{"id":"https://openalex.org/W4392223601","doi":"https://doi.org/10.1109/tcsvt.2024.3397997","title":"CLIPose: Category-Level Object Pose Estimation With Pre-Trained Vision-Language Knowledge","display_name":"CLIPose: Category-Level Object Pose Estimation With Pre-Trained Vision-Language Knowledge","publication_year":2024,"publication_date":"2024-05-08","ids":{"openalex":"https://openalex.org/W4392223601","doi":"https://doi.org/10.1109/tcsvt.2024.3397997"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2024.3397997","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3397997","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2402.15726","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xiao Lin","orcid":"https://orcid.org/0009-0000-9989-8233"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Lin","raw_affiliation_strings":["College of Electronics and Information Engineering, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0000-9989-8233","affiliations":[{"raw_affiliation_string":"College of Electronics and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103274374","display_name":"Minghao Zhu","orcid":"https://orcid.org/0009-0008-0291-5841"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minghao Zhu","raw_affiliation_strings":["College of Electronics and Information Engineering, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0008-0291-5841","affiliations":[{"raw_affiliation_string":"College of Electronics and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020099966","display_name":"Ronghao Dang","orcid":"https://orcid.org/0000-0003-1176-3735"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ronghao Dang","raw_affiliation_strings":["College of Electronics and Information Engineering, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-1176-3735","affiliations":[{"raw_affiliation_string":"College of Electronics and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059751345","display_name":"Guangliang Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangliang Zhou","raw_affiliation_strings":["College of Electronics and Information Engineering, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-7845-7068","affiliations":[{"raw_affiliation_string":"College of Electronics and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068080569","display_name":"Shaolong Shu","orcid":"https://orcid.org/0000-0001-7343-1782"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaolong Shu","raw_affiliation_strings":["College of Electronics and Information Engineering, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-7343-1782","affiliations":[{"raw_affiliation_string":"College of Electronics and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Feng Lin","orcid":"https://orcid.org/0000-0002-6831-4458"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Lin","raw_affiliation_strings":["College of Electronics and Information Engineering, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-6831-4458","affiliations":[{"raw_affiliation_string":"College of Electronics and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037285766","display_name":"Chengju Liu","orcid":"https://orcid.org/0000-0001-7543-0855"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengju Liu","raw_affiliation_strings":["College of Electronics and Information Engineering, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-7543-0855","affiliations":[{"raw_affiliation_string":"College of Electronics and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073789459","display_name":"Qijun Chen","orcid":"https://orcid.org/0000-0001-5644-1188"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qijun Chen","raw_affiliation_strings":["College of Electronics and Information Engineering, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-5644-1188","affiliations":[{"raw_affiliation_string":"College of Electronics and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":null,"apc_paid":null,"fwci":3.6609,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.94523632,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"34","issue":"10","first_page":"9125","last_page":"9138"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9889000058174133,"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":0.9889000058174133,"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/T12874","display_name":"Digital Imaging for Blood Diseases","score":0.9865000247955322,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9768999814987183,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.6819342374801636},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6188080906867981},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6177709698677063},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5785974264144897},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5104924440383911},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4857516884803772},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.46945279836654663},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3205331563949585},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10732650756835938}],"concepts":[{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.6819342374801636},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6188080906867981},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6177709698677063},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5785974264144897},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5104924440383911},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4857516884803772},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.46945279836654663},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3205331563949585},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10732650756835938},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcsvt.2024.3397997","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3397997","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2402.15726","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.15726","pdf_url":"https://arxiv.org/pdf/2402.15726","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2402.15726","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.15726","pdf_url":"https://arxiv.org/pdf/2402.15726","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7699999809265137}],"awards":[{"id":"https://openalex.org/G2581980031","display_name":null,"funder_award_id":"62073245","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6265052862","display_name":null,"funder_award_id":"22511104900","funder_id":"https://openalex.org/F4320336612","funder_display_name":"Science