{"id":"https://openalex.org/W4402455728","doi":"https://doi.org/10.1145/3695877","title":"Category-Level Pose Estimation and Iterative Refinement for Monocular RGB-D Image","display_name":"Category-Level Pose Estimation and Iterative Refinement for Monocular RGB-D Image","publication_year":2024,"publication_date":"2024-09-11","ids":{"openalex":"https://openalex.org/W4402455728","doi":"https://doi.org/10.1145/3695877"},"language":"en","primary_location":{"id":"doi:10.1145/3695877","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3695877","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"type":"article","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/A5085055482","display_name":"Yongtang Bao","orcid":"https://orcid.org/0000-0002-1010-7229"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongtang Bao","raw_affiliation_strings":["Shandong University of Science and Technology, Qingdao, China","College of Computer Science and Engineering, Shandong University of Science and Technology, China"],"raw_orcid":"https://orcid.org/0000-0002-1010-7229","affiliations":[{"raw_affiliation_string":"Shandong University of Science and Technology, Qingdao, China","institution_ids":["https://openalex.org/I80143920"]},{"raw_affiliation_string":"College of Computer Science and Engineering, Shandong University of Science and Technology, China","institution_ids":["https://openalex.org/I80143920"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037497070","display_name":"Chunjian Su","orcid":"https://orcid.org/0000-0001-6867-8246"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunjian Su","raw_affiliation_strings":["Shandong University of Science and Technology, Qingdao, China","College of Computer Science and Engineering, Shandong University of Science and Technology, China"],"raw_orcid":"https://orcid.org/0009-0003-3609-7676","affiliations":[{"raw_affiliation_string":"Shandong University of Science and Technology, Qingdao, China","institution_ids":["https://openalex.org/I80143920"]},{"raw_affiliation_string":"College of Computer Science and Engineering, Shandong University of Science and Technology, China","institution_ids":["https://openalex.org/I80143920"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112388647","display_name":"Yutong Qi","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]},{"id":"https://openalex.org/I2799376586","display_name":"The Scarborough Hospital","ror":"https://ror.org/04pzgb662","country_code":"CA","type":"healthcare","lineage":["https://openalex.org/I2799376586"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yutong Qi","raw_affiliation_strings":["University of Toronto, Scarborough, ON, Canada","Department of Computer and Mathematical Sciences, University of Toronto, Canada"],"raw_orcid":"https://orcid.org/0009-0008-8887-6854","affiliations":[{"raw_affiliation_string":"University of Toronto, Scarborough, ON, Canada","institution_ids":["https://openalex.org/I185261750","https://openalex.org/I2799376586"]},{"raw_affiliation_string":"Department of Computer and Mathematical Sciences, University of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yanbing Geng","orcid":"https://orcid.org/0009-0004-6971-3276"},"institutions":[{"id":"https://openalex.org/I135714990","display_name":"North University of China","ror":"https://ror.org/047bp1713","country_code":"CN","type":"education","lineage":["https://openalex.org/I135714990"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanbing Geng","raw_affiliation_strings":["North University of China, Taiyuan, China","School of Data Science and Technology, North University of China, China"],"raw_orcid":"https://orcid.org/0009-0004-6971-3276","affiliations":[{"raw_affiliation_string":"North University of China, Taiyuan, China","institution_ids":["https://openalex.org/I135714990"]},{"raw_affiliation_string":"School of Data Science and Technology, North University of China, China","institution_ids":["https://openalex.org/I135714990"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015789205","display_name":"Haojie Li","orcid":"https://orcid.org/0009-0007-0334-3681"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haojie Li","raw_affiliation_strings":["Shandong University of Science and Technology, Qingdao, China","College of Computer Science and Engineering, Shandong University of Science and Technology, China"],"raw_orcid":"https://orcid.org/0009-0007-0334-3681","affiliations":[{"raw_affiliation_string":"Shandong University of Science and Technology, Qingdao, China","institution_ids":["https://openalex.org/I80143920"]},{"raw_affiliation_string":"College of Computer Science and Engineering, Shandong University of Science and Technology, China","institution_ids":["https://openalex.org/I80143920"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.1704,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.92632036,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"20","issue":"12","first_page":"1","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T12549","display_name":"Image and Object Detection Techniques","score":0.9991999864578247,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9990000128746033,"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/computer-science","display_name":"Computer