{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T18:17:07Z","timestamp":1775067427923,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":29,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T00:00:00Z","timestamp":1705622400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,1,19]]},"DOI":"10.1145\/3647649.3647676","type":"proceedings-article","created":{"date-parts":[[2024,5,3]],"date-time":"2024-05-03T19:40:20Z","timestamp":1714765220000},"page":"159-165","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Assembly Action Recognition based on Dual Stream Fusion of Skeleton and Video Data"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8015-387X","authenticated-orcid":false,"given":"Chunhui","family":"Zhao","sequence":"first","affiliation":[{"name":"College of Information and Communication Engineering, Harbin Engineering University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3577-1079","authenticated-orcid":false,"given":"Tao","family":"Jin","sequence":"additional","affiliation":[{"name":"College of Information and Communication Engineering,, Harbin Engineering University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9601-536X","authenticated-orcid":false,"given":"Nan","family":"Su","sequence":"additional","affiliation":[{"name":"College of Information and Communication Engineering,, Harbin Engineering University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0751-7726","authenticated-orcid":false,"given":"Yiming","family":"Yan","sequence":"additional","affiliation":[{"name":"College of Information and Communication Engineering,, Harbin Engineering University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,5,3]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.3390\/s19051005"},{"key":"e_1_3_2_1_2_1","first-page":"977","article-title":"Reconfigurable handling systems as an enabler for large components in mass customized production[J]","volume":"2013","author":"M\u00fcller R","unstructured":"M\u00fcller R, Esser M, Vette M. Reconfigurable handling systems as an enabler for large components in mass customized production[J]. Journal of Intelligent Manufacturing,2013, 24: 977-990.","journal-title":"Journal of Intelligent Manufacturing"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Ziaeefard Maryam Hossein E. Hierarchical Human Action Recognition by Normalized-Polar Histogram[C]\/\/20th Internati-onal Conference on Pattern Recognition 2010: 3720-3723.","DOI":"10.1109\/ICPR.2010.906"},{"key":"e_1_3_2_1_4_1","volume-title":"Hierarchical recurrent neural network for skeleton based action recognition[C]\/\/IEEE Conference on Computer Vision and Pattern Recognition","author":"Du Y","year":"2015","unstructured":"Du Y, Wang W, Wang L. Hierarchical recurrent neural network for skeleton based action recognition[C]\/\/IEEE Conference on Computer Vision and Pattern Recognition, 2015: 1110-1118."},{"key":"e_1_3_2_1_5_1","volume-title":"Conference on Computer Vision and Pattern Recognition Workshops","author":"Kim T S","unstructured":"Kim T S, Austin R. Interpretable 3D Human Action Analysis with Temporal Convolutional Networks[C]\/\/IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2017: 1623-1631."},{"key":"e_1_3_2_1_6_1","first-page":"807","volume":"2018","author":"Hou Y H","unstructured":"Hou Y H, ZhaoY L, Pichao W, Skeleton Optical Spectra-Based Action Recognition Using Convolutional Neural Networks[J]. IEEE Transactions on Circuits and Systems for Video Technology ,2018, 18: 807-811.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"e_1_3_2_1_7_1","volume-title":"24th ACM international conference on Multimedia","author":"Pichao W","year":"2016","unstructured":"Pichao W, Li Z Y, Hou Y H, Action Recognition Based on Joint Trajectory Maps Using Convolutional Neural Networks[C]\/\/Pro-ceedings of the 24th ACM international conference on Multimedia, 2016."