{"id":"https://openalex.org/W4392903769","doi":"https://doi.org/10.1109/icassp48485.2024.10447649","title":"Semi-Decoupled 6D Pose Estimation via Multi-Modal Feature Fusion","display_name":"Semi-Decoupled 6D Pose Estimation via Multi-Modal Feature Fusion","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903769","doi":"https://doi.org/10.1109/icassp48485.2024.10447649"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447649","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447649","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":["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/A5109692713","display_name":"Zhenhu Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]},{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]},{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhenhu Zhang","raw_affiliation_strings":["Zhejiang University,School of Software Technology,China","School of Software Technology, Zhejiang University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,School of Software Technology,China","institution_ids":["https://openalex.org/I55712492","https://openalex.org/I168879160"]},{"raw_affiliation_string":"School of Software Technology, Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009095415","display_name":"Xin Cao","orcid":"https://orcid.org/0000-0003-3560-6523"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Cao","raw_affiliation_strings":["Shandong University,School of Software,China","School of Software, Shandong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University,School of Software,China","institution_ids":["https://openalex.org/I154099455"]},{"raw_affiliation_string":"School of Software, Shandong University, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100781249","display_name":"Jin Li","orcid":"https://orcid.org/0000-0002-0260-3169"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Jin","raw_affiliation_strings":["Shandong University,School of Software,China","School of Software, Shandong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University,School of Software,China","institution_ids":["https://openalex.org/I154099455"]},{"raw_affiliation_string":"School of Software, Shandong University, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008274291","display_name":"Xueying Qin","orcid":"https://orcid.org/0000-0003-0057-295X"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueying Qin","raw_affiliation_strings":["Shandong University,School of Software,China","School of Software, Shandong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University,School of Software,China","institution_ids":["https://openalex.org/I154099455"]},{"raw_affiliation_string":"School of Software, Shandong University, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057181928","display_name":"Ruofeng Tong","orcid":"https://orcid.org/0000-0002-8167-5354"},"institutions":[{"id":"https://openalex.org/I132210918","display_name":"North China Institute of Science and Technology","ror":"https://ror.org/0096c7651","country_code":"CN","type":"education","lineage":["https://openalex.org/I132210918"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruofeng Tong","raw_affiliation_strings":["College of Computer Science and Technology,China","College of Computer Science and Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology,China","institution_ids":["https://openalex.org/I132210918"]},{"raw_affiliation_string":"College of Computer Science and Technology, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5109692713"],"corresponding_institution_ids":["https://openalex.org/I168879160","https://openalex.org/I55712492","https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.5868,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.64004399,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"2610","last_page":"2614"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9995999932289124,"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":0.9995999932289124,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9952999949455261,"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":0.9929999709129333,"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/point-cloud","display_name":"Point cloud","score":0.7907888889312744},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.748741626739502},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6776048541069031},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.6646704077720642},{"id":"https://openalex.org/keywords/rotation","display_name":"Rotation (mathematics)","score":0.6473357081413269},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.6353006362915039},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5739297866821289},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5396900177001953},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5346535444259644},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.5335676670074463},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5182473659515381},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.48044225573539734},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.4678279757499695},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4551903307437897},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34602946043014526},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.19277667999267578},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.0698438286781311}],"concepts":[{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.7907888889312744},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.748741626739502},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6776048541069031},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.6646704077720642},{"id":"https://openalex.org/C74050887","wikidata":"https://www.wikidata.org/wiki/Q848368","display_name":"Rotation (mathematics)","level":2,"score":0.6473357081413269},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.6353006362915039},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5739297866821289},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5396900177001953},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5346535444259644},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.5335676670074463},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5182473659515381},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.48044225573539734},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.4678279757499695},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4551903307437897},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34602946043014526},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.19277667999267578},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0698438286781311},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447649","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447649","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2440452572","display_name":null,"funder_award_id":"61972342","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5270119419","display_name":null,"funder_award_id":"62172260","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7596092009","display_name":"\u57fa\u4e8e\u89c6\u89c9\u8ba4\u77e5\u7684\u53ef\u89c6\u5a92\u4f53\u5408\u6210\u4e0e\u8bc4\u4ef7","funder_award_id":"61832016","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":19,"referenced_works":["https://openalex.org/W62794737","https://openalex.org/W132147841","https://openalex.org/W2058761328","https://openalex.org/W2344474200","https://openalex.org/W2962888833","https://openalex.org/W2963177347","https://openalex.org/W2963188159","https://openalex.org/W2963756608","https://openalex.org/W2981378444","https://openalex.org/W2989915422","https://openalex.org/W3004525945","https://openalex.org/W3009516594","https://openalex.org/W3034986117","https://openalex.org/W3035268949","https://openalex.org/W3035355652","https://openalex.org/W3179923621","https://openalex.org/W3194916214","https://openalex.org/W4280571998","https://openalex.org/W6773186523"],"related_works":["https://openalex.org/W4389574804","https://openalex.org/W2123263858","https://openalex.org/W3127959533","https://openalex.org/W3016928466","https://openalex.org/W2936725271","https://openalex.org/W3150655618","https://openalex.org/W3108295644","https://openalex.org/W1578717197","https://openalex.org/W2626737336","https://openalex.org/W4320086129"],"abstract_inverted_index":{"The":[0,105,137],"existing":[1],"methods":[2],"for":[3,70],"6D":[4,86],"pose":[5,87],"estimation":[6,88],"based":[7,116,149],"on":[8,117,150,157],"RGB-D":[9],"employ":[10],"RGB":[11],"images":[12],"and":[13,28,32,37,40,64,100,126,133,144],"observed":[14,56],"point":[15,57],"cloud":[16,58],"derived":[17],"from":[18,130],"depth":[19],"maps":[20],"as":[21],"input,":[22],"then":[23],"concurrently":[24],"predicting":[25,146],"both":[26],"rotation":[27,31,143],"translation.":[29],"However,":[30],"translation":[33],"possess":[34],"distinct":[35,152],"characteristics":[36],"scale":[38],"ranges,":[39],"their":[41,118,151],"simultaneous":[42],"prediction":[43,141],"can":[44],"lead":[45],"to":[46,61,73],"mutual":[47],"influence":[48],"in":[49,122],"the":[50,55,71,84,140,164],"network":[51,72],"parameter":[52],"space.":[53],"Additionally,":[54],"are":[59],"susceptible":[60],"systematic":[62,131],"noise":[63,132],"partial":[65,134],"data":[66,111,135],"loss,":[67],"presenting":[68],"challenges":[69],"capture":[74],"comprehensive":[75],"object":[76],"features.":[77],"To":[78],"address":[79],"these":[80],"issues,":[81],"we":[82],"propose":[83],"Semi-Decoupled":[85,102],"via":[89],"multi-modal":[90],"feature":[91],"fusion":[92],"(SD6D).":[93],"SD6D":[94],"comprises":[95],"a":[96,101],"Multi-Modal":[97],"Fusion":[98],"Module":[99],"Prediction":[103],"Module.":[104],"former":[106],"dynamically":[107],"fuses":[108],"different":[109],"modal":[110],"(RGB,":[112],"depth,":[113],"CAD":[114],"model)":[115],"inter-modality":[119],"correlations,":[120],"aiding":[121],"establishing":[123],"2D-3D":[124],"correspondences":[125],"addressing":[127],"issues":[128],"stemming":[129],"loss.":[136],"latter":[138],"semi-decouples":[139],"of":[142,166],"translation,":[145],"them":[147],"separately":[148],"characteristics.":[153],"We":[154],"conducted":[155],"experiments":[156],"two":[158],"popular":[159],"benchmark":[160],"datasets,":[161],"which":[162],"prove":[163],"superiority":[165],"our":[167],"method.":[168]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-06T09:05:17.133730","created_date":"2025-10-10T00:00:00"}