{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T19:03:19Z","timestamp":1783710199616,"version":"3.55.0"},"reference-count":33,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T00:00:00Z","timestamp":1769990400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Robotics and Computer-Integrated Manufacturing"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.rcim.2026.103258","type":"journal-article","created":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T05:19:15Z","timestamp":1770700755000},"page":"103258","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["Spatiotemporal perception and motion similarity learning for real-time assembly verification"],"prefix":"10.1016","volume":"100","author":[{"given":"Q.","family":"Ye","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Y.Q.","family":"Niu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"A.Y.C.","family":"Nee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9569-3350","authenticated-orcid":false,"given":"S.K.","family":"Ong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.rcim.2026.103258_bib0001","doi-asserted-by":"crossref","DOI":"10.1016\/j.rcim.2022.102449","article-title":"Deep learning-based human action recognition to leverage context awareness in collaborative assembly","volume":"80","author":"Moutinho","year":"2023","journal-title":"Robot. Comput.-Integr. Manuf."},{"key":"10.1016\/j.rcim.2026.103258_bib0002","doi-asserted-by":"crossref","first-page":"178","DOI":"10.1016\/j.jmsy.2025.05.020","article-title":"Human-in-the-loop in smart manufacturing (H-SM): a review and perspective","volume":"82","author":"Kim","year":"2025","journal-title":"J. Manuf. Syst."},{"key":"10.1016\/j.rcim.2026.103258_bib0003","doi-asserted-by":"crossref","first-page":"57009","DOI":"10.1109\/ACCESS.2025.3554263","article-title":"Real-time assembly task validation using deep learning-based object detection and operator's hand-joints trajectory classification","volume":"13","author":"Ay","year":"2025","journal-title":"IEEE Access"},{"issue":"6","key":"10.1016\/j.rcim.2026.103258_bib0004","first-page":"854","article-title":"A novel multi-stream hand-object interaction network for assembly action recognition","volume":"44","author":"Li","year":"2024","journal-title":"Rob. Intell. Autom."},{"key":"10.1016\/j.rcim.2026.103258_bib0005","doi-asserted-by":"crossref","DOI":"10.1016\/j.cviu.2025.104592","article-title":"A vision-based framework and dataset for human behavior understanding in industrial assembly lines","volume":"263","author":"Papoutsakis","year":"2026","journal-title":"Comput. Vis. Image Underst."},{"key":"10.1016\/j.rcim.2026.103258_bib0006","doi-asserted-by":"crossref","first-page":"745","DOI":"10.1038\/s41597-022-01843-z","article-title":"The HA4M dataset: multi-modal monitoring of an assembly task for human action recognition in manufacturing","volume":"9","author":"Cicirelli","year":"2022","journal-title":"Sci. Data"},{"issue":"30908","key":"10.1016\/j.rcim.2026.103258_bib0007","first-page":"1","article-title":"Human motion similarity evaluation based on deep metric learning","volume":"14","author":"Zhang","year":"2024","journal-title":"Sci. Rep."},{"key":"10.1016\/j.rcim.2026.103258_bib0008","article-title":"Modeling Time Series Similarity with Siamese Recurrent Networks","author":"Pei","year":"2016","journal-title":"arXiv preprint"},{"key":"10.1016\/j.rcim.2026.103258_bib0009","series-title":"2017 IEEE International Conference on Computer Vision (ICCV)","first-page":"1992","article-title":"A Two Stream Siamese Convolutional Neural Network for Person Re-identification","author":"Chung","year":"2017"},{"key":"10.1016\/j.rcim.2026.103258_bib0010","series-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"244","article-title":"Video Action Transformer Network","author":"Girdhar","year":"2019"},{"key":"10.1016\/j.rcim.2026.103258_bib0011","series-title":"Proc. Eur. Conf. Comput. Vis. (ECCV)","first-page":"297","article-title":"Global-local motion transformer for unsupervised skeleton-based action learning","author":"Kim","year":"2022"},{"key":"10.1016\/j.rcim.2026.103258_bib0012","author":"Jocher"},{"issue":"1","key":"10.1016\/j.rcim.2026.103258_bib0013","first-page":"1","article-title":"Action recognition based on human skeleton: review and prospect","volume":"54","author":"Meng","year":"2025","journal-title":"Inf. Control"},{"key":"10.1016\/j.rcim.2026.103258_bib0014","doi-asserted-by":"crossref","DOI":"10.1016\/j.aei.2023.101950","article-title":"A marker-less assembly stage recognition method based on corner feature","volume":"56","author":"Hong","year":"2023","journal-title":"Adv. Eng. Inf."},{"issue":"5","key":"10.1016\/j.rcim.2026.103258_bib0015","first-page":"509","article-title":"Manual assembly actions segmentation system using temporal-spatial-contact features","volume":"43","author":"Kang","year":"2023","journal-title":"Robot. Intell. Autom."},{"issue":"12","key":"10.1016\/j.rcim.2026.103258_bib0016","doi-asserted-by":"crossref","first-page":"5116","DOI":"10.3390\/app14125116","article-title":"Optimization method for assembly sequence evaluation based on assembly cost and ontology of aviation reducers","volume":"14","author":"Liu","year":"2024","journal-title":"Appl. Sci."},{"key":"10.1016\/j.rcim.2026.103258_bib0017","doi-asserted-by":"crossref","first-page":"709","DOI":"10.1016\/j.jmsy.2022.10.015","article-title":"Real-time monitoring for manual operations with machine vision in smart manufacturing","volume":"65","author":"Lou","year":"2022","journal-title":"J. Manuf. Syst."