{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T01:56:09Z","timestamp":1763344569360,"version":"3.45.0"},"reference-count":44,"publisher":"Tech Science Press","issue":"2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["CMC"],"published-print":{"date-parts":[[2025]]},"DOI":"10.32604\/cmc.2025.065895","type":"journal-article","created":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:18:26Z","timestamp":1750220306000},"page":"3787-3810","source":"Crossref","is-referenced-by-count":0,"title":["Prediction of Assembly Intent for Human-Robot Collaboration Based on Video Analytics and Hidden Markov Model"],"prefix":"10.32604","volume":"84","author":[{"given":"Jing","family":"Qu","sequence":"first","affiliation":[]},{"given":"Yanmei","family":"Li","sequence":"additional","affiliation":[]},{"given":"Changrong","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Wen","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Weiping","family":"Fu","sequence":"additional","affiliation":[]}],"member":"17807","published-online":{"date-parts":[[2025]]},"reference":[{"key":"ref1","series-title":"2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201905); 2005 Jun 20\u201325; San Diego, CA, USA","first-page":"886","article-title":"Histograms of oriented gradients for human detection","author":"Dalal"},{"key":"ref2","series-title":"2009 IEEE Conference on Computer Vision and Pattern Recognition; 2009 Jun 20\u201325; Miami, FL, USA","first-page":"1932","article-title":"Histograms of oriented optical flow and Binet-Cauchy kernels on nonlinear dynamical systems for the recognition of human actions","author":"Chaudhry"},{"key":"ref3","series-title":"2013 IEEE International Conference on Computer Vision; 2013 Dec 1\u20138; Sydney, NSW, Australia","first-page":"3551","article-title":"Action recognition with improved trajectories","author":"Wang"},{"key":"ref4","series-title":"2022 6th International Symposium on Computer Science and Intelligent Control (ISCSIC); 2022 Nov 11\u201313; Beijing, China","first-page":"55","article-title":"Learning spatiotemporal features for video semantic segmentation using 3D convolutional neural networks","author":"Chen"},{"key":"ref5","series-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2017 Jul 21\u201326; Honolulu, HI, USA","first-page":"4724","article-title":"Quo vadis, action recognition? A new model and the kinetics dataset","author":"Carreira"},{"key":"ref6","series-title":"2019 IEEE\/CVF International Conference on Computer Vision (ICCV); 2019 Oct 27\u2013Nov 2; Seoul, Republic of Korea","first-page":"6201","article-title":"SlowFast networks for video recognition","author":"Feichtenhofer"},{"key":"ref7","unstructured":"Zhu S, Yang T, Mendieta M, Chen C. A3D: adaptive 3D networks for video action recognition. arXiv:2011.12384. 2020."},{"key":"ref8","series-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR); 2020 Jun 13\u201319; Seattle, WA, USA","first-page":"200","article-title":"X3D: expanding architectures for efficient video recognition","author":"Feichtenhofer"},{"key":"ref9","series-title":"2022 International Conference on Image Processing, Computer Vision and Machine Learning (ICICML); 2022 Oct 28\u201330; Xi\u2019an, China","first-page":"179","article-title":"TS-D3D: a novel two-stream model for action recognition","author":"Yang"},{"key":"ref10","series-title":"2019 IEEE\/CVF International Conference on Computer Vision (ICCV); 2019 Oct 27\u2013Nov 2; Seoul, Republic of Korea","first-page":"7082","article-title":"TSM: temporal shift module for efficient video understanding","author":"Lin"},{"key":"ref11","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence; 2020 Feb 7\u201312; New York, NY, USA","first-page":"11966","article-title":"Temporal interlacing network","author":"Shao"},{"key":"ref12","series-title":"2019 IEEE\/CVF International Conference on Computer Vision (ICCV); 2019 Oct 27\u2013Nov 2; Seoul, Republic of Korea","first-page":"2000","article-title":"STM: spatiotemporal and motion encoding for action recognition","author":"Jiang"},{"key":"ref13","series-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR); 2020 Jun 13\u201319; Seattle, WA, USA","first-page":"588","article-title":"Temporal pyramid network for action