{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,23]],"date-time":"2026-05-23T07:05:52Z","timestamp":1779519952473,"version":"3.53.1"},"reference-count":51,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computers & Industrial Engineering"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.cie.2026.112013","type":"journal-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T03:05:29Z","timestamp":1775099129000},"page":"112013","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["TA-Net: real-time identification of transient actions in manual assembly lines"],"prefix":"10.1016","volume":"217","author":[{"given":"Jiaming","family":"Shi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiang","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guoyi","family":"Hou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuanggao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengda","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yumin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingxue","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.cie.2026.112013_b0005","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109484","article-title":"DeepActsNet: A deep ensemble framework combining features from face, hands, and body for action recognition","volume":"139","author":"Asif","year":"2023","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.cie.2026.112013_b0010","doi-asserted-by":"crossref","unstructured":"Baccouche, M., Mamalet, F., Wolf, C., Christophe Garcia, Atilla Baskurt, Sequential deep learning for human action recognition, In Proceedings of the 2nd International Workshop on Human Behavior Under- standing (HBU\u201911), Springer, 2011; 29\u201339.","DOI":"10.1007\/978-3-642-25446-8_4"},{"key":"10.1016\/j.cie.2026.112013_b0015","doi-asserted-by":"crossref","unstructured":"Bao, W., Q. Yu, Y. Kong, Evidential deep learning for open set action recognition, Proceedings of the IEEE\/CVF international conference on computer vision. 2021: 13349-13358.","DOI":"10.1109\/ICCV48922.2021.01310"},{"issue":"3","key":"10.1016\/j.cie.2026.112013_b0020","first-page":"4","article-title":"Is space-time attention all you need for video understanding?","volume":"2","author":"Bertasius","year":"2021","journal-title":"Icml"},{"key":"10.1016\/j.cie.2026.112013_b0025","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201917)","first-page":"4724","article-title":"Quo vadis, action recognition? a new model and the Kinetics dataset","author":"Carreira","year":"2017"},{"key":"10.1016\/j.cie.2026.112013_b0030","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.126255","article-title":"STAN: Spatio-Temporal Analysis Network for efficient video action recognition","volume":"268","author":"Chen","year":"2025","journal-title":"Expert Systems with Applications"},{"issue":"04","key":"10.1016\/j.cie.2026.112013_b0035","first-page":"112","article-title":"A fusion of longformer for spatio-temporal separation attention assembly action recognition network","volume":"47","author":"Congping","year":"2025","journal-title":"Manufacturing Automation"},{"key":"10.1016\/j.cie.2026.112013_b0040","doi-asserted-by":"crossref","unstructured":"R. De Geest, E. Gavves, A. Ghodrati, Z. Li, C. Snoek, and T. Tuytelaars, Online action detection, in Proc. 14th Eur. Conf. Comput. Vis., Amsterdam, The Netherlands, Springer, 2016; pp. 269\u2013284.","DOI":"10.1007\/978-3-319-46454-1_17"},{"key":"10.1016\/j.cie.2026.112013_b0045","series-title":"International Conference on Learning Representations (ICLR)","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021"},{"key":"10.1016\/j.cie.2026.112013_b0050","doi-asserted-by":"crossref","unstructured":"Fan, H., Xiong, B., Mangalam, K., Multiscale vision transformers, Proceedings of the IEEE\/CVF international conference on computer vision, 2021: 6824-6835.","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"10.1016\/j.cie.2026.112013_b0055","series-title":"In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR\u201920)","first-page":"203","article-title":"X3D: Expanding architectures for efficient video