{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T04:03:03Z","timestamp":1743134583575,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":33,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819629107"},{"type":"electronic","value":"9789819629114"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-96-2911-4_7","type":"book-chapter","created":{"date-parts":[[2025,3,10]],"date-time":"2025-03-10T09:44:00Z","timestamp":1741599840000},"page":"54-68","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Learning-Based Monitoring System for\u00a0Factory Assembly Behavior"],"prefix":"10.1007","author":[{"given":"Yi","family":"Liu","sequence":"first","affiliation":[]},{"given":"Hao","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Xiaodong","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Man","family":"Jiao","sequence":"additional","affiliation":[]},{"given":"Wenchang","family":"Li","sequence":"additional","affiliation":[]},{"given":"Xiaochuan","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Ruijun","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,3,11]]},"reference":[{"key":"7_CR1","doi-asserted-by":"crossref","unstructured":"Wang, J., et al.: Real-time Workshop information acquisition and monitoring system based on three-layer network. In: 3rd International Conference on Electric and Electronics. Atlantis Press (2013)","DOI":"10.2991\/eeic-13.2013.64"},{"key":"7_CR2","doi-asserted-by":"publisher","first-page":"325","DOI":"10.1016\/j.jmsy.2020.04.018","volume":"55","author":"C Chen","year":"2020","unstructured":"Chen, C., et al.: Repetitive assembly action recognition based on object detection and pose estimation. J. Manuf. Syst. 55, 325\u2013333 (2020)","journal-title":"J. Manuf. Syst."},{"key":"7_CR3","doi-asserted-by":"crossref","unstructured":"Parmar, P., Morris, B.T.: Learning to score Olympic events. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (2017)","DOI":"10.1109\/CVPRW.2017.16"},{"key":"7_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107388","volume":"229","author":"L-J Dong","year":"2021","unstructured":"Dong, L.-J., et al.: Learning and fusing multiple hidden substages for action quality assessment. Knowl. Based Syst. 229, 107388 (2021)","journal-title":"Knowl. Based Syst."},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Wang, S., et al.: TSA-net: tube self-attention network for action quality assessment. In: Proceedings of the 29th ACM International Conference on Multimedia (2021)","DOI":"10.1145\/3474085.3475438"},{"key":"7_CR6","doi-asserted-by":"crossref","unstructured":"Parsa, B., Dariush, B.: Spatio-temporal pyramid graph convolutions for human action recognition and postural assessment. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (2020)","DOI":"10.1109\/WACV45572.2020.9093368"},{"issue":"1","key":"7_CR7","first-page":"3831","volume":"15","author":"M-F Balcan","year":"2014","unstructured":"Balcan, M.-F., Liang, Y., Gupta, P.: Robust hierarchical clustering. J. Mach. Learn. Res. 15(1), 3831\u20133871 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"7_CR8","unstructured":"Bazarevsky, V.: BlazePose: On-device Real-time Body Pose tracking. arXiv preprint arXiv:2006.10204 (2020)"},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Lin, C., et al.: Learning salient boundary feature for anchor-free temporal action localization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.00333"},{"issue":"54","key":"7_CR10","first-page":"1","volume":"21","author":"G Siglidis","year":"2020","unstructured":"Siglidis, G., et al.: Grakel: a graph kernel library in python. J. Mach. Learn. Res. 21(54), 1\u20135 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Redmon, J., et al.: You only look once: Unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"7_CR12","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Advances in Neural Information Processing Systems, vol. 27 (2014)"},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"Tran, D., et al.: Learning spatiotemporal features with 3d convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"7_CR14","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"7_CR15","doi-asserted-by":"crossref","unstructured":"Cao, Z., et al.: Realtime multi-person 2d pose estimation using part affinity fields. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.143"},{"key":"7_CR16","doi-asserted-by":"publisher","unstructured":"Newell, A., Yang, K., Deng, J.: Stacked Hourglass Networks for Human Pose Estimation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 483\u2013499. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_29","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"7_CR17","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.cogr.2020.12.002","volume":"1","author":"C Ma","year":"2021","unstructured":"Ma, C., et al.: Visual information processing for deep-sea visual monitoring system. Cogn. Robot. 1, 3\u201311 (2021)","journal-title":"Cogn. Robot."