recognition","author":"Yang"},{"key":"ref14","series-title":"2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR); 2021 Jun 20\u201325; Nashville, TN, USA","first-page":"1895","article-title":"TDN: temporal difference networks for efficient action recognition","author":"Wang"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"3912","DOI":"10.1109\/TCSVT.2023.3235522","article-title":"AGPN: action granularity pyramid network for video action recognition","volume":"33","author":"Chen","year":"2023","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"570","DOI":"10.1016\/j.icte.2023.12.004","article-title":"Making TSM better: preserving foundational philosophy for efficient action recognition","volume":"10","author":"Ryu","year":"2024","journal-title":"ICT Express"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"4208","DOI":"10.3390\/s20154208","article-title":"Monitoring of assembly process using deep learning technology","volume":"20","author":"Chen","year":"2020","journal-title":"Sensors"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"1291","DOI":"10.1007\/s10514-018-9706-9","article-title":"Kinesthetic teaching and attentional supervision of structured tasks in human-robot interaction","volume":"43","author":"Caccavale","year":"2019","journal-title":"Auton Rob"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"102231","DOI":"10.1016\/j.rcim.2021.102231","article-title":"A survey of robot learning strategies for human-robot collaboration in industrial settings","volume":"73","author":"Mukherjee","year":"2022","journal-title":"Robot Comput Integr Manuf"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"3728","DOI":"10.1109\/LRA.2021.3064149","article-title":"Fine-grained activity recognition for assembly videos","volume":"6","author":"Jones","year":"2021","journal-title":"IEEE Robot Autom Lett"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1016\/j.procir.2022.02.184","article-title":"A methods-time-measurement based approach to enable action recognition for multi-variant assembly in human-robot collaboration","volume":"106","author":"Koch","year":"2022","journal-title":"Procedia CIRP"},{"key":"ref22","series-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2017 Jul 21\u201326; Honolulu, HI, USA","first-page":"1003","article-title":"Temporal convolutional networks for action segmentation and detection","author":"Lea"},{"key":"ref23","series-title":"2014 IEEE Conference on Computer Vision and Pattern Recognition; 2014 Jun 23\u201328; Columbus, OH, USA","first-page":"780","article-title":"The language of actions: recovering the syntax and semantics of goal-directed human activities","author":"Kuehne"},{"key":"ref24","series-title":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2016 Jun 27\u201330; Las Vegas, NV, USA","first-page":"1049","article-title":"Temporal action localization in untrimmed videos via multi-stage CNNs","author":"Shou"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1016\/j.cirp.2018.04.066","article-title":"Deep learning-based human motion recognition for predictive context-aware human-robot collaboration","volume":"67","author":"Wang","year":"2018","journal-title":"CIRP Ann"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"107192","DOI":"10.1016\/j.compbiomed.2023.107192","article-title":"Improving performance of human action intent recognition: analysis of gait recognition machine learning algorithms and optimal combination with inertial measurement units","volume":"163","author":"Liu","year":"2023","journal-title":"Comput Biol Med"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"806","DOI":"10.3390\/bioengineering11080806","article-title":"Adaptive detection in real-time gait analysis through the dynamic gait event identifier","volume":"11","author":"Liu","year":"2024","journal-title":"Bioengineering"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"102184","DOI":"10.1016\/j.rcim.2021.102184","article-title":"Hybrid machine learning for human action recognition and prediction in assembly","volume":"72","author":"Zhang","year":"2021","journal-title":"Robot Comput Integr Manuf"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"4279","DOI":"10.3390\/s22114279","article-title":"Prediction-based human-robot collaboration in assembly tasks using a learning from demonstration