{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T13:48:04Z","timestamp":1785937684555,"version":"3.56.0"},"reference-count":32,"publisher":"MDPI AG","issue":"15","license":[{"start":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T00:00:00Z","timestamp":1785888000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276032"],"award-info":[{"award-number":["62276032"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"award":["62276032"],"award-info":[{"award-number":["62276032"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Industrial assembly videos contain substantial temporal redundancy, creating a need for preprocessing methods that remain usable when task-specific labels, retraining, or opaque learned selection rules are undesirable. This study designs a deterministic, training-free skeleton-semantic keyframe extraction framework for fixed-view monocular assembly video preprocessing. OpenPose BODY-25 keypoints are confidence-filtered, normalized, interpolated, and represented by eight upper-body joints. Neck-relative bilateral-wrist activity controls an inverse threshold, while sequential reference updates and a maximum-gap rule provide an explicit output budget. At 271 frames per analyzed file, the method obtains CVsd = 0.3340 \u00b1 0.1117 and MSD = 0.7781 \u00b1 0.1003, compared with 1.0681 \u00b1 0.0754 and 0.2961 \u00b1 0.0305 for pretrained MViT-V2-S feature clustering. Thus, under the shared normalized skeleton evaluation, the method reduces semantic-distance variation by 68.7% and increases adjacent pose-state separation by 162.8% relative to MViT. Matched ablation identifies the skeleton representation as the primary source of this organization; adaptive thresholding provides smaller, budget-dependent density adjustment. A second independent human annotation and adjudication establish a 34-transition event reference. Event results reveal a complementary trade-off: the proposed method retains 79.41% of transitions within \u00b10.5 s, whereas several temporal and appearance-based baselines retain 97.06\u2013100%, showing that pose-state diversity and process-boundary coverage are different sampling objectives. Matched-baseline observed-joint-only and confidence-weighted analyses show that interpolation contributes to numerical regularity, but the proposed method retains substantially lower semantic-distance variation and greater adjacent pose-state separation than all evaluated baselines under both missing-data treatments. These results establish the method as an interpretable, budget-controllable preprocessing strategy for pose-oriented review and data reduction in the evaluated fixed-view setting. Validation across independently recorded production environments and task-specific downstream systems is the next step toward broader deployment.<\/jats:p>","DOI":"10.3390\/s26154956","type":"journal-article","created":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T13:16:29Z","timestamp":1785935789000},"page":"4956","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Training-Free Skeleton-Semantic Keyframe Extraction for Fixed-View Industrial Assembly Video: Method Design and Case Study Evaluation"],"prefix":"10.3390","volume":"26","author":[{"given":"Qianhui","family":"Li","sequence":"first","affiliation":[{"name":"School of Computer Science, Yangtze University, Jingzhou 434023, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hua","family":"Xiang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Yangtze University, Jingzhou 434023, China"},{"name":"Research Center for Digital Agriculture and Intelligent Engineering, Yangtze University, Jingzhou 434023, China"},{"name":"Artificial Intelligence Research Platform, Yangtze University, Jingzhou 434023, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tongxi","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Yangtze University, Jingzhou 434023, China"},{"name":"Research Center for Digital Agriculture and Intelligent Engineering, Yangtze University, Jingzhou 434023, China"},{"name":"Artificial Intelligence Research Platform, Yangtze University, Jingzhou 434023, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0626-7470","authenticated-orcid":false,"given":"Wei","family":"Zhan","sequence":"additional","affiliation":[{"name":"School of Computer Science, Yangtze University, Jingzhou 434023, China"},{"name":"Research Center for Digital Agriculture and Intelligent Engineering, Yangtze University, Jingzhou 434023, China"},{"name":"Artificial Intelligence Research Platform, Yangtze University, Jingzhou 434023, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,5]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"110527","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."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Sener, F., Chatterjee, D., Shelepov, D., He, K., Singhania, D., Wang, R., and Yao, A. (2022, January 18\u201324). Assembly101: A large-scale multi-view video dataset for understanding procedural activities. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.02042"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"103764","DOI":"10.1016\/j.cviu.2023.103764","article-title":"MECCANO: A multimodal egocentric dataset for humans behavior understanding in the industrial-like domain","volume":"235","author":"Ragusa","year":"2023","journal-title":"Comput. Vis. Image Underst."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Ben-Shabat, Y., Yu, X., Saleh, F., Campbell, D., Rodriguez-Opazo, C., Li, H., and Gould, S. (2021, January 3\u20138). The IKEA ASM dataset: Understanding people assembling furniture through actions, objects and pose. Proceedings of the IEEE Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA.","DOI":"10.1109\/WACV48630.2021.00089"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Ben-Shabat, Y., Paul, J., Segev, E., Shrout, O., and Gould, S. (2024, January 3\u20138). IKEA Ego 3D dataset: Understanding furniture assembly actions from ego-view 3D point clouds. Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA.","DOI":"10.1109\/WACV57701.2024.00430"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"7457","DOI":"10.1109\/JIOT.2020.2984887","article-title":"Edge intelligence: The confluence of edge computing and artificial intelligence","volume":"7","author":"Deng","year":"2020","journal-title":"IEEE Internet Things J."