{"id":"https://openalex.org/W7128500689","doi":"https://doi.org/10.1016/j.rcim.2026.103258","title":"Spatiotemporal perception and motion similarity learning for real-time assembly verification","display_name":"Spatiotemporal perception and motion similarity learning for real-time assembly verification","publication_year":2026,"publication_date":"2026-02-10","ids":{"openalex":"https://openalex.org/W7128500689","doi":"https://doi.org/10.1016/j.rcim.2026.103258"},"language":"en","primary_location":{"id":"doi:10.1016/j.rcim.2026.103258","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.rcim.2026.103258","pdf_url":null,"source":{"id":"https://openalex.org/S118216261","display_name":"Robotics and Computer-Integrated Manufacturing","issn_l":"0736-5845","issn":["0736-5845","1879-2537"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Robotics and Computer-Integrated Manufacturing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.rcim.2026.103258","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125546096","display_name":"Q. Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Q. Ye","raw_affiliation_strings":["Department of Mechanical Engineering, College of Design and Engineering, National University of Singapore, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, College of Design and Engineering, National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012488247","display_name":"Y.Q. Niu","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Y.Q. Niu","raw_affiliation_strings":["Department of Mechanical Engineering, College of Design and Engineering, National University of Singapore, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, College of Design and Engineering, National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125491264","display_name":"A.Y.C. Nee","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"A.Y.C. Nee","raw_affiliation_strings":["Department of Mechanical Engineering, College of Design and Engineering, National University of Singapore, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, College of Design and Engineering, National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5125547056","display_name":"S.K. Ong","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"S.K. Ong","raw_affiliation_strings":["Department of Mechanical Engineering, College of Design and Engineering, National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-9569-3350","affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, College of Design and Engineering, National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5125547056"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":{"value":4240,"currency":"USD","value_usd":4240},"apc_paid":{"value":4240,"currency":"USD","value_usd":4240},"fwci":9.8969,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.95867382,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"100","issue":null,"first_page":"103258","last_page":"103258"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.5781999826431274,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.5781999826431274,"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":0.22059999406337738,"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"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.1492999941110611,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.6638000011444092},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5565000176429749},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.4350000023841858},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.3765000104904175},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.37049999833106995},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.3571999967098236},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34769999980926514},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3418999910354614},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.33730000257492065}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7290999889373779},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7249000072479248},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.6638000011444092},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5565000176429749},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5253999829292297},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.4350000023841858},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3765000104904175},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.37049999833106995},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3571999967098236},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34769999980926514},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3418999910354614},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.33730000257492065},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.33390000462532043},{"id":"https://openalex.org/C143271835","wikidata":"https://www.wikidata.org/wiki/Q254515","display_name":"Similitude","level":2,"score":0.33169999718666077},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.31949999928474426},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.30300000309944153},{"id":"https://openalex.org/C176809094","wikidata":"https://www.wikidata.org/wiki/Q15401496","display_name":"Traverse","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.28870001435279846},{"id":"https://openalex.org/C2780624872","wikidata":"https://www.wikidata.org/wiki/Q852453","display_name":"Motion