and Technology Innovation Foundation of Harbin"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320336612","display_name":"Science and Technology Innovation Foundation of Harbin","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W1920022804","https://openalex.org/W2101199297","https://openalex.org/W2128019145","https://openalex.org/W2344474200","https://openalex.org/W2472269674","https://openalex.org/W2555618208","https://openalex.org/W2798991696","https://openalex.org/W2963150697","https://openalex.org/W2963177347","https://openalex.org/W2963188159","https://openalex.org/W2963756608","https://openalex.org/W2963892972","https://openalex.org/W2979579363","https://openalex.org/W3034597466","https://openalex.org/W3035398346","https://openalex.org/W3035524453","https://openalex.org/W3107992529","https://openalex.org/W3108655343","https://openalex.org/W3163945288","https://openalex.org/W3179923621","https://openalex.org/W3193686508","https://openalex.org/W3202459445","https://openalex.org/W3202538459","https://openalex.org/W3205341492","https://openalex.org/W4205274304","https://openalex.org/W4226255121","https://openalex.org/W4226321491","https://openalex.org/W4280533594","https://openalex.org/W4283838088","https://openalex.org/W4312270234","https://openalex.org/W4312296985","https://openalex.org/W4312604533","https://openalex.org/W4312651322","https://openalex.org/W4312818263","https://openalex.org/W4312956471","https://openalex.org/W4312980231","https://openalex.org/W4313027996","https://openalex.org/W4313189197","https://openalex.org/W4313427326","https://openalex.org/W4385245566","https://openalex.org/W4386075656","https://openalex.org/W4386076097","https://openalex.org/W4386320409","https://openalex.org/W4387831730","https://openalex.org/W4387969371","https://openalex.org/W4388266322","https://openalex.org/W4389665527","https://openalex.org/W4390873470","https://openalex.org/W4399419060","https://openalex.org/W6638157756","https://openalex.org/W6754677871","https://openalex.org/W6790453339","https://openalex.org/W6791353385","https://openalex.org/W6798805250","https://openalex.org/W6803063336","https://openalex.org/W6811072154","https://openalex.org/W6811433417","https://openalex.org/W6846948935","https://openalex.org/W6853127316","https://openalex.org/W6857247053","https://openalex.org/W6857735095","https://openalex.org/W6858492201","https://openalex.org/W6859428516","https://openalex.org/W7037203704"],"related_works":["https://openalex.org/W2123263858","https://openalex.org/W3127959533","https://openalex.org/W2894986065","https://openalex.org/W4387967917","https://openalex.org/W4287600488","https://openalex.org/W4386925306","https://openalex.org/W4387968151","https://openalex.org/W2736638679","https://openalex.org/W4313046826","https://openalex.org/W1968716783"],"abstract_inverted_index":{"Most":[0],"of":[1,22,32,64,93,122,139],"existing":[2],"category-level":[3],"object":[4,12,94],"pose":[5,81,152],"estimation":[6],"methods":[7],"devote":[8],"to":[9,28,56,67,89,134,147,161],"learning":[10,92],"the":[11,20,29,39,85,111,136,140,173],"category":[13,40,69,95],"information":[14,171],"from":[15,43],"point":[16,46],"cloud":[17,47],"modality.":[18],"However,":[19],"scale":[21],"3D":[23,33,112],"datasets":[24],"is":[25],"limited":[26,45],"due":[27],"high":[30],"cost":[31],"data":[34],"collection":[35],"and":[36,106,169,186,188],"annotation.":[37],"Consequently,":[38],"features":[41,116],"extracted":[42],"these":[44],"samples":[48],"may":[49],"not":[50],"be":[51,148],"comprehensive.":[52],"This":[53],"motivates":[54],"us":[55],"investigate":[57],"whether":[58],"we":[59,75,119,143,155,166],"can":[60,98],"draw":[61],"on":[62,180],"knowledge":[63,103,138],"other":[65],"modalities":[66,124],"obtain":[68],"information.":[70],"Inspired":[71],"by":[72],"this":[73],"motivation,":[74],"propose":[76],"CLIPose,":[77],"a":[78,157],"novel":[79],"6D":[80],"framework":[82],"that":[83],"employs":[84],"pre-trained":[86,137],"vision-language":[87],"model":[88],"develop":[90],"better":[91],"information,":[96],"which":[97],"fully":[99],"leverage":[100],"abundant":[101],"semantic":[102],"in":[104,125,172,190],"image":[105,163],"text":[107,174],"modalities.":[108],"To":[109],"make":[110],"encoder":[113,164],"learn":[114],"category-specific":[115],"more":[117,149],"efficiently,":[118],"align":[120],"representations":[121],"three":[123],"feature":[126],"space":[127],"via":[128],"multi-modal":[129],"contrastive":[130],"learning.":[131],"In":[132],"addition":[133],"exploiting":[135],"CLIP\u2019s":[141],"model,":[142],"also":[144],"expect":[145],"it":[146],"sensitive":[150],"with":[151],"parameters.":[153],"Therefore,":[154],"introduce":[156],"prompt":[158],"tuning":[159],"approach":[160],"fine-tune":[162],"while":[165],"incorporate":[167],"rotations":[168],"translations":[170],"descriptions.":[175],"CLIPose":[176],"achieves":[177],"state-of-the-art":[178],"performance":[179],"two":[181],"mainstream":[182],"benchmark":[183],"datasets,":[184],"REAL275":[185],"CAMERA25,":[187],"runs":[189],"real-time":[191],"during":[192],"inference":[193],"(40FPS).":[194]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2024-02-28T00:00:00"}