{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T01:47:10Z","timestamp":1785894430922,"version":"3.56.0"},"reference-count":77,"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\/501100009103","name":"Education Department of Shaanxi Province","doi-asserted-by":"publisher","award":["21JK0468"],"award-info":[{"award-number":["21JK0468"]}],"id":[{"id":"10.13039\/501100009103","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61673318"],"award-info":[{"award-number":["61673318"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.knosys.2026.116412","type":"journal-article","created":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T06:43:42Z","timestamp":1781333022000},"page":"116412","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["SHMG: Semantic-guided Human Motion Generation for action recognition"],"prefix":"10.1016","volume":"348","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-9018-5128","authenticated-orcid":false,"given":"Kai","family":"Lu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5053-9201","authenticated-orcid":false,"given":"Long","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0645-4188","authenticated-orcid":false,"given":"Xin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinzhe","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"8","key":"10.1016\/j.knosys.2026.116412_b1","doi-asserted-by":"crossref","first-page":"1128","DOI":"10.1109\/TCSVT.2008.927111","article-title":"Activity recognition using a combination of category components and local models for video surveillance","volume":"18","author":"Lin","year":"2008","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"13s","key":"10.1016\/j.knosys.2026.116412_b2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3587931","article-title":"Continuous human action recognition for human-machine interaction: a review","volume":"55","author":"Gammulle","year":"2023","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.knosys.2026.116412_b3","doi-asserted-by":"crossref","first-page":"612","DOI":"10.1016\/j.patcog.2017.12.007","article-title":"Motion analysis: Action detection, recognition and evaluation based on motion capture data","volume":"76","author":"Patrona","year":"2018","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.knosys.2026.116412_b4","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112480","article-title":"Contextual visual and motion salient fusion framework for action recognition in dark environments","volume":"304","author":"Munsif","year":"2024","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116412_b5","article-title":"GSLTA-CDFSAR: Global sequences and local tuples alignment for cross-domain few-shot action recognition","author":"Guo","year":"2025","journal-title":"Knowl.-Based Syst."},{"issue":"1","key":"10.1016\/j.knosys.2026.116412_b6","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","article-title":"3D convolutional neural networks for human action recognition","volume":"35","author":"Ji","year":"2012","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.knosys.2026.116412_b7","doi-asserted-by":"crossref","unstructured":"Christoph Feichtenhofer, Axel Pinz, Andrew Zisserman, Convolutional two-stream network fusion for video action recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 1933\u20131941.","DOI":"10.1109\/CVPR.2016.213"},{"key":"10.1016\/j.knosys.2026.116412_b8","doi-asserted-by":"crossref","unstructured":"Christoph Feichtenhofer, Haoqi Fan, Jitendra Malik, Kaiming He, Slowfast networks for video recognition, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 6202\u20136211.","DOI":"10.1109\/ICCV.2019.00630"},{"key":"10.1016\/j.knosys.2026.116412_b9","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112868","article-title":"Skeleton-based action recognition through attention guided heterogeneous graph neural network","volume":"309","author":"Li","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116412_b10","article-title":"Active generation network of human skeleton for action recognition","author":"Wang","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.knosys.2026.116412_b11","series-title":"Graph contrastive learning for skeleton-based action recognition","author":"Huang","year":"2023"},{"key":"10.1016\/j.knosys.2026.116412_b12","doi-asserted-by":"crossref","unstructured":"Haoxuan Qu, Yujun Cai, Jun Liu, Llms are good action recognizers, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 