{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T06:06:33Z","timestamp":1784181993173,"version":"3.55.0"},"reference-count":59,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62476076"],"award-info":[{"award-number":["62476076"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Engineering Applications of Artificial Intelligence"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.engappai.2026.114966","type":"journal-article","created":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T06:52:59Z","timestamp":1778309579000},"page":"114966","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"P1","title":["Multi-scale spatio-temporal hierarchical collaborative network and powergrid construction video action dataset for action recognition in power construction scenarios"],"prefix":"10.1016","volume":"178","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4240-5554","authenticated-orcid":false,"given":"Shuo","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0045-3259","authenticated-orcid":false,"given":"Yaguang","family":"Kong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3377-1904","authenticated-orcid":false,"given":"Xiaoqing","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuangxun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weibin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.engappai.2026.114966_b1","doi-asserted-by":"crossref","unstructured":"Abbas, Yasir, Jalal, Atif, 2024. Drone-based human action recognition for surveillance: A multi-feature approach. In: Proceedings of the 2024 International Conference on Engineering & Computing Technologies. ICECT, pp. 1\u20136.","DOI":"10.1109\/ICECT61618.2024.10581378"},{"issue":"2","key":"10.1016\/j.engappai.2026.114966_b2","doi-asserted-by":"crossref","first-page":"526","DOI":"10.3390\/buildings14020526","article-title":"A review on construction safety: Hazards, mitigation strategies, and impacted sectors","volume":"14","author":"Almaskati","year":"2024","journal-title":"Buildings"},{"key":"10.1016\/j.engappai.2026.114966_b3","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2024.108243","article-title":"A hybrid attention-guided ConvNeXt-GRU network for action recognition","volume":"133","author":"An","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.engappai.2026.114966_b4","doi-asserted-by":"crossref","unstructured":"Arnab, Anurag, Dehghani, Mostafa, Heigold, Georg, Sun, Chen, Lu\u010di\u0107, Mario, Schmid, Cordelia, 2021. ViViT: A video vision transformer.. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. ICCV, pp. 6816\u20136826.","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"10.1016\/j.engappai.2026.114966_b5","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2025.111710","article-title":"Graph-based framework for temporal human action recognition and segmentation in industrial context","volume":"159","author":"Benmessabih","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.engappai.2026.114966_b6","volume":"Vol. 2","author":"Bertasius","year":"2021"},{"key":"10.1016\/j.engappai.2026.114966_b7","first-page":"19594","article-title":"Space\u2013time mixing attention for video transformer","volume":"34","author":"Bulat","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"issue":"8","key":"10.1016\/j.engappai.2026.114966_b8","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":"10.1016\/j.engappai.2026.114966_b9","doi-asserted-by":"crossref","unstructured":"Dai, Ruilong, Das, Shuvendu, Kahatapitiya, Kanchana, Michael, S. Ryoo, Br\u00e9mond, Francois, 2022. MS-TCT: Multi-scale temporal ConvTransformer for action detection.. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. CVPR, pp. 20009\u201320019.","DOI":"10.1109\/CVPR52688.2022.01941"},{"key":"10.1016\/j.engappai.2026.114966_b10","doi-asserted-by":"crossref","unstructured":"Dey, Arnab, Biswas, Samit, Workout action recognition in video streams using an attention driven residual DC-GRU network. Comput. Mater. Contin. 