},{"key":"7_CR18","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, vol. 25 (2012)"},{"key":"7_CR19","doi-asserted-by":"crossref","unstructured":"Martinez, J., et al.: A simple yet effective baseline for 3d human pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision (2017)","DOI":"10.1109\/ICCV.2017.288"},{"key":"7_CR20","doi-asserted-by":"crossref","unstructured":"Sun, K., et al.: Deep high-resolution representation learning for human pose estimation. In: Proceedings of the IEEE\/CVF Conference On Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00584"},{"key":"7_CR21","doi-asserted-by":"crossref","unstructured":"Yan, S., Xiong, Y., Lin, D.: Spatial temporal graph convolutional networks for skeleton-based action recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32. No. 1 (2018)","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"7_CR22","doi-asserted-by":"publisher","unstructured":"Wang, L., et al.: Temporal segment networks: towards good practices for deep action recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) Computer Vision \u2013 ECCV 2016. LNCS, vol. 9912. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_2","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"7_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-01225-0_1","volume-title":"Computer Vision \u2013 ECCV 2018","author":"T Lin","year":"2018","unstructured":"Lin, T., Zhao, X., Su, H., Wang, C., Yang, M.: BSN: boundary sensitive network for temporal action proposal generation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 3\u201321. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01225-0_1"},{"key":"7_CR24","doi-asserted-by":"crossref","unstructured":"Zheng, C., et al.: 3d human pose estimation with spatial and temporal transformers. In: Proceedings of the IEEE\/CVF International Conference On Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.01145"},{"key":"7_CR25","doi-asserted-by":"crossref","unstructured":"Zhao, Q., et al.: Poseformerv2: exploring frequency domain for efficient and robust 3d human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.00857"},{"key":"7_CR26","doi-asserted-by":"crossref","unstructured":"Li, W., et al.: MHFormer: multi-hypothesis transformer for 3d human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.01280"},{"key":"7_CR27","doi-asserted-by":"crossref","unstructured":"Gao, J., et al.: Turn tap: Temporal unit regression network for temporal action proposals. In: Proceedings of the IEEE International Conference on Computer Vision (2017)","DOI":"10.1109\/ICCV.2017.392"},{"key":"7_CR28","doi-asserted-by":"crossref","unstructured":"Gao, J., Yang, Z., Nevatia, R.: Cascaded boundary regression for temporal action detection. arXiv preprint arXiv:1705.01180 (2017)","DOI":"10.5244\/C.31.52"},{"key":"7_CR29","doi-asserted-by":"crossref","unstructured":"Long, F., et al.: Gaussian temporal awareness networks for action localization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00043"},{"key":"7_CR30","doi-asserted-by":"crossref","unstructured":"Shou, Z., et al.: CDC: convolutional-de-convolutional networks for precise temporal action localization in untrimmed videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.155"},{"key":"7_CR31","doi-asserted-by":"publisher","unstructured":"Zhao, P., Xie, L., Ju, C., Zhang, Y., Wang, Y., Tian, Q.: Bottom-up temporal action localization with mutual regularization. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12353, pp. 539\u2013555. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58598-3_32","DOI":"10.1007\/978-3-030-58598-3_32"},{"key":"7_CR32","doi-asserted-by":"crossref","unstructured":"Xu, M., et al.: G-tad: sub-graph localization for temporal action detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.01017"},{"key":"7_CR33","doi-asserted-by":"crossref","unstructured":"Koga, S., et al.: Optimizing food sample handling and placement pattern recognition with YOLO: advanced techniques in robotic object detection. In: Proceedings of Cognitive Robotics (2024)","DOI":"10.2139\/ssrn.4694378"}],"container-title":["Communications in Computer and Information Science","Artificial Intelligence and Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-2911-4_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,10]],"date-time":"2025-03-10T09:44:13Z","timestamp":1741599853000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-2911-4_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819629107","9789819629114"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-2911-4_7","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"11 March 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ISAIR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Artificial Intelligence and Robotics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Guilin","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"isair2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/isair.site\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}