recognition","author":"Feichtenhofer","year":"2020"},{"key":"10.1016\/j.cie.2026.112013_b0060","series-title":"In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV\u201919)","first-page":"6202","article-title":"Kaiming He, SlowFast networks for video recognition","author":"Feichtenhofer","year":"2019"},{"key":"10.1016\/j.cie.2026.112013_b0065","doi-asserted-by":"crossref","unstructured":"Gayathri, T., Mamatha, H.R., How to Improve Video Analytics with Action Recognition: A Survey, ACM Comput. Surv. 57, 1, Article 9 (January 2025), 2024; 36 pages, https:\/\/doi.org\/10.1145\/3679011.","DOI":"10.1145\/3679011"},{"key":"10.1016\/j.cie.2026.112013_b0070","doi-asserted-by":"crossref","unstructured":"Gu, X., X. Xue, and F. Wang, Fine-grained action recognition on a novel basketball dataset, in Proc. ICASSP - IEEE Int. Conf. Acoust. Speech Signal Process, (ICASSP), 2020; pp, 2563\u20132567.","DOI":"10.1109\/ICASSP40776.2020.9053928"},{"key":"10.1016\/j.cie.2026.112013_b0075","doi-asserted-by":"crossref","unstructured":"Heilbron, F.C., V. Escorcia, B. Ghanem, J. C. Niebles, ActivityNet: A large-scale video benchmark for human activity understanding, in Proc. IEEE Conf. Computer. Vis. Pattern Recognition, (CVPR), Jun. 2015; pp. 961\u2013970.","DOI":"10.1109\/CVPR.2015.7298698"},{"issue":"1","key":"10.1016\/j.cie.2026.112013_b0080","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","article-title":"3D convolutional neural networks for human action recognition","volume":"35","author":"Ji","year":"2012","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"issue":"04","key":"10.1016\/j.cie.2026.112013_b0085","first-page":"1099","article-title":"Online method for worker operation recognition based on attention of workpiece","volume":"27","author":"Jiacheng","year":"2021","journal-title":"Computer Integrated Manufacturing Systems"},{"key":"10.1016\/j.cie.2026.112013_b0090","doi-asserted-by":"crossref","unstructured":"Karpathy, A., G. Toderici, S. Shetty, T. Leung, R. Sukthankar, L. Fei-Fei, Large-scale video classification with convolutional neural networks, in Proc. IEEE Conf. Computer. Vis. Pattern Recognition., Jun, 2014; pp. 1725\u20131732.","DOI":"10.1109\/CVPR.2014.223"},{"key":"10.1016\/j.cie.2026.112013_b0095","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2021.108068","article-title":"Weakly-supervised temporal attention 3D network for human action recognition","volume":"119","author":"Kim","year":"2021","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.cie.2026.112013_b0100","series-title":"Proceedings of the International Conference on Computer Vision (ICCV\u201911). IEEE","first-page":"2556","article-title":"A large video database for human motion recognition","author":"Kuehne","year":"2011"},{"key":"10.1016\/j.cie.2026.112013_b0105","series-title":"International Conference on Learning Representations (ICLR)","article-title":"UniFormer: Unified transformer for efficient spatiotemporal representation learning","author":"Li","year":"2022"},{"key":"10.1016\/j.cie.2026.112013_b0110","doi-asserted-by":"crossref","unstructured":"Li, K., D. Guo, and M. Wang, ViGT: Proposal-free video grounding with a learnable token in the transformer, Sci. China Inf. Sci. vol. 66, no. 10, Oct. 2023; Art. no. 202102.","DOI":"10.1007\/s11432-022-3783-3"},{"key":"10.1016\/j.cie.2026.112013_b0115","series-title":"Proc Vis Eur. Conf. Computer","first-page":"513","article-title":"Resound: Towards action recognition without representation bias","author":"Li","year":"2018"},{"key":"10.1016\/j.cie.2026.112013_b0120","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2020.107356","article-title":"SGM-Net: Skeleton-guided multimodal network for action recognition","volume":"104","author":"Li","year":"2020","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.cie.2026.112013_b0125","doi-asserted-by":"crossref","unstructured":"Li, F., Shichang Du, and Chen Zhao, State space modelling of variation propagation in multistage machining systems with generalized fixture layouts: a case study from an engine manufacturing enterprise. Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture. 2026. DOI: 10.1177\/09544054261434877.","DOI":"10.1177\/09544054261434877"},{"issue":"2","key":"10.1016\/j.cie.2026.112013_b0130","doi-asserted-by":"crossref","first-page":"451","DOI":"10.1016\/S0031-3203(02)00060-2","article-title":"The global K-means clustering algorithm","volume":"36","author":"Likas","year":"2003","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.cie.2026.112013_b0135","doi-asserted-by":"crossref","unstructured":"Lin, J., C. Gan, and S. Han, TSM: Temporal shift module for efficient video understanding, in Proc. IEEE\/CVF Int. Conf. Computer, Vis. (ICCV), Oct, 2019; pp. 7083\u20137093.","DOI":"10.1109\/ICCV.2019.00718"},{"key":"10.1016\/j.cie.2026.112013_b0140","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r P, Girshick R, et al. Feature pyramid networks for object detection, Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 2117-2125.","DOI":"10.1109\/CVPR.2017.106"},{"key":"10.1016\/j.cie.2026.112013_b0145","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","article-title":"Video swin transformer","author":"Liu","year":"2022"},{"key":"10.1016\/j.cie.2026.112013_b0150","series-title":"Human Action Recognition based on 3D SIFT and LDA Model, 2011 IEEE Workshop on Robotic Intelligence In Informationally Structured Space (R12S)","first-page":"12","author":"Liu","year":"2011"},{"key":"10.1016\/j.cie.2026.112013_b0155","article-title":"THTFormer: Topology-adaptive hypergraph transformer network for skeleton-based action recognition","volume":"112125","author":"Ma","year":"2025","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.cie.2026.112013_b0160","series-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"1569","article-title":"The meccano dataset: Understanding human-object interactions from egocentric videos in an industrial-like domain","author":"Ragusa","year":"2021"},{"issue":"1","key":"10.1016\/j.cie.2026.112013_b0165","doi-asserted-by":"crossref","first-page":"3","DOI":"10.20899\/jpna.3.1.3-22","article-title":"A comparative analysis of two streams of implementation research","volume":"3","author":"Roll","year":"2017","journal-title":"Journal of Public and Nonprofit Affairs"},{"key":"10.1016\/j.cie.2026.112013_b0170","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"21096","article-title":"Assembly101: A large-scale multi-view video dataset for understanding procedural activities","author":"Sener","year":"2022"},{"key":"10.1016\/j.cie.2026.112013_b0175","doi-asserted-by":"crossref","unstructured":"Shao, D., Y. Zhao, B. Dai, D. Lin, FineGym: A hierarchical video dataset for fine-grained action understanding, in Proc. IEEE\/CVF Conf. Computer. Vis, Pattern Recognition. (CVPR), 2020; pp. 2613\u20132622.","DOI":"10.1109\/CVPR42600.2020.00269"},{"issue":"4","key":"10.1016\/j.cie.2026.112013_b0180","doi-asserted-by":"crossref","first-page":"6007","DOI":"10.1109\/JSEN.2025.3650493","article-title":"An improved variational autoencoder and graph attention network method for wear prediction of aerospace self-lubricating bearing using acoustic emission signal","volume":"26","author":"Shen","year":"2026","journal-title":"IEEE Sensors Journal."},{"key":"10.1016\/j.cie.2026.112013_b0185","unstructured":"Soomro, K., A. R. Zamir, M. Shah, UCF101: A dataset of 101 human action classes from videos in the wild, CRCV-TR-12-01, Nov. 2012."},{"key":"10.1016\/j.cie.2026.112013_b0190","series-title":"In Proceedings of the IEEE International Conference on Computer Vision (ICCV\u201915)","first-page":"4489","article-title":"Manohar Paluri, Learning spatiotemporal features with 3D convolutional networks","author":"Tran","year":"2015"},{"key":"10.1016\/j.cie.2026.112013_b0195","unstructured":"Vaswani A, Shazeer N, Parmar N, Attention is all you need, Advances in neural information processing systems, 2017, 30."},{"key":"10.1016\/j.cie.2026.112013_b0200","doi-asserted-by":"crossref","first-page":"2740","DOI":"10.1109\/TPAMI.2018.2868668","article-title":"Temporal segment networks for action recognition in videos","author":"Wang","year":"2019","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.cie.2026.112013_b0205","doi-asserted-by":"crossref","DOI":"10.1115\/1.4071182","article-title":"A hybrid physical damage neural network for wear prediction of self-lubricating bearings","author":"Wang","year":"2026","journal-title":"ASME Transaction on Journal of Computing and Information Science in Engineering."