science","score":0.8556968569755554},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6896557807922363},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6708856225013733},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.5630276799201965},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.5580009818077087},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.5177778005599976}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8556968569755554},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6896557807922363},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6708856225013733},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.5630276799201965},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.5580009818077087},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.5177778005599976}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3695877","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3695877","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G781428067","display_name":null,"funder_award_id":"62072020","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1530404542","https://openalex.org/W2026644205","https://openalex.org/W2128019145","https://openalex.org/W2186222003","https://openalex.org/W2194775991","https://openalex.org/W2560023338","https://openalex.org/W2949924544","https://openalex.org/W2963150697","https://openalex.org/W2963188159","https://openalex.org/W2963264709","https://openalex.org/W2963892972","https://openalex.org/W3034986117","https://openalex.org/W3035355652","https://openalex.org/W3035398346","https://openalex.org/W3045696934","https://openalex.org/W3100922749","https://openalex.org/W3110923198","https://openalex.org/W3112108866","https://openalex.org/W3130138602","https://openalex.org/W3163945288","https://openalex.org/W3168682287","https://openalex.org/W3175844808","https://openalex.org/W3193676140","https://openalex.org/W3196328566","https://openalex.org/W3202459445","https://openalex.org/W3202538459","https://openalex.org/W4205105995","https://openalex.org/W4221025196","https://openalex.org/W4226321491","https://openalex.org/W4236965008","https://openalex.org/W4241614188","https://openalex.org/W4283726734","https://openalex.org/W4283775758","https://openalex.org/W4285048978","https://openalex.org/W4312908079","https://openalex.org/W4316660744","https://openalex.org/W4320002827","https://openalex.org/W4327518030","https://openalex.org/W4385644316","https://openalex.org/W4386003392","https://openalex.org/W4386320409","https://openalex.org/W4391407216","https://openalex.org/W4392223601","https://openalex.org/W4396753489","https://openalex.org/W6600137863"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Category-level":[0],"pose":[1,9,36,79,125,149],"estimation":[2,37,80],"is":[3],"proposed":[4],"to":[5,52,59,66,89,93,105,119,137,168],"predict":[6],"the":[7,31,72,107,138,153,195,200],"6D":[8],"of":[10,33,109],"objects":[11],"under":[12],"a":[13,41,77,98,122,147,162],"specific":[14],"category":[15],"and":[16,27,56,81,101,126,142,156,175,190,199],"has":[17,38],"wide":[18],"applications":[19],"in":[20,44,184],"fields":[21],"such":[22],"as":[23],"robotics,":[24],"virtual":[25],"reality,":[26],"autonomous":[28],"driving.":[29],"With":[30],"development":[32],"VR/AR":[34],"technology,":[35],"gradually":[39],"become":[40],"research":[42],"hotspot":[43],"3D":[45],"scene":[46],"understanding.":[47],"However,":[48],"most":[49],"methods":[50],"fail":[51],"fully":[53],"utilize":[54],"geometric":[55,111],"color":[57,95,177],"information":[58,92,178],"solve":[60,71],"intra-class":[61],"shape":[62],"variations,":[63],"which":[64],"leads":[65],"inaccurate":[67],"prediction":[68],"results.":[69],"To":[70],"above":[73],"problems,":[74],"we":[75,114,145,160],"propose":[76],"novel":[78],"iterative":[82,103,131],"refinement":[83,132],"network,":[84],"use":[85,115],"an":[86,116,130],"attention":[87,166],"mechanism":[88],"fuse":[90],"multi-modal":[91],"obtain":[94],"features":[96,171,183],"after":[97],"coordinate":[99,164,186],"transformation,":[100],"design":[102,146,161],"modules":[104],"ensure":[106],"accuracy":[108],"object":[110],"features.":[112,158],"Specifically,":[113],"encoder-decoder":[117],"architecture":[118],"implicitly":[120],"generate":[121],"coarse-grained":[123],"initial":[124],"refine":[127],"it":[128],"through":[129],"module.":[133],"In":[134],"addition,":[135],"due":[136],"differences":[139],"between":[140],"rotation":[141],"position":[143],"estimation,":[144],"multi-head":[148],"decoder":[150],"that":[151,207],"utilizes":[152],"local":[154],"geometry":[155],"global":[157],"Finally,":[159],"transformer-based":[163],"transformation":[165],"module":[167],"extract":[169],"pose-sensitive":[170],"from":[172],"RGB":[173],"images":[174],"supervise":[176],"by":[179],"correlating":[180],"point":[181],"cloud":[182],"different":[185],"systems.":[187],"We":[188],"train":[189],"test":[191],"our":[192,208],"network":[193],"on":[194,213],"synthetic":[196],"dataset":[197,202],"CAMERA25":[198],"real":[201],"REAL275.":[203],"Experimental":[204],"results":[205],"show":[206],"method":[209],"achieves":[210],"state-of-the-art":[211],"performance":[212],"multiple":[214],"evaluation":[215],"metrics.":[216]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