18395\u201318406.","DOI":"10.1109\/CVPR52733.2024.01741"},{"key":"10.1016\/j.knosys.2026.116412_b13","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113045","article-title":"AGMS-GCN: Attention-guided multi-scale graph convolutional networks for skeleton-based action recognition","author":"Kilic","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116412_b14","article-title":"Spatial temporal graph convolutional networks for skeleton-based action recognition","volume":"vol. 32","author":"Yan","year":"2018"},{"key":"10.1016\/j.knosys.2026.116412_b15","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1016\/j.neucom.2022.07.080","article-title":"Skeleton-based similar action recognition through integrating the salient image feature into a center-connected graph convolutional network","volume":"507","author":"Bai","year":"2022","journal-title":"Neurocomputing"},{"key":"10.1016\/j.knosys.2026.116412_b16","unstructured":"Jinmiao Cai, Nianjuan Jiang, Xiaoguang Han, Kui Jia, Jiangbo Lu, JOLO-GCN: mining joint-centered light-weight information for skeleton-based action recognition, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2021, pp. 2735\u20132744."},{"issue":"2","key":"10.1016\/j.knosys.2026.116412_b17","doi-asserted-by":"crossref","first-page":"1474","DOI":"10.1109\/TPAMI.2022.3157033","article-title":"Constructing stronger and faster baselines for skeleton-based action recognition","volume":"45","author":"Song","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.knosys.2026.116412_b18","doi-asserted-by":"crossref","unstructured":"Yuxuan Zhou, Xudong Yan, Zhi-Qi Cheng, Yan Yan, Qi Dai, Xian-Sheng Hua, Blockgcn: Redefine topology awareness for skeleton-based action recognition, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 2049\u20132058.","DOI":"10.1109\/CVPR52733.2024.00200"},{"key":"10.1016\/j.knosys.2026.116412_b19","doi-asserted-by":"crossref","unstructured":"Aniruddha Mahapatra, Kuldeep Kulkarni, Controllable animation of fluid elements in still images, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 3667\u20133676.","DOI":"10.1109\/CVPR52688.2022.00365"},{"key":"10.1016\/j.knosys.2026.116412_b20","doi-asserted-by":"crossref","unstructured":"Haomiao Ni, Yihao Liu, Sharon X. Huang, Yuan Xue, Cross-identity video motion retargeting with joint transformation and synthesis, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2023, pp. 412\u2013422.","DOI":"10.1109\/WACV56688.2023.00049"},{"key":"10.1016\/j.knosys.2026.116412_b21","doi-asserted-by":"crossref","unstructured":"Liang Xu, Ziyang Song, Dongliang Wang, Jing Su, Zhicheng Fang, Chenjing Ding, Weihao Gan, Yichao Yan, Xin Jin, Xiaokang Yang, et al., Actformer: A gan-based transformer towards general action-conditioned 3d human motion generation, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 2228\u20132238.","DOI":"10.1109\/ICCV51070.2023.00212"},{"key":"10.1016\/j.knosys.2026.116412_b22","doi-asserted-by":"crossref","unstructured":"Wenfeng Song, Xingliang Jin, Shuai Li, Chenglizhao Chen, Aimin Hao, Xia Hou, Ning Li, Hong Qin, Arbitrary Motion Style Transfer with Multi-condition Motion Latent Diffusion Model, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 821\u2013830.","DOI":"10.1109\/CVPR52733.2024.00084"},{"issue":"4","key":"10.1016\/j.knosys.2026.116412_b23","first-page":"1","article-title":"Ganimator: Neural motion synthesis from a single sequence","volume":"41","author":"Li","year":"2022","journal-title":"ACM Trans. Graph."},{"issue":"4","key":"10.1016\/j.knosys.2026.116412_b24","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3386569.3392469","article-title":"Unpaired motion style transfer from video to animation","volume":"39","author":"Aberman","year":"2020","journal-title":"ACM Trans. Graph."},{"key":"10.1016\/j.knosys.2026.116412_b25","unstructured":"Xiaolei Wu, Zhihao Hu, Lu Sheng, Dong Xu, Styleformer: Real-time arbitrary style transfer via parametric style composition, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 14618\u201314627."},{"issue":"4","key":"10.1016\/j.knosys.2026.116412_b26","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3386569.3392422","article-title":"Character controllers using motion vaes","volume":"39","author":"Ling","year":"2020","journal-title":"ACM Trans. Graph."