{"id":"https://openalex.org/W7118776126","doi":"https://doi.org/10.1109/tii.2025.3646626","title":"ViTaDex: Vision\u2013Tactile Fusion for 6-D Object-in-Hand Pose Estimation in Dexterous Anthropomorphic Manipulation","display_name":"ViTaDex: Vision\u2013Tactile Fusion for 6-D Object-in-Hand Pose Estimation in Dexterous Anthropomorphic Manipulation","publication_year":2026,"publication_date":"2026-01-06","ids":{"openalex":"https://openalex.org/W7118776126","doi":"https://doi.org/10.1109/tii.2025.3646626"},"language":"en","primary_location":{"id":"doi:10.1109/tii.2025.3646626","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tii.2025.3646626","pdf_url":null,"source":{"id":"https://openalex.org/S184777250","display_name":"IEEE Transactions on Industrial Informatics","issn_l":"1551-3203","issn":["1551-3203","1941-0050"],"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 Industrial Informatics","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/A5101515133","display_name":"Ling Tong","orcid":"https://orcid.org/0000-0003-0203-7838"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ling Tong","raw_affiliation_strings":["School of Automation, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-0203-7838","affiliations":[{"raw_affiliation_string":"School of Automation, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kun Qian","orcid":"https://orcid.org/0000-0001-7429-1742"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Qian","raw_affiliation_strings":["School of Automation, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-7429-1742","affiliations":[{"raw_affiliation_string":"School of Automation, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122026392","display_name":"Zhaokun Yue","orcid":null},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaokun Yue","raw_affiliation_strings":["School of Automation, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0006-4671-473X","affiliations":[{"raw_affiliation_string":"School of Automation, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100964815","display_name":"Shan Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119896","display_name":"King's College School","ror":"https://ror.org/02bbqcn27","country_code":"GB","type":"education","lineage":["https://openalex.org/I4210119896"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shan Luo","raw_affiliation_strings":["Department of Engineering, King’s College London, London, U.K"],"raw_orcid":"https://orcid.org/0000-0003-4760-0372","affiliations":[{"raw_affiliation_string":"Department of Engineering, King’s College London, London, U.K","institution_ids":["https://openalex.org/I4210119896"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101515133"],"corresponding_institution_ids":["https://openalex.org/I76569877"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03572542,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"22","issue":"4","first_page":"3585","last_page":"3596"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.7128999829292297,"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":0.7128999829292297,"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/T10338","display_name":"Advanced Sensor and Energy Harvesting Materials","score":0.11069999635219574,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/T10784","display_name":"Muscle activation and electromyography studies","score":0.07980000227689743,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.6643000245094299},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5979999899864197},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.4925999939441681},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4715999960899353},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.4681999981403351},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.36910000443458557},{"id":"https://openalex.org/keywords/motion-capture","display_name":"Motion capture","score":0.3637000024318695},{"id":"https://openalex.org/keywords/teleoperation","display_name":"Teleoperation","score":0.33970001339912415},{"id":"https://openalex.org/keywords/human\u2013robot-interaction","display_name":"Human\u2013robot interaction","score":0.33820000290870667}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7774999737739563},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.710099995136261},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.6643000245094299},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6208000183105469},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5979999899864197},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.4925999939441681},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4715999960899353},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.4681999981403351},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.36910000443458557},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.3637000024318695},{"id":"https://openalex.org/C161759796","wikidata":"https://www.wikidata.org/wiki/Q3982902","display_name":"Teleoperation","level":3,"score":0.33970001339912415},