},{"key":"10.1016\/j.rcim.2026.103258_bib0018","doi-asserted-by":"crossref","first-page":"158","DOI":"10.1016\/j.promfg.2020.01.288","article-title":"Action recognition in manufacturing assembly using multimodal sensor fusion","volume":"39","author":"Al-Amin","year":"2019","journal-title":"Procedia Manuf"},{"key":"10.1016\/j.rcim.2026.103258_bib0019","series-title":"2013 International Conference on Advanced Robotics and Intelligent Systems (ARIS)","first-page":"28","article-title":"Safety-based human-robot collaboration in cellular manufacturing: a case study of power protector assembly","author":"Hu","year":"2013"},{"issue":"6","key":"10.1016\/j.rcim.2026.103258_bib0020","doi-asserted-by":"crossref","first-page":"925","DOI":"10.1108\/AA-06-2018-078","article-title":"Utilising Low-Cost RGB-D Cameras to Track the Real-Time Progress of a Manual Assembly Sequence","volume":"40","author":"Oyekan","year":"2020","journal-title":"Assembly Autom."},{"key":"10.1016\/j.rcim.2026.103258_bib0021","doi-asserted-by":"crossref","DOI":"10.1016\/j.cie.2024.110527","article-title":"Deep learning based assembly process action recognition and progress prediction facing human-centric intelligent manufacturing","volume":"196","author":"Wang","year":"2024","journal-title":"Comput. Ind. Eng."},{"issue":"9","key":"10.1016\/j.rcim.2026.103258_bib0022","doi-asserted-by":"crossref","first-page":"4134","DOI":"10.3390\/app12094134","article-title":"Evaluation of RGB-D multi-camera pose estimation for 3D reconstruction","volume":"12","author":"de Medeiros Esper","year":"2022","journal-title":"Appl. Sci."},{"key":"10.1016\/j.rcim.2026.103258_bib0023","article-title":"Skeleton-based action recognition via spatial and temporal transformer networks","volume":"208\u2013209","author":"Plizzari","year":"2021","journal-title":"Comput. Vis. Image Underst."},{"issue":"11","key":"10.1016\/j.rcim.2026.103258_bib0024","doi-asserted-by":"crossref","first-page":"1330","DOI":"10.1109\/34.888718","article-title":"A flexible new technique for camera calibration","volume":"22","author":"Zhang","year":"2000","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.rcim.2026.103258_bib0025","series-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. Workshops (CVPRW)","first-page":"129","article-title":"MediaPipe: a Framework for Perceiving and Processing Reality","author":"Lugaresi","year":"2019"},{"key":"10.1016\/j.rcim.2026.103258_bib0026","series-title":"Economic Control of Quality of Manufactured Product","author":"Shewhart","year":"1931"},{"issue":"2","key":"10.1016\/j.rcim.2026.103258_bib0027","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1080\/00031305.1994.10476030","article-title":"The three sigma rule","volume":"48","author":"Pukelsheim","year":"1994","journal-title":"Amer. Statist."},{"key":"10.1016\/j.rcim.2026.103258_bib0028","series-title":"2009 IEEE Conference on Computer Vision and Pattern Recognition","first-page":"248","article-title":"ImageNet: a large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"10.1016\/j.rcim.2026.103258_bib0029","series-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","first-page":"409","article-title":"First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations","author":"Garcia-Hernando","year":"2018"},{"key":"10.1016\/j.rcim.2026.103258_bib0030","article-title":"LightYOLO: lightweight model based on YOLOv8n for defect detection of ultrasonically welded wire terminations","volume":"60","author":"Xu","year":"2024","journal-title":"Eng. Sci. Technol., Int. J."},{"key":"10.1016\/j.rcim.2026.103258_bib0031","series-title":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)","first-page":"1724","article-title":"Learning phrase representations using RNN encoder\u2013decoder for statistical machine translation","author":"Cho","year":"2014"},{"key":"10.1016\/j.rcim.2026.103258_bib0032","series-title":"Proc. IEEE Int. Conf. Acoust., Speech Signal Process. (ICASSP)","first-page":"5329","article-title":"X-vectors: robust DNN embeddings for speaker recognition","author":"Snyder","year":"2018"},{"issue":"3","key":"10.1016\/j.rcim.2026.103258_bib0033","doi-asserted-by":"crossref","first-page":"621","DOI":"10.3390\/s25030621","article-title":"Beyond information distortion: imaging variable-length time series data for classification","volume":"25","author":"Lee","year":"2025","journal-title":"Sensors"}],"container-title":["Robotics and Computer-Integrated Manufacturing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0736584526000372?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0736584526000372?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T02:49:00Z","timestamp":1782960540000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0736584526000372"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":33,"alternative-id":["S0736584526000372"],"URL":"https:\/\/doi.org\/10.1016\/j.rcim.2026.103258","relation":{},"ISSN":["0736-5845"],"issn-type":[{"value":"0736-5845","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Spatiotemporal perception and motion similarity learning for real-time assembly verification","name":"articletitle","label":"Article Title"},{"value":"Robotics and Computer-Integrated Manufacturing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.rcim.2026.103258","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Author(s). Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"103258"}}