},{"key":"10.1016\/j.knosys.2026.116412_b27","doi-asserted-by":"crossref","unstructured":"Mathis Petrovich, Michael J. Black, G\u00fcl Varol, Action-conditioned 3d human motion synthesis with transformer vae, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 10985\u201310995.","DOI":"10.1109\/ICCV48922.2021.01080"},{"issue":"3","key":"10.1016\/j.knosys.2026.116412_b28","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3516429","article-title":"Motion puzzle: Arbitrary motion style transfer by body part","volume":"41","author":"Jang","year":"2022","journal-title":"ACM Trans. Graph."},{"issue":"4","key":"10.1016\/j.knosys.2026.116412_b29","first-page":"1","article-title":"Diverse motion stylization for multiple style domains via spatial-temporal graph-based generative model","volume":"3","author":"Soomin","year":"2021","journal-title":"Proc. ACM Comput. Graph. Interact. Tech."},{"key":"10.1016\/j.knosys.2026.116412_b30","doi-asserted-by":"crossref","unstructured":"Chuan Guo, Yuxuan Mu, Muhammad Gohar Javed, Sen Wang, Li Cheng, Momask: Generative masked modeling of 3d human motions, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 1900\u20131910.","DOI":"10.1109\/CVPR52733.2024.00186"},{"key":"10.1016\/j.knosys.2026.116412_b31","doi-asserted-by":"crossref","unstructured":"Rishabh Dabral, Muhammad Hamza Mughal, Vladislav Golyanik, Christian Theobalt, Mofusion: A framework for denoising-diffusion-based motion synthesis, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 9760\u20139770.","DOI":"10.1109\/CVPR52729.2023.00941"},{"key":"10.1016\/j.knosys.2026.116412_b32","series-title":"On-the-fly learning to transfer motion style with diffusion models: A semantic guidance approach","author":"Hu","year":"2024"},{"issue":"4","key":"10.1016\/j.knosys.2026.116412_b33","doi-asserted-by":"crossref","first-page":"2430","DOI":"10.1109\/TPAMI.2023.3330935","article-title":"Human motion generation: A survey","volume":"46","author":"Zhu","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.knosys.2026.116412_b34","doi-asserted-by":"crossref","unstructured":"Boeun Kim, Jungho Kim, Hyung Jin Chang, Jin Young Choi, MoST: Motion Style Transformer between Diverse Action Contents, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 1705\u20131714.","DOI":"10.1109\/CVPR52733.2024.00168"},{"key":"10.1016\/j.knosys.2026.116412_b35","doi-asserted-by":"crossref","unstructured":"Xun Huang, Serge Belongie, Arbitrary style transfer in real-time with adaptive instance normalization, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 1501\u20131510.","DOI":"10.1109\/ICCV.2017.167"},{"issue":"4","key":"10.1016\/j.knosys.2026.116412_b36","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2897824.2925975","article-title":"A deep learning framework for character motion synthesis and editing","volume":"35","author":"Holden","year":"2016","journal-title":"ACM Trans. Graph. (ToG)"},{"issue":"11","key":"10.1016\/j.knosys.2026.116412_b37","doi-asserted-by":"crossref","first-page":"4361","DOI":"10.1109\/TVCG.2023.3320216","article-title":"Finestyle: Semantic-aware fine-grained motion style transfer with dual interactive-flow fusion","volume":"29","author":"Song","year":"2023","journal-title":"IEEE Trans. Vis. Comput. Graphics"},{"key":"10.1016\/j.knosys.2026.116412_b38","series-title":"European Conference on Computer Vision","first-page":"405","article-title":"Smoodi: Stylized motion diffusion model","author":"Zhong","year":"2024"},{"key":"10.1016\/j.knosys.2026.116412_b39","series-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"10.1016\/j.knosys.2026.116412_b40","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.knosys.2026.116412_b41","doi-asserted-by":"crossref","unstructured":"Raviteja Vemulapalli, Felipe Arrate, Rama Chellappa, Human action recognition by representing 3d skeletons as points in a lie group, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014, pp. 588\u2013595.","DOI":"10.1109\/CVPR.2014.82"},{"key":"10.1016\/j.knosys.2026.116412_b42","doi-asserted-by":"crossref","unstructured":"Raviteja Vemulapalli, Rama Chellapa, Rolling rotations for recognizing human actions from 3d skeletal data, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 4471\u20134479.","DOI":"10.1109\/CVPR.2016.484"},{"key":"10.1016\/j.knosys.2026.116412_b43","doi-asserted-by":"crossref","unstructured":"Colin Lea, Michael D Flynn, Rene Vidal, Austin Reiter, Gregory D Hager, Temporal convolutional networks for action segmentation and detection, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 