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.33820000290870667},{"id":"https://openalex.org/C2776196576","wikidata":"https://www.wikidata.org/wiki/Q196113","display_name":"Camouflage","level":2,"score":0.3255999982357025},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.31769999861717224},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.31060001254081726},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.30649998784065247},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.3061999976634979},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2976999878883362},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29109999537467957},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.2892000079154968},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26260000467300415},{"id":"https://openalex.org/C46722567","wikidata":"https://www.wikidata.org/wiki/Q7674139","display_name":"Tactile sensor","level":3,"score":0.2606000006198883},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C52970973","wikidata":"https://www.wikidata.org/wiki/Q2497134","display_name":"Adaptive system","level":2,"score":0.2547999918460846},{"id":"https://openalex.org/C74222875","wikidata":"https://www.wikidata.org/wiki/Q16000312","display_name":"Robot kinematics","level":4,"score":0.25279998779296875}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tii.2025.3646626","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tii.2025.3646626","pdf_url":null,"source":{"id":"https://openalex.org/S184777250","display_name":"IEEE Transactions on Industrial Informatics","issn_l":"1551-3203","issn":["1551-3203","1941-0050"],"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 Industrial Informatics","raw_type":"journal-article"},{"id":"pmh:oai:kclpure.kcl.ac.uk:publications/447171ac-168e-4153-8405-ddd252d32161","is_oa":false,"landing_page_url":"https://kclpure.kcl.ac.uk/portal/en/publications/447171ac-168e-4153-8405-ddd252d32161","pdf_url":null,"source":{"id":"https://openalex.org/S4306400216","display_name":"Research Portal (King's College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I183935753","host_organization_name":"King's College London","host_organization_lineage":["https://openalex.org/I183935753"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Tong, L, Qian, K, Yue, Z & Luo, S 2026, 'ViTaDex: Vision\u2013Tactile Fusion for 6-D Object-in-Hand Pose Estimation in Dexterous Anthropomorphic Manipulation', IEEE Transactions on Industrial Informatics, vol. 22, no. 4, pp. 3585-3596. https://doi.org/10.1109/TII.2025.3646626","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2989300276","display_name":null,"funder_award_id":"2025A1515010397","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Object-in-hand":[0],"6-D":[1,129],"pose":[2,14,130,145],"estimation":[3,15],"is":[4],"critical":[5],"for":[6,35,128],"dexterous":[7,151],"manipulation":[8],"and":[9,31,58,153],"assembly":[10],"tasks.":[11],"Existing":[12],"object-in-hand":[13,50],"methods":[16],"neglect":[17],"the":[18,42,74,95,118,159,165],"varying":[19],"significance":[20],"of":[21,110,167],"tactile":[22,92,156],"information":[23],"from":[24],"distinct":[25],"hand":[26,142],"regions":[27],"during":[28],"feature":[29],"extraction":[30],"employ":[32],"simplistic":[33],"concatenation":[34],"vision\u2013tactile":[36,75,101],"fusion,":[37],"which":[38,63],"fails":[39],"to":[40,88,148],"capture":[41],"complementary":[43],"relationships":[44],"between":[45],"these":[46,70],"modalities.":[47],"Moreover,":[48],"prevailing":[49],"datasets":[51],"predominantly":[52],"rely":[53],"on":[54,125],"predefined":[55],"motion":[56],"trajectories":[57],"single-point":[59],"fingertip":[60],"contact":[61],"information,":[62],"inadequately":[64],"represent":[65],"real-world":[66],"scenarios.":[67],"To":[68],"address":[69],"limitations,":[71],"we":[72,80,116],"propose":[73],"adaptive":[76,85],"fusion":[77,104],"network.":[78],"Specifically,":[79],"design":[81],"a":[82,100,135,144],"novel":[83],"tactile-gated":[84],"graph":[86],"convolution":[87],"dynamically":[89],"model":[90],"multiregional":[91],"features":[93],"across":[94],"hand.":[96,161],"We":[97],"also":[98],"introduce":[99],"cross-attention":[102],"gated":[103],"module":[105],"that":[106,138],"facilitates":[107],"efficient":[108],"integration":[109],"multimodal":[111],"sensory":[112],"information.":[113],"In":[114],"addition,":[115],"construct":[117],"Vision\u2013Tactile":[119],"Object-in-Hand":[120],"Dexterous":[121],"Manipulation":[122],"dataset":[123,133],"based":[124],"human":[126,150],"demonstration":[127],"estimation.":[131],"The":[132],"employs":[134],"teleoperation":[136],"system":[137,147],"combines":[139],"an":[140],"exoskeleton":[141],"with":[143],"tracking":[146],"replicate":[149],"behaviors":[152],"encompasses":[154],"high-density":[155],"data":[157],"spanning":[158],"entire":[160],"Extensive":[162],"experiments":[163],"demonstrate":[164],"robustness":[166],"our":[168],"framework":[169],"against":[170],"occlusions.":[171]},"counts_by_year":[],"updated_date":"2026-05-09T13:55:54.758798","created_date":"2026-01-08T00:00:00"}