{"id":"https://openalex.org/W4392910566","doi":"https://doi.org/10.1109/icassp48485.2024.10447716","title":"Mask6D: Masked Pose Priors for 6D Object Pose Estimation","display_name":"Mask6D: Masked Pose Priors for 6D Object Pose Estimation","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392910566","doi":"https://doi.org/10.1109/icassp48485.2024.10447716"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447716","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447716","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.06486","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030841930","display_name":"Yuechen Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuechen Xie","raw_affiliation_strings":["Nanjing University of Science and Technology,PCA Lab, School of Computer Science and Engineering,Nanjing,China","PCA Lab, School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology,PCA Lab, School of Computer Science and Engineering,Nanjing,China","institution_ids":["https://openalex.org/I36399199"]},{"raw_affiliation_string":"PCA Lab, School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051412865","display_name":"Haobo Jiang","orcid":"https://orcid.org/0000-0003-1357-1315"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haobo Jiang","raw_affiliation_strings":["Nanjing University of Science and Technology,PCA Lab, School of Computer Science and Engineering,Nanjing,China","PCA Lab, School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology,PCA Lab, School of Computer Science and Engineering,Nanjing,China","institution_ids":["https://openalex.org/I36399199"]},{"raw_affiliation_string":"PCA Lab, School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089409762","display_name":"Jin Xie","orcid":"https://orcid.org/0000-0001-6978-8834"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Xie","raw_affiliation_strings":["Nanjing University of Science and Technology,PCA Lab, School of Computer Science and Engineering,Nanjing,China","PCA Lab, School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology,PCA Lab, School of Computer Science and Engineering,Nanjing,China","institution_ids":["https://openalex.org/I36399199"]},{"raw_affiliation_string":"PCA Lab, School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I36399199"],"apc_list":null,"apc_paid":null,"fwci":0.8238,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.70578536,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3545","last_page":"3549"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9869999885559082,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9869999885559082,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9704999923706055,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9641000032424927,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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":0.8430683016777039},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.7572824954986572},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6662296056747437},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6043444275856018},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5681813955307007},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5664691925048828},{"id":"https://openalex.org/keywords/3d-pose-estimation","display_name":"3D pose estimation","score":0.5084789991378784},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.4580570161342621},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4115429222583771},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40183496475219727},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.08819648623466492},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07320365309715271}],"concepts":[{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.8430683016777039},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.7572824954986572},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6662296056747437},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6043444275856018},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5681813955307007},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5664691925048828},{"id":"https://openalex.org/C36613465","wikidata":"https://www.wikidata.org/wiki/Q4636322","display_name":"3D pose estimation","level":3,"score":0.5084789991378784},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.4580570161342621},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4115429222583771},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40183496475219727},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.08819648623466492},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07320365309715271},{"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/icassp48485.2024.10447716","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447716","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.06486","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.06486","pdf_url":"https://arxiv.org/pdf/2507.06486","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.06486","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.06486","pdf_url":"https://arxiv.org/pdf/2507.06486","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1526868886","https://openalex.org/W2058761328","https://openalex.org/W2133665775","https://openalex.org/W2344474200","https://openalex.org/W2472269674","https://openalex.org/W2574567538","https://openalex.org/W2950921159","https://openalex.org/W2962783853","https://openalex.org/W2963188159","https://openalex.org/W2963217716","https://openalex.org/W2963756608","https://openalex.org/W2989915422","https://openalex.org/W3027201070","https://openalex.org/W3035355652","https://openalex.org/W3092774272","https://openalex.org/W3094502228","https://openalex.org/W3177069133","https://openalex.org/W3193676140","https://openalex.org/W4236965008","https://openalex.org/W4280496682","https://openalex.org/W4295312788","https://openalex.org/W4312685069","https://openalex.org/W4313156423","https://openalex.org/W6763422710","https://openalex.org/W6766978945","https://openalex.org/W6784333009","https://openalex.org/W6838393215"],"related_works":["https://openalex.org/W4253893311","https://openalex.org/W3089306886","https://openalex.org/W2113785214","https://openalex.org/W2798721181","https://openalex.org/W3201205132","https://openalex.org/W4312694060","https://openalex.org/W4386075737","https://openalex.org/W4393563475","https://openalex.org/W4387967917","https://openalex.org/W4382141741"],"abstract_inverted_index":{"Robust":[0],"6D":[1],"object":[2,98],"pose":[3,23,58,105,154,159,166,177],"estimation":[4,24,178],"in":[5,48,110],"cluttered":[6,49,127],"or":[7],"occluded":[8],"conditions":[9],"using":[10,32],"monocular":[11],"RGB":[12,40,83],"images":[13,84],"remains":[14],"a":[15,56,95],"challenging":[16],"task.":[17],"One":[18],"reason":[19],"is":[20,42,80,137],"that":[21,171],"current":[22],"networks":[25],"struggle":[26],"to":[27,45,100,125,139,144,162],"extract":[28],"discriminative,":[29],"pose-aware":[30,67],"features":[31],"2D":[33,101],"feature":[34],"backbones,":[35],"especially":[36],"when":[37],"the":[38,86,104,108,115,146,164],"available":[39],"information":[41,106],"limited":[43],"due":[44],"target":[46,109],"occlusion":[47],"scenes.":[50],"To":[51],"mitigate":[52],"this,":[53],"we":[54,150],"propose":[55],"novel":[57],"estimation-specific":[59],"pre-training":[60,134],"strategy":[61,161],"named":[62],"Mask6D.":[63],"Our":[64],"approach":[65],"incorporates":[66],"2D-3D":[68,92],"correspondence":[69,93],"maps":[70,74,94],"and":[71],"visible":[72,117],"mask":[73,118],"as":[75],"additional":[76],"modal":[77],"information,":[78],"which":[79],"combined":[81],"with":[82],"for":[85],"reconstruction-based":[87],"model":[88,99,124],"pre-training.":[89],"Essentially,":[90],"this":[91],"transformed":[96],"3D":[97],"pixels,":[102],"reflecting":[103],"of":[107],"camera":[111],"coordinate":[112],"system.":[113],"Meanwhile,":[114],"integrated":[116],"map":[119],"can":[120],"effectively":[121],"guide":[122],"our":[123,142,152,172],"disregard":[126],"background":[128,147],"information.":[129],"In":[130],"addition,":[131],"an":[132],"object-focused":[133],"loss":[135],"function":[136],"designed":[138],"further":[140],"facilitate":[141],"network":[143,156],"remove":[145],"interference.":[148],"Finally,":[149],"fine-tune":[151],"pre-trained":[153],"prior-aware":[155],"via":[157],"conventional":[158],"training":[160],"realize":[163],"reliable":[165],"prediction.":[167],"Extensive":[168],"experiments":[169],"verify":[170],"method":[173],"outperforms":[174],"previous":[175],"end-to-end":[176],"methods.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}