},{"issue":"19","key":"10.1016\/j.cie.2026.112013_b0210","doi-asserted-by":"crossref","first-page":"36513","DOI":"10.1109\/JSEN.2025.3597796","article-title":"MTCAT: A modern temporal convolution and enhanced attention transformer model for remaining useful life prediction of aerospace self-lubricating bearings","volume":"25","author":"Wang","year":"2025","journal-title":"IEEE Sensors Journal."},{"key":"10.1016\/j.cie.2026.112013_b0215","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110927","article-title":"Distilling interaction knowledge for semi-supervised egocentric action recognition","volume":"157","author":"Wang","year":"2025","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.cie.2026.112013_b0220","unstructured":"Wang, X. et al, OadTR: Online action detection with transformers, in Proc. IEEE\/CVF Int. Conf. Comput. Vis, 2021; pp. 7565\u20137575."},{"key":"10.1016\/j.cie.2026.112013_b0225","doi-asserted-by":"crossref","unstructured":"Wang, Q., Wu B, Zhu P, et al. ECA-Net: Efficient channel attention for deep convolutional neural networks, Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2020: 11534-11542.","DOI":"10.1109\/CVPR42600.2020.01155"},{"issue":"4","key":"10.1016\/j.cie.2026.112013_b0230","first-page":"41","article-title":"Assembly action recognition based on attention spatio-temporal feature network","volume":"50","author":"Xicong","year":"2022","journal-title":"Machine Tool & Hydraulics"},{"key":"10.1016\/j.cie.2026.112013_b0235","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","article-title":"Temporal pyramid network for action recognition","author":"Yang","year":"2020"},{"key":"10.1016\/j.cie.2026.112013_b0240","series-title":"Proc Eur. Conf. Comput. Vis.","first-page":"485","article-title":"Real-time online video detection with temporal smoothing transformers","author":"Zhao","year":"2022"},{"key":"10.1016\/j.cie.2026.112013_b0245","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1016\/j.jmsy.2025.09.015","article-title":"Flexible pallet automation system scheduling with limited fixture-pallets and material-pallets: A case study from an engine manufacturing enterprise","volume":"83","author":"Zhou","year":"2025","journal-title":"Journal of Manufacturing Systems."},{"issue":"4","key":"10.1016\/j.cie.2026.112013_b0250","doi-asserted-by":"crossref","first-page":"2868","DOI":"10.1109\/TSMC.2026.3655483","article-title":"Multiresource constrained flexible job shop scheduling with fixture-pallets and setup stations under pallet automation systems","volume":"56","author":"Zhou","year":"2026","journal-title":"IEEE Transactions on Systems, Man and Cybernetics: Systems."},{"key":"10.1016\/j.cie.2026.112013_b0255","article-title":"A renaissance of explicit motion information mining from transformers for action recognition","volume":"112645","author":"Zhuang","year":"2025","journal-title":"Pattern Recognition"}],"container-title":["Computers & Industrial Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0360835226002147?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0360835226002147?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,23]],"date-time":"2026-05-23T06:48:11Z","timestamp":1779518891000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0360835226002147"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":51,"alternative-id":["S0360835226002147"],"URL":"https:\/\/doi.org\/10.1016\/j.cie.2026.112013","relation":{},"ISSN":["0360-8352"],"issn-type":[{"value":"0360-8352","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"TA-Net: real-time identification of transient actions in manual assembly lines","name":"articletitle","label":"Article Title"},{"value":"Computers & Industrial Engineering","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.cie.2026.112013","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"112013"}}