detection","level":3,"score":0.2797999978065491},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C39394851","wikidata":"https://www.wikidata.org/wiki/Q921594","display_name":"Inter frame","level":4,"score":0.25450000166893005},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.2533999979496002},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.rcim.2026.103258","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.rcim.2026.103258","pdf_url":null,"source":{"id":"https://openalex.org/S118216261","display_name":"Robotics and Computer-Integrated Manufacturing","issn_l":"0736-5845","issn":["0736-5845","1879-2537"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Robotics and Computer-Integrated Manufacturing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.rcim.2026.103258","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.rcim.2026.103258","pdf_url":null,"source":{"id":"https://openalex.org/S118216261","display_name":"Robotics and Computer-Integrated Manufacturing","issn_l":"0736-5845","issn":["0736-5845","1879-2537"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Robotics and Computer-Integrated Manufacturing","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.6507055163383484}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2079054072","https://openalex.org/W2167667767","https://openalex.org/W2978015975","https://openalex.org/W3007287549","https://openalex.org/W4224301927","https://openalex.org/W4306253932","https://openalex.org/W4309567669","https://openalex.org/W4311121622","https://openalex.org/W4365505260","https://openalex.org/W4399633935","https://openalex.org/W4401946706","https://openalex.org/W4406664763","https://openalex.org/W4408859198","https://openalex.org/W4411261595","https://openalex.org/W4417080356"],"related_works":[],"abstract_inverted_index":{"The":[0,177],"increasing":[1],"demand":[2],"for":[3,46,137,201],"personalized":[4],"products":[5],"and":[6,42,60,112,122,169,188,195],"operational":[7],"flexibility":[8],"in":[9,16,204],"Industry":[10],"4.0":[11],"has":[12],"exposed":[13],"critical":[14],"limitations":[15],"traditional":[17],"quality":[18],"assurance":[19],"systems,":[20],"particularly":[21],"within":[22],"human-in-the-loop":[23],"manual":[24],"assembly.":[25],"To":[26,129],"address":[27],"these":[28],"challenges,":[29],"this":[30,92],"paper":[31],"introduces":[32],"an":[33,95,107,170],"integrated":[34],"vision-based":[35],"framework":[36],"that":[37],"combines":[38],"spatiotemporal":[39],"object":[40],"detection":[41,87],"motion":[43,151],"similarity":[44],"assessment":[45],"the":[47,101,115,135,140,158],"automated":[48],"verification":[49,203],"of":[50,98,110,118,172],"procedural":[51,202],"correctness.":[52],"A":[53],"multi-modal":[54],"acquisition":[55],"system,":[56],"utilizing":[57],"synchronized":[58],"RGB":[59],"depth":[61],"data,":[62],"is":[63,146],"employed":[64],"to":[65,126],"support":[66],"precise":[67],"3D":[68,149],"hand":[69,150],"keypoint":[70],"reconstruction.":[71],"For":[72],"process":[73],"segmentation,":[74],"STM-YOLO":[75],"(Spatiotemporal":[76],"Multi-View":[77],"You":[78],"Only":[79],"Look":[80],"Once)":[81],"was":[82],"developed.":[83],"By":[84],"reconfiguring":[85],"standard":[86],"heads":[88],"into":[89],"stage-transition":[90],"classifiers,":[91],"model":[93],"achieves":[94],"average":[96],"accuracy":[97,168],"87%,":[99],"outperforming":[100],"single-view,":[102],"single-frame":[103],"baseline":[104],"(S-S)":[105],"by":[106],"absolute":[108],"margin":[109],"27.67%,":[111],"further":[113],"validates":[114],"complementary":[116],"contributions":[117],"both":[119],"temporal":[120],"modeling":[121],"multi-view":[123],"perception":[124],"modules":[125],"performance":[127],"improvement.":[128],"assess":[130],"operator":[131],"action":[132],"conformity":[133],"without":[134],"need":[136],"gesture-level":[138],"annotation,":[139],"Siamese":[141],"Transformer":[142],"Encoder":[143],"Network":[144],"(STEN)":[145],"introduced,":[147],"evaluating":[148],"trajectories":[152],"against":[153],"golden-standard":[154],"references.":[155],"Validated":[156],"on":[157,185],"filtered":[159],"FPHA":[160],"(First-Person":[161],"Hand":[162],"Action)":[163],"benchmark,":[164],"STEN":[165],"attains":[166],"99.28%":[167],"F1-score":[171],"0.9858,":[173],"surpassing":[174],"classical":[175],"approaches.":[176],"proposed":[178],"system":[179],"operates":[180],"at":[181],"over":[182],"10":[183],"fps":[184],"laboratory":[186],"hardware":[187],"demonstrates":[189],"robust":[190],"generalization":[191],"across":[192],"diverse":[193],"operators":[194],"tasks,":[196],"offering":[197],"a":[198],"scalable":[199],"solution":[200],"flexible":[205],"manufacturing":[206],"environments.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-14T06:11:07.267592","created_date":"2026-02-11T00:00:00"}