model","volume":"22","author":"Zhang","year":"2022","journal-title":"Sensors"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"101792","DOI":"10.1016\/j.aei.2022.101792","article-title":"Human-object integrated assembly intention recognition for context-aware human-robot collaborative assembly","volume":"54","author":"Zhang","year":"2022","journal-title":"Adv Eng Inform"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"272","DOI":"10.1016\/j.procir.2019.04.080","article-title":"Deep learning-based human motion prediction considering context awareness for human-robot collaboration in manufacturing","volume":"83","author":"Liu","year":"2019","journal-title":"Procedia CIRP"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"8579","DOI":"10.1109\/TIE.2021.3105977","article-title":"Toward proactive human-robot collaborative assembly: a multimodal transfer-learning-enabled action prediction approach","volume":"69","author":"Li","year":"2022","journal-title":"IEEE Trans Ind Electron"},{"key":"ref33","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"ref34","unstructured":"Marcus G. Deep learning: a critical appraisal. arXiv:1801.00631. 2018."},{"key":"ref35","doi-asserted-by":"crossref","first-page":"e253","DOI":"10.1017\/S0140525X16001837","article-title":"Building machines that learn and think like people","volume":"40","author":"Lake","year":"2017","journal-title":"Behav Brain Sci"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"051003","DOI":"10.1115\/1.4064258","article-title":"Early prediction of human intention for human-robot collaboration using transformer network","volume":"24","author":"Zhang","year":"2024","journal-title":"J Comput Inf Sci Eng"},{"key":"ref37","series-title":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2016 Jun 27\u201330; Las Vegas, NV, USA","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He"},{"key":"ref38","doi-asserted-by":"crossref","first-page":"6647","DOI":"10.1109\/TPAMI.2020.3021756","article-title":"MS-TCN++: multi-stage temporal convolutional network for action segmentation","volume":"45","author":"Li","year":"2023","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref39","series-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR); 2020 Jun 13\u201319; Seattle, WA, USA","first-page":"11531","article-title":"ECA-net: efficient channel attention for deep convolutional neural networks","author":"Wang"},{"key":"ref40","series-title":"2009 IEEE Conference on Computer Vision and Pattern Recognition; 2009 Jun 20\u201325; Miami, FL, USA","first-page":"248","article-title":"ImageNet: a large-scale hierarchical image database","author":"Deng"},{"key":"ref41","series-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR); 2020 Jun 13\u201319; Seattle, WA, USA","first-page":"12592","article-title":"AugFPN: improving multi-scale feature learning for object detection","author":"Guo"},{"key":"ref42","series-title":"2021 IEEE Winter Conference on Applications of Computer Vision (WACV); 2021 Jan 3\u20138; Waikoloa, HI, USA","first-page":"2321","article-title":"Alleviating over-segmentation errors by detecting action boundaries","author":"Ishikawa"},{"key":"ref43","doi-asserted-by":"crossref","unstructured":"Yi F, Wen H, Jiang T. ASFormer: transformer for action segmentation. arXiv:2110.08568. 2021.","DOI":"10.5244\/C.35.49"},{"key":"ref44","first-page":"2262","article-title":"Iterative contrast-classify for semi-supervised temporal action segmentation","volume":"36","author":"Singhania","year":"2022","journal-title":"Proc AAAI Conf Artif Intell"}],"container-title":["Computers, Materials & Continua"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/cdn.techscience.cn\/files\/cmc\/2025\/TSP_CMC-84-2\/TSP_CMC_65895\/TSP_CMC_65895.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T01:53:01Z","timestamp":1763344381000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.techscience.com\/cmc\/v84n2\/62926"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":44,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025]]},"published-print":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.32604\/cmc.2025.065895","relation":{},"ISSN":["1546-2226"],"issn-type":[{"type":"electronic","value":"1546-2226"}],"subject":[],"published":{"date-parts":[[2025]]}}}