.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}