},{"key":"e_1_3_2_1_8_1","first-page":"624","volume":"2017","author":"Li C K","unstructured":"Li C K, Hou Y H, Pichao W, Joint Distance Maps Based Action Recognition With Convolutional Neural Networks[J]. IEEE Signal Processing Letters ,2017, 24: 624-628.","journal-title":"IEEE Signal Processing Letters"},{"key":"e_1_3_2_1_9_1","volume-title":"Spatial temporal graph convolutional networks for skeleton based action recognition-n[C]\/\/Thirty-second AAAI conference on artificial intelligence","author":"Yan S J","year":"2018","unstructured":"Yan S J, Xiong Y J, and Lin D H. Spatial temporal graph convolutional networks for skeleton based action recognition-n[C]\/\/Thirty-second AAAI conference on artificial intelligence, 2018: 1-4."},{"key":"e_1_3_2_1_10_1","volume-title":"Conference on Computer Vision and Pattern Recognition","author":"Li M S","unstructured":"Li, M S, Chen S H, Chen X, Actional-Structural Graph Convolutional Networks for Skeleton-Based Action Recognitio-n[C]\/\/IEEE Conference on Computer Vision and Pattern Recognition, 2019: 3590-3598."},{"key":"e_1_3_2_1_11_1","volume-title":"Context Aware Graph Convolution for Skeleton-Based Action Recognition[C]\/\/IEEE Conference on Computer Vision and Pattern Recognition","author":"Zhang X K","year":"2020","unstructured":"Zhang, X K, Xu C, Tao D C. Context Aware Graph Convolution for Skeleton-Based Action Recognition[C]\/\/IEEE Conference on Computer Vision and Pattern Recognition, 2020: 14321-14330."},{"key":"e_1_3_2_1_12_1","volume-title":"Conference on Computer Vision and Pattern Recognition","author":"Shi L","unstructured":"Shi L, Zhang Y F, Cheng J, Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognitio-n[C]\/\/IEEE Conference on Computer Vision and Pattern Recognition, 2019: 12018-12027."},{"key":"e_1_3_2_1_13_1","volume-title":"Conference on Computer Vision and Pattern Recog-nition","author":"Liu Z Y","unstructured":"Liu Z Y, Zhang H W, Chen Z H, Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognitio-n[C]\/\/IEEE Conference on Computer Vision and Pattern Recog-nition, 2020: 140-149."},{"key":"e_1_3_2_1_14_1","volume-title":"Chen K","author":"Duan H D","year":"2022","unstructured":"Duan, H D, Wang J Q, Chen K, PYSKL: Towards Good Practices for Skeleton Action Recognition[C]\/\/Proceedings of the 30th ACM International Conference on Multimedia, 2022."},{"issue":"04","key":"e_1_3_2_1_15_1","first-page":"41","article-title":"Assembly action recognition based on attentional spatio-temporal feature network[J]","volume":"50","author":"Zhao Xicong","year":"2022","unstructured":"Zhao Xicong, Huang Kai, Chen Chengjun, Assembly action recognition based on attentional spatio-temporal feature network[J]. Machine Tools and Hydraulics, 2022, 50(04): 41-45.","journal-title":"Machine Tools and Hydraulics"},{"key":"e_1_3_2_1_16_1","first-page":"325","article-title":"Repetitive assembly action recognition based on object detection and pose estimatio-n[J]","volume":"2020","author":"Chen C J","unstructured":"Chen C J, Wang T N, Li D N, Jun Hong, Repetitive assembly action recognition based on object detection and pose estimatio-n[J]. Journal of Manufacturing Systems,2020,55: 325-333.","journal-title":"Journal of Manufacturing Systems"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10845-021-01815-x"},{"key":"e_1_3_2_1_18_1","volume-title":"Two-Stream Convolutional Networks for ActionRecognition in Videos[C]\/\/27th International Conf-erence on Neural Information Processing Systems[J]. ArXiv abs\/1406.2199","author":"Simonyan K","year":"2014","unstructured":"Simonyan K, Zisserman A, Two-Stream Convolutional Networks for ActionRecognition in Videos[C]\/\/27th International Conf-erence on Neural Information Processing Systems[J]. ArXiv abs\/1406.2199, 2014."},{"key":"e_1_3_2_1_19_1","volume-title":"Common Objects in Context[C]\/\/European Conference on Computer Vision","author":"Lin T Y","year":"2014","unstructured":"Lin, T Y, Michael M, Serge J, \"Microsoft COCO: Common Objects in Context[C]\/\/European Conference on Computer Vision, 2014."