79 (2), 2024.","DOI":"10.32604\/cmc.2024.049512"},{"key":"10.1016\/j.engappai.2026.114966_b11","unstructured":"Fan, Quanfu, Chen, Richard, Panda, Rameswar, 2022. Can an image classifier suffice for action recognition?. In: Proceedings of the International Conference on Learning Representations. ICLR."},{"key":"10.1016\/j.engappai.2026.114966_b12","doi-asserted-by":"crossref","unstructured":"Fan, Haoqi, et al., 2021. Multiscale vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. ICCV, pp. 6804\u20136815.","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"10.1016\/j.engappai.2026.114966_b13","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, Christoph, Fan, Haoqi, Malik, Jitendra, He, Kaiming, 2019. SlowFast networks for video recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. ICCV, pp. 6201\u20136210.","DOI":"10.1109\/ICCV.2019.00630"},{"key":"10.1016\/j.engappai.2026.114966_b14","doi-asserted-by":"crossref","unstructured":"Gu, Chunhui, et al., 2018. AVA: A video dataset of spatio-temporally localized atomic visual actions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. CVPR, pp. 6047\u20136056.","DOI":"10.1109\/CVPR.2018.00633"},{"issue":"4","key":"10.1016\/j.engappai.2026.114966_b15","doi-asserted-by":"crossref","first-page":"1005","DOI":"10.3390\/buildings14041005","article-title":"Near-miss detection metrics: An approach to enable sensing technologies for proactive construction safety management","volume":"14","author":"Hashmi","year":"2024","journal-title":"Buildings"},{"key":"10.1016\/j.engappai.2026.114966_b16","doi-asserted-by":"crossref","unstructured":"Huang, Shanshan, Gong, Mingming, Tao, Dacheng, 2017. A coarse-fine network for keypoint localization. In: Proceedings of the IEEE International Conference on Computer Vision. ICCV, pp. 3047\u20133056.","DOI":"10.1109\/ICCV.2017.329"},{"key":"10.1016\/j.engappai.2026.114966_b17","doi-asserted-by":"crossref","unstructured":"Jiang, Zhiqiang, Yang, Jianhua, Jiang, Nan, Liu, Shuaiyan, Xie, Tao, Zhao, Lijun, Li, Ruifeng, 2025. YOWOv2: A stronger yet efficient multi-level detection framework for real-time spatio-temporal action detection.. In: Proceedings of Intelligent Robotics and Applications. pp. 33\u201348.","DOI":"10.1007\/978-981-96-0774-7_3"},{"key":"10.1016\/j.engappai.2026.114966_b18","series-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"10.1016\/j.engappai.2026.114966_b19","doi-asserted-by":"crossref","unstructured":"Kim, Minsoo, Spinola, Francesco, Benz, Peter, Kim, Tae-Hyun, 2024. A*: Atrous spatial temporal action recognition for real-time applications.. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. WACV, pp. 6999\u20137000.","DOI":"10.1109\/WACV57701.2024.00686"},{"key":"10.1016\/j.engappai.2026.114966_b20","doi-asserted-by":"crossref","unstructured":"Kuehne, Hildegard, Jhuang, Hueihan, Garrote, Estibaliz, Poggio, Tomaso, Serre, Thomas, 2011. HMDB: A large video database for human motion recognition.. In: Proceedings of the International Conference on Computer Vision. ICCV, pp. 2556\u20132563.","DOI":"10.1109\/ICCV.2011.6126543"},{"issue":"4","key":"10.1016\/j.engappai.2026.114966_b21","first-page":"4109","article-title":"Action recognition from a single coded image","volume":"45","author":"Kumawat","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.engappai.2026.114966_b22","doi-asserted-by":"crossref","unstructured":"Li, Yixuan, Wang, Zixu, Wang, Limin, Wu, Gangshan, 2020. Actions as moving points. In: Proceedings of the European Conference on Computer Vision. ECCV, pp. 68\u201384.","DOI":"10.1007\/978-3-030-58517-4_5"},{"key":"10.1016\/j.engappai.2026.114966_b23","unstructured":"Li, Kunchang, et al., 2021. Ct-net: Channel tensorization network for video classification. In: Proceedings of the International Conference on Learning Representations. ICLR."},{"key":"10.1016\/j.engappai.2026.114966_b24","unstructured":"Li, Kunchang, et al., 2022. Uniformer: Unified transformer for efficient spatio-temporal representation learning. In: Proceedings of the International Conference on Learning Representations. ICLR."