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1838","DOI":"10.1109\/JPROC.2021.3117472","article-title":"Video summarization using deep neural networks: A survey","volume":"109","author":"Apostolidis","year":"2021","journal-title":"Proc. IEEE"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1699","DOI":"10.1109\/TPAMI.2020.3029425","article-title":"A dynamic frame selection framework for fast video recognition","volume":"44","author":"Wu","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"3278","DOI":"10.1109\/TCSVT.2020.3037883","article-title":"AC-SUM-GAN: Connecting actor-critic and generative adversarial networks for unsupervised video summarization","volume":"31","author":"Apostolidis","year":"2021","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1016\/j.neucom.2022.11.028","article-title":"Unsupervised video summarization using deep non-local video summarization networks","volume":"519","author":"Zang","year":"2023","journal-title":"Neurocomputing"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Sheng, H., Wang, X., Zhang, C., Wang, J., Duan, P., and Wang, Y. (2026). AIGC video detection based on the fusion of spatial-frequency-optical flow multimodal features. J. Syst. Eng. Electron., 1\u201315.","DOI":"10.23919\/JSEE.2026.000049"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"3820","DOI":"10.1109\/TNNLS.2024.3357118","article-title":"Adaptive sparse memory networks for efficient and robust video object segmentation","volume":"36","author":"Dang","year":"2025","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Duan, H., Zhao, Y., Chen, K., Lin, D., and Dai, B. (2022, January 18\u201324). Revisiting skeleton-based action recognition. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.00298"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Chen, Y., Zhang, Z., Yuan, C., Li, B., Deng, Y., and Hu, W. (2021, January 10\u201317). Channel-wise topology refinement graph convolution for skeleton-based action recognition. Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada.","DOI":"10.1109\/ICCV48922.2021.01311"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Lee, J., Lee, M., Lee, D., and Lee, S. (2023, January 1\u20136). Hierarchically decomposed graph convolutional networks for skeleton-based action recognition. Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), Paris, France.","DOI":"10.1109\/ICCV51070.2023.00958"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"514","DOI":"10.1109\/TPAMI.2024.3466212","article-title":"InfoGCN++: Learning representation by predicting the future for online skeleton-based action recognition","volume":"47","author":"Chi","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"104012","DOI":"10.1016\/j.cviu.2024.104012","article-title":"Static graph convolution with learned temporal and channel-wise graph topology generation for skeleton-based action recognition","volume":"244","author":"Li","year":"2024","journal-title":"Comput. Vis. Image Underst."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1109\/TPAMI.2019.2929257","article-title":"OpenPose: Realtime multi-person 2D pose estimation using Part Affinity Fields","volume":"43","author":"Cao","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1212","DOI":"10.1109\/TPAMI.2023.3330016","article-title":"ViTPose++: Vision transformer for generic body pose estimation","volume":"46","author":"Xu","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Sun, P., Gu, K., Wang, Y., Yang, L., and Yao, A. (2024, January 3\u20138). Rethinking visibility in human pose estimation: Occluded pose reasoning via transformers. Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA.","DOI":"10.1109\/WACV57701.2024.00580"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Ye, S., Hong, Z., Zheng, J., and Zhang, S. (2023, January 4\u201310). Improving occluded human pose estimation via linked joints. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes Island, Greece.","DOI":"10.1109\/ICASSP49357.2023.10097055"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Rublee, E., Rabaud, V., Konolige, K., and Bradski, G. (2011, January 6\u201313). ORB: An efficient alternative to SIFT or SURF. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Barcelona, Spain.","DOI":"10.1109\/ICCV.2011.6126544"},{"key":"ref_23","unstructured":"Lucas, B.D., and Kanade, T. (1981, January 24\u201328). An iterative image registration technique with an application to stereo vision. Proceedings of the 7th International Joint Conference on Artificial Intelligence (IJCAI), Vancouver, BC, Canada."},{"key":"ref_24","unstructured":"Arthur, D., and Vassilvitskii, S. (2007, January 7\u20139). k-means++: The advantages of careful seeding. Proceedings of the Eighteenth Annual ACM-SIAM Symposium on Discrete Algorithms, New Orleans, LA, USA."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Li, Y., Wu, C.-Y., Fan, H., Mangalam, K., Xiong, B., Malik, J., and Feichtenhofer, C. (2022, January 19\u201324). MViTv2: Improved multiscale vision transformers for classification and detection. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Yi, F., Wen, H., and Jiang, T. (2021, January 22\u201325). ASFormer: Transformer for action segmentation. Proceedings of the British Machine Vision Conference (BMVC), Online.","DOI":"10.5244\/C.35.49"},{"key":"ref_27","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":"ref_28","doi-asserted-by":"crossref","unstructured":"Xu, L., Zhao, L., Sun, X., Wang, D., Li, G., and Yan, K. (2024, January 14\u201319). A comprehensive framework for occluded human pose estimation. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Seoul, Republic of Korea.","DOI":"10.1109\/ICASSP48485.2024.10448372"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"105441","DOI":"10.1016\/j.imavis.2025.105441","article-title":"Resource-aware strategies for real-time multi-person pose estimation","volume":"155","author":"Esmail","year":"2025","journal-title":"Image Vis. Comput."},{"key":"ref_30","first-page":"2760","article-title":"TSM: Temporal shift module for efficient and scalable video understanding on edge devices","volume":"44","author":"Lin","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C. (2020, January 13\u201319). X3D: Expanding architectures for efficient video recognition. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Wang, L., Huang, B., Zhao, Z., Tong, Z., He, Y., Wang, Y., Wang, Y., and Qiao, Y. (2023, January 17\u201324). VideoMAE V2: Scaling video masked autoencoders with dual masking. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.01398"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/15\/4956\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T13:18:30Z","timestamp":1785935910000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/15\/4956"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,5]]},"references-count":32,"journal-issue":{"issue":"15","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["s26154956"],"URL":"https:\/\/doi.org\/10.3390\/s26154956","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,5]]}}}