},{"key":"e_1_3_2_1_20_1","volume-title":"Semi-Supervised Classification with Graph Convolutional Networks[J]. ArXiv abs\/1609.02907","author":"Kipf","year":"2016","unstructured":"Kipf, Thomas, Max W. Semi-Supervised Classification with Graph Convolutional Networks[J]. ArXiv abs\/1609.02907, 2016."},{"key":"e_1_3_2_1_21_1","volume-title":"Conference on Computer Vision and Patte-rn Recognition","author":"He K M","unstructured":"He K M, Zhang S Q, Ren, Deep Residual Learning for Image Recognition[C]\/\/IEEE Conference on Computer Vision and Patte-rn Recognition, 2015: 770- 778."},{"key":"e_1_3_2_1_22_1","volume-title":"International Conference on Computer Vision Workshops","author":"Hara","unstructured":"Hara, Kensho, Hirokatsu K, Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognit-ion[C]\/\/IEEE International Conference on Computer Vision Workshops, 2017: 3154-3160."},{"key":"e_1_3_2_1_23_1","volume-title":"A Large Scale Dataset for 3D Human Activity Analysis[C]\/\/ IEEE Conference on Computer Vision and Pattern Recognition","author":"Shahroudy","year":"2016","unstructured":"Shahroudy, Amir, Liu J, NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis[C]\/\/ IEEE Conference on Computer Vision and Pattern Recognition, 2016: 1010-1019."},{"key":"e_1_3_2_1_24_1","volume-title":"Conference on Computer Vision and Pattern Recognition","author":"Cheng K","unstructured":"Cheng K, Zhang Y F, He X Y, Skeleton-Based Action Recognition With Shift Graph Convolutional Network[C]\/\/IEEE Conference on Computer Vision and Pattern Recognition, 2020: 180-189."},{"key":"e_1_3_2_1_25_1","volume-title":"Channel-wise topology refinement graph convolution for skeleton-based action recognition[C]\/\/ IEEE\/CVF International Conference on Computer Vision","author":"Chen Y X","year":"2021","unstructured":"Chen Y X, Zhang Z Q, Yuan C F, Channel-wise topology refinement graph convolution for skeleton-based action recognition[C]\/\/ IEEE\/CVF International Conference on Computer Vision, 2021:13359\u201313368."},{"key":"e_1_3_2_1_26_1","volume-title":"Revisiting Skeleton-based Action Recognition[C]\/\/ IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Duan Y.","year":"2022","unstructured":"H. Duan, Y. Zhao, K. Chen, D. Lin and B. Dai, Revisiting Skeleton-based Action Recognition[C]\/\/ IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022: 2959-2968."},{"key":"e_1_3_2_1_27_1","volume-title":"Human Activity Recognition with Pose-driven Attention to RGB[C]\/\/ British Machine Vision Conference","author":"Baradel","year":"2018","unstructured":"Baradel,Fabien,Christian W. Human Activity Recognition with Pose-driven Attention to RGB[C]\/\/ British Machine Vision Conference, 2018."},{"key":"e_1_3_2_1_28_1","first-page":"6","volume-title":"IEEE","author":"Song C.","year":"2018","unstructured":"S. Song , C. Lan , J. Xing , Skeleton-indexed deep multi-modal feature learning for high performance human action recognition[C]\/\/ 2018 IEEE International Conference on Multimedia and Expo, IEEE, 2018, pp. 1\u20136 ."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107356"}],"event":{"name":"ICIGP 2024: 2024 the 7th International Conference on Image and Graphics Processing","location":"Beijing China","acronym":"ICIGP 2024"},"container-title":["Proceedings of the 2024 7th International Conference on Image and Graphics Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3647649.3647676","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3647649.3647676","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T14:54:10Z","timestamp":1769525650000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3647649.3647676"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,19]]},"references-count":29,"alternative-id":["10.1145\/3647649.3647676","10.1145\/3647649"],"URL":"https:\/\/doi.org\/10.1145\/3647649.3647676","relation":{},"subject":[],"published":{"date-parts":[[2024,1,19]]},"assertion":[{"value":"2024-05-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}