{"id":"https://openalex.org/W7137965875","doi":"https://doi.org/10.1609/aaai.v40i9.37618","title":"Tensor Decomposition and Language Description for Open-Vocabulary Object Detection","display_name":"Tensor Decomposition and Language Description for Open-Vocabulary Object Detection","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137965875","doi":"https://doi.org/10.1609/aaai.v40i9.37618"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i9.37618","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i9.37618","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37618/41580","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37618/41580","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129749630","display_name":"Qiuyu Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiuyu Liang","raw_affiliation_strings":["College of Computer Science, Inner Mongolia University, Hohhot, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129752941","display_name":"Yongqiang Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongqiang Zhang","raw_affiliation_strings":["College of Computer Science, Inner Mongolia University, Hohhot, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2722730"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18945869,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"9","first_page":"6853","last_page":"6861"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8669000267982483,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8669000267982483,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.056699998676776886,"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/T10028","display_name":"Topic Modeling","score":0.015300000086426735,"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/discriminative-model","display_name":"Discriminative model","score":0.7784000039100647},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.6169999837875366},{"id":"https://openalex.org/keywords/singular-value-decomposition","display_name":"Singular value decomposition","score":0.5720999836921692},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5253999829292297},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5131999850273132},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5078999996185303},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.47609999775886536},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.4478999972343445},{"id":"https://openalex.org/keywords/completeness","display_name":"Completeness (order theory)","score":0.42899999022483826}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7784000039100647},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6601999998092651},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6389999985694885},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.6169999837875366},{"id":"https://openalex.org/C22789450","wikidata":"https://www.wikidata.org/wiki/Q420904","display_name":"Singular value decomposition","level":2,"score":0.5720999836921692},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5253999829292297},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5131999850273132},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5078999996185303},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47609999775886536},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.4478999972343445},{"id":"https://openalex.org/C17231256","wikidata":"https://www.wikidata.org/wiki/Q5156540","display_name":"Completeness (order theory)","level":2,"score":0.42899999022483826},{"id":"https://openalex.org/C42704193","wikidata":"https://www.wikidata.org/wiki/Q7851097","display_name":"Tucker decomposition","level":4,"score":0.4203999936580658},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4081000089645386},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.3955000042915344},{"id":"https://openalex.org/C154771677","wikidata":"https://www.wikidata.org/wiki/Q17098361","display_name":"K-SVD","level":3,"score":0.3837999999523163},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36970001459121704},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3562999963760376},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.34790000319480896},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.32269999384880066},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3176000118255615},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.3098999857902527},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.30250000953674316},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.2930000126361847},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.25589999556541443}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i9.37618","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i9.37618","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37618/41580","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/37618","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37618","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i9.37618","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i9.37618","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37618/41580","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6774558424949646}],"awards":[{"id":"https://openalex.org/G4168310557","display_name":null,"funder_award_id":"62206077","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/F4320322216","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496"},{"id":"https://openalex.org/F4320322868","display_name":"Natural Science Foundation of Inner Mongolia","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7137965875.pdf","grobid_xml":"https://content.openalex.org/works/W7137965875.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Open-vocabulary":[0],"object":[1,63,81],"detection":[2],"(OVOD)":[3],"aims":[4],"at":[5],"detecting":[6],"and":[7,19,41,58,112,128,137,156,165,231,237],"recognizing":[8],"objects":[9],"beyond":[10],"a":[11,27,94,148,193],"fixed":[12],"set":[13],"of":[14,104,116,132,190,204,210,223],"classes.":[15],"Although":[16],"region-word":[17,86],"alignment":[18,133],"knowledge":[20,144,181,203],"distillation":[21,151,167],"have":[22],"been":[23],"explored":[24],"for":[25,61],"training":[26],"strong":[28],"open-vocabulary":[29,62],"detector,":[30],"our":[31,224],"analysis":[32],"reveals":[33],"three":[34],"main":[35],"issues":[36],"(inaccurate":[37],"alignment,":[38],"redundant":[39,143],"distillation,":[40],"low-quality":[42],"class":[43,191],"embedding)":[44],"that":[45,99,153,174],"limit":[46],"OVOD's":[47],"performance.":[48],"In":[49],"this":[50,90],"paper,":[51],"we":[52,92,146],"explore":[53],"the":[54,69,102,114,122,130,175,178,183,188,202,208,220],"well-designed":[55],"Tensor":[56],"decomposition":[57,111,164],"Language":[59],"descriptions":[60],"Detection":[64],"(called":[65],"TLDet).":[66],"Proposals":[67],"with":[68],"highest":[70],"similarity":[71],"score":[72],"often":[73],"correspond":[74],"to":[75,124,141,186,206],"discriminative":[76,126],"but":[77],"incomplete":[78],"regions":[79,136],"(e.g.,":[80],"heads),":[82],"resulting":[83],"in":[84],"inaccurate":[85],"alignment.":[87,171],"To":[88],"mitigate":[89,142],"issue,":[91],"propose":[93],"low-rank":[95],"proposal":[96,106],"filtering":[97],"module":[98],"quantitatively":[100],"assesses":[101],"completeness":[103],"each":[105],"by":[107,200],"performing":[108],"singular":[109,118],"value":[110],"computing":[113],"sum":[115],"its":[117],"values.":[119],"This":[120,172],"allows":[121],"model":[123],"reduce":[125],"proposals":[127],"enhance":[129],"precision":[131],"between":[134],"visual":[135],"textual":[138],"concepts.":[139],"Furthermore,":[140],"transfer,":[145],"introduce":[147],"core":[149,160],"tensor":[150,170],"approach":[152],"decomposes":[154],"teacher":[155],"student":[157,176],"features":[158],"into":[159],"tensors":[161],"via":[162],"Tucker":[163],"performs":[166],"through":[168],"optimized":[169],"ensures":[173],"acquires":[177],"most":[179],"essential":[180],"from":[182],"teacher.":[184],"Finally,":[185],"improve":[187],"quality":[189],"embedding,":[192],"language":[194],"description":[195],"enhancement":[196],"method":[197],"is":[198],"proposed":[199],"exploring":[201],"LLM":[205],"enrich":[207],"representations":[209],"categories":[211],"during":[212],"inference.":[213],"Extensive":[214],"experiments":[215],"on":[216,229,235,241],"popular":[217],"datasets":[218],"demonstrate":[219],"superior":[221],"performance":[222],"TLDet,":[225],"achieving":[226],"36.1%":[227],"mAP":[228,234],"COCO":[230],"30.1%":[232],"mask":[233],"LVIS,":[236],"outperforming":[238],"existing":[239],"methods":[240],"novel":[242],"categories.":[243]},"counts_by_year":[],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2026-03-18T00:00:00"}