},{"key":"10.1016\/j.engappai.2026.114966_b25","doi-asserted-by":"crossref","first-page":"2493","DOI":"10.1109\/TIP.2023.3269228","article-title":"Self-supervised video-based action recognition with disturbances","volume":"32","author":"Lin","year":"2023","journal-title":"IEEE Trans. Image Process."},{"issue":"2","key":"10.1016\/j.engappai.2026.114966_b26","doi-asserted-by":"crossref","first-page":"318","DOI":"10.1109\/TPAMI.2018.2858826","article-title":"Focal loss for dense object detection","volume":"42","author":"Lin","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.engappai.2026.114966_b27","doi-asserted-by":"crossref","unstructured":"Lin, Tsung-Yi, Piotr Doll\u00e1r, Ross Girshick, He, Kaiming, Hariharan, Bharath, Belongie, Serge, 2017. Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. CVPR, pp. 936\u2013944.","DOI":"10.1109\/CVPR.2017.106"},{"key":"10.1016\/j.engappai.2026.114966_b28","doi-asserted-by":"crossref","unstructured":"Lin, Cheng, et al., 2021. Learning salient boundary feature for anchor-free temporal action localization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. CVPR, pp. 3319\u20133328.","DOI":"10.1109\/CVPR46437.2021.00333"},{"key":"10.1016\/j.engappai.2026.114966_b29","doi-asserted-by":"crossref","unstructured":"Liu, Wen, Luo, Weixin, Lian, Dongze, Gao, Shenghua, 2018. Future frame prediction for anomaly detection \u2013 A new baseline. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. CVPR, pp. 6536\u20136545.","DOI":"10.1109\/CVPR.2018.00684"},{"key":"10.1016\/j.engappai.2026.114966_b30","doi-asserted-by":"crossref","DOI":"10.1016\/j.ress.2023.109679","article-title":"A probabilistic framework for post-disaster recovery modeling of buildings and electric power networks in developing countries","volume":"242","author":"Opabola","year":"2024","journal-title":"Reliab. Eng. Syst. Saf."},{"key":"10.1016\/j.engappai.2026.114966_b31","unstructured":"Oquab, Maxime, Darcet, Timoth\u00e9e, Moutakanni, Th\u00e9o, Vo, Huy, Szafraniec, Marc, Khalidov, Vasil, Fernandez, Pierre, Haziza, Daniel, Massa, Francisco, El-Nouby, Alaaeldin, et al., Dinov2: Learning robust visual features without supervision. Trans. Mach. Learn. Res. 2023."},{"key":"10.1016\/j.engappai.2026.114966_b32","doi-asserted-by":"crossref","unstructured":"Pan, Jia, Chen, Shoufa, Shou, Min Zhan, Liu, Yunchao, Shao, Jing, Li, Hongsheng, 2021. Actor-context-actor relation network for spatio-temporal action localization.. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. CVPR, pp. 464\u2013474.","DOI":"10.1109\/CVPR46437.2021.00053"},{"key":"10.1016\/j.engappai.2026.114966_b33","first-page":"12493","article-title":"Keeping your eye on the ball: Trajectory attention in video transformers","volume":"34","author":"Patrick","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"issue":"4","key":"10.1016\/j.engappai.2026.114966_b34","doi-asserted-by":"crossref","first-page":"5840","DOI":"10.1109\/TIA.2024.3397778","article-title":"Safety for the non-electrical worker: Special-purpose GFCIs are a step closer in prevention through design","volume":"60","author":"Piemonte","year":"2024","journal-title":"IEEE Trans. Ind. Appl."},{"key":"10.1016\/j.engappai.2026.114966_b35","doi-asserted-by":"crossref","unstructured":"Ranasinghe, Kanchana, Naseer, Muzammal, Khan, Salman, Khan, Fahad Shahbaz, Ryoo, Michael S., 2022. Self-supervised video transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. CVPR, pp. 2864\u20132874.","DOI":"10.1109\/CVPR52688.2022.00289"},{"issue":"11","key":"10.1016\/j.engappai.2026.114966_b36","doi-asserted-by":"crossref","first-page":"16574","DOI":"10.1109\/TITS.2024.3432654","article-title":"Improving network performance and coverage using contract-based incentivized V2V communications","volume":"25","author":"Saraydar","year":"2024","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.engappai.2026.114966_b37","doi-asserted-by":"crossref","first-page":"8395","DOI":"10.1109\/TMM.2024.3361157","article-title":"Commonsense knowledge prompting for few-shot action recognition in videos","volume":"26","author":"Shi","year":"2024","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.engappai.2026.114966_b38","doi-asserted-by":"crossref","unstructured":"Shi, Dong, Zhong, Yuxin, Cao, Qian, Ma, Lei, Li, Jian, Tao, Dacheng, 2023. TriDet: Temporal action detection with relative boundary modeling.. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. CVPR, pp. 18857\u201318866.","DOI":"10.1109\/CVPR52729.2023.01808"},{"issue":"6","key":"10.1016\/j.engappai.2026.114966_b39","doi-asserted-by":"crossref","first-page":"1461","DOI":"10.1109\/TAI.2022.3221912","article-title":"Action recognition in dark videos using spatio-temporal features and bidirectional encoder representations from transformers","volume":"4","author":"Singh","year":"2023","journal-title":"IEEE Trans. Artif. Intell."},{"issue":"11","key":"10.1016\/j.engappai.2026.114966_b40","first-page":"1","article-title":"A dataset of 101 human action classes from videos in the wild","volume":"2","author":"Soomro","year":"2012","journal-title":"Cent. Res. Comput. Vis."},{"issue":"1","key":"10.1016\/j.engappai.2026.114966_b41","doi-asserted-by":"crossref","first-page":"260","DOI":"10.1109\/TCSVT.2023.3284977","article-title":"Transductive learning with prior knowledge for generalized zero-shot action recognition","volume":"34","author":"Su","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.engappai.2026.114966_b42","doi-asserted-by":"crossref","unstructured":"Sultani, Waqas, Chen, Chen, Shah, Mubarak, 2018. Real-world anomaly detection in surveillance videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. CVPR, pp. 6479\u20136488.","DOI":"10.1109\/CVPR.2018.00678"},{"key":"10.1016\/j.engappai.2026.114966_b43","doi-asserted-by":"crossref","unstructured":"Thatipelli, Anuradha, Narayan, Salman, Khan, Salman, Anwer, Rao Muhammad, Khan, Fahad Shahbaz, Ghanem, Bernard, 2022. Spatio-temporal relation modeling for few-shot action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. CVPR, pp. 19926\u201319935.","DOI":"10.1109\/CVPR52688.2022.01933"},{"key":"10.1016\/j.engappai.2026.114966_b44","doi-asserted-by":"crossref","unstructured":"Tong, Zhan, Song, Yibing, Wang, Jue, Wang, Limin, 2022. VideoMAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training. In. In: Proceedings of the 36th International Conference on Neural Information Processing Systems (NeurIPS). pp. 10078\u201310093.","DOI":"10.52202\/068431-0732"},{"key":"10.1016\/j.engappai.2026.114966_b45","doi-asserted-by":"crossref","unstructured":"Truong, Trung-Duc, et al., 2022. DirecFormer: A directed attention in transformer approach to robust action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. CVPR, pp. 19998\u201320008.","DOI":"10.1109\/CVPR52688.2022.01940"},{"issue":"5","key":"10.1016\/j.engappai.2026.114966_b46","doi-asserted-by":"crossref","first-page":"6412","DOI":"10.1109\/TPWRS.2024.3362056","article-title":"Probabilistic frequency stability analysis considering dynamics of wind power generation with different control strategies","volume":"39","author":"Wang","year":"2024","journal-title":"IEEE Trans. Power Syst."},{"issue":"8","key":"10.1016\/j.engappai.2026.114966_b47","doi-asserted-by":"crossref","first-page":"1220","DOI":"10.3390\/sym17081220","article-title":"Model-agnostic meta-learning in predicting tunneling-induced surface ground deformation","volume":"17","author":"Wang","year":"2025","journal-title":"Symmetry"},{"key":"10.1016\/j.engappai.2026.114966_b48","doi-asserted-by":"crossref","first-page":"1175","DOI":"10.1109\/TMM.2021.3139768","article-title":"Dear-net: Learning diversities for skeleton-based early action recognition","volume":"25","author":"Wang","year":"2023","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.engappai.2026.114966_b49","doi-asserted-by":"crossref","unstructured":"Wang, Zhaofan, She, Qiang, Smolic, Aljosa, 2021. ACTION-Net: Multipath excitation for action recognition.. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. CVPR, pp. 13209\u201313218.","DOI":"10.1109\/CVPR46437.2021.01301"},{"key":"10.1016\/j.engappai.2026.114966_b50","doi-asserted-by":"crossref","unstructured":"Wang, Limin, Tong, Zhaofan, Ji, Bin, Wu, Gangshan, 2021. TDN: Temporal difference networks for efficient action recognition.. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. CVPR, pp. 1895\u20131904.","DOI":"10.1109\/CVPR46437.2021.00193"},{"issue":"4","key":"10.1016\/j.engappai.2026.114966_b51","doi-asserted-by":"crossref","first-page":"4406","DOI":"10.1109\/TITS.2025.3546232","article-title":"Study on unsafe behavior detection of tower crane drivers in prefabricated building construction","volume":"26","author":"Wang","year":"2025","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.engappai.2026.114966_b52","doi-asserted-by":"crossref","unstructured":"Wang, Qian, Zhang, Yong, Zheng, Yadong, Pan, Peng, 2022. RCL: Recurrent continuous localization for temporal action detection.. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. CVPR, pp. 13556\u201313565.","DOI":"10.1109\/CVPR52688.2022.01320"},{"issue":"10","key":"10.1016\/j.engappai.2026.114966_b53","doi-asserted-by":"crossref","first-page":"6842","DOI":"10.1109\/TPAMI.2024.3387127","article-title":"STMixer: A one-stage sparse action detector","volume":"46","author":"Wu","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.engappai.2026.114966_b54","doi-asserted-by":"crossref","unstructured":"Yan, Shiwei, et al., 2022. Multiview transformers for video recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. CVPR, pp. 3323\u20133333.","DOI":"10.1109\/CVPR52688.2022.00333"},{"key":"10.1016\/j.engappai.2026.114966_b55","doi-asserted-by":"crossref","unstructured":"Yang, Jian, Dong, Xin, Liu, Lin, Zhang, Chen, Shen, Jian, Yu, Dong, 2022. Recurring the transformer for video action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. CVPR, pp. 14043\u201314053.","DOI":"10.1109\/CVPR52688.2022.01367"},{"key":"10.1016\/j.engappai.2026.114966_b56","first-page":"11384","article-title":"Shifted chunk transformer for spatio-temporal representational learning","volume":"34","author":"Zha","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"10.1016\/j.engappai.2026.114966_b57","doi-asserted-by":"crossref","unstructured":"Zhang, Fengda, Campbell, Dylan, Gould, Stephen, 2022. Efficient two-stage detection of human-object interactions with a novel unary-pairwise transformer.. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. CVPR, pp. 20072\u201320080.","DOI":"10.1109\/CVPR52688.2022.01947"},{"key":"10.1016\/j.engappai.2026.114966_b58","doi-asserted-by":"crossref","unstructured":"Zhang, Bing, Song, Jie, Liu, Qiang, Yan, Yu, 2024. Wear-YOLO: Research on detection methods of safety equipment for power personnel in substations.. In: Proceedings of the 2024 5th International Conference on Clean Energy and Electric Power Engineering. ICCEPE, pp. 274\u2013278.","DOI":"10.1109\/ICCEPE62686.2024.10931509"},{"issue":"16","key":"10.1016\/j.engappai.2026.114966_b59","doi-asserted-by":"crossref","first-page":"3405","DOI":"10.1177\/13694332221127340","article-title":"Typical advances of artificial intelligence in civil engineering","volume":"25","author":"Zhang","year":"2022","journal-title":"Adv. Struct. Eng."}],"container-title":["Engineering Applications of Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626012480?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626012480?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T05:22:39Z","timestamp":1784179359000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0952197626012480"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":59,"alternative-id":["S0952197626012480"],"URL":"https:\/\/doi.org\/10.1016\/j.engappai.2026.114966","relation":{},"ISSN":["0952-1976"],"issn-type":[{"value":"0952-1976","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Multi-scale spatio-temporal hierarchical collaborative network and powergrid construction video action dataset for action recognition in power construction scenarios","name":"articletitle","label":"Article Title"},{"value":"Engineering Applications of Artificial Intelligence","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.engappai.2026.114966","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":"114966"}}