156\u2013165.","DOI":"10.1109\/CVPR.2017.113"},{"key":"10.1016\/j.knosys.2026.116412_b44","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2020.107293","article-title":"Learning shape and motion representations for view invariant skeleton-based action recognition","volume":"103","author":"Li","year":"2020","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.knosys.2026.116412_b45","doi-asserted-by":"crossref","unstructured":"Yong Du, Wei Wang, Liang Wang, Hierarchical recurrent neural network for skeleton based action recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 1110\u20131118.","DOI":"10.1109\/CVPR.2015.7298714"},{"key":"10.1016\/j.knosys.2026.116412_b46","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2020.107511","article-title":"Skeleton-based action recognition with hierarchical spatial reasoning and temporal stack learning network","volume":"107","author":"Si","year":"2020","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.knosys.2026.116412_b47","unstructured":"Maosen Li, Siheng Chen, Xu Chen, Ya Zhang, Yanfeng Wang, Qi Tian, Actional-structural graph convolutional networks for skeleton-based action recognition, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 3595\u20133603."},{"key":"10.1016\/j.knosys.2026.116412_b48","doi-asserted-by":"crossref","unstructured":"Lei Shi, Yifan Zhang, Jian Cheng, Hanqing Lu, Two-stream adaptive graph convolutional networks for skeleton-based action recognition, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 12026\u201312035.","DOI":"10.1109\/CVPR.2019.01230"},{"key":"10.1016\/j.knosys.2026.116412_b49","doi-asserted-by":"crossref","unstructured":"Yuxin Chen, Ziqi Zhang, Chunfeng Yuan, Bing Li, Ying Deng, Weiming Hu, Channel-wise topology refinement graph convolution for skeleton-based action recognition, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 13359\u201313368.","DOI":"10.1109\/ICCV48922.2021.01311"},{"key":"10.1016\/j.knosys.2026.116412_b50","series-title":"Step catformer: Spatial-temporal effective body-part cross attention transformer for skeleton-based action recognition","author":"Long","year":"2023"},{"key":"10.1016\/j.knosys.2026.116412_b51","unstructured":"Zhimin Gao, Peitao Wang, Pei Lv, Xiaoheng Jiang, Qidong Liu, Pichao Wang, Mingliang Xu, Wanqing Li, Focal and global spatial-temporal transformer for skeleton-based action recognition, in: Proceedings of the Asian Conference on Computer Vision, 2022, pp. 382\u2013398."},{"key":"10.1016\/j.knosys.2026.116412_b52","doi-asserted-by":"crossref","DOI":"10.1016\/j.iot.2024.101134","article-title":"MTAN: Multi-degree tail-aware attention network for human motion prediction","volume":"25","author":"Tang","year":"2024","journal-title":"Internet Things"},{"key":"10.1016\/j.knosys.2026.116412_b53","article-title":"Unbiased spatial-temporal atomic fusion-based zero-shot action recognition","author":"Xing","year":"2025","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.knosys.2026.116412_b54","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110898","article-title":"Semantic-driven dual consistency learning for weakly supervised video anomaly detection","volume":"157","author":"Su","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.knosys.2026.116412_b55","doi-asserted-by":"crossref","unstructured":"Leon A. Gatys, Alexander S. Ecker, Matthias Bethge, Image style transfer using convolutional neural networks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 2414\u20132423.","DOI":"10.1109\/CVPR.2016.265"},{"key":"10.1016\/j.knosys.2026.116412_b56","series-title":"Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, the Netherlands, October 11-14, 2016, Proceedings, Part II 14","first-page":"694","article-title":"Perceptual losses for real-time style transfer and super-resolution","author":"Johnson","year":"2016"},{"issue":"4","key":"10.1016\/j.knosys.2026.116412_b57","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2897824.2925975","article-title":"A deep learning framework for character motion synthesis and editing","volume":"35","author":"Holden","year":"2016","journal-title":"ACM Trans. Graph. (ToG)"},{"issue":"1","key":"10.1016\/j.knosys.2026.116412_b58","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1007\/s11633-022-1369-5","article-title":"Vlp: A survey on vision-language pre-training","volume":"20","author":"Chen","year":"2023","journal-title":"Mach. Intell. Res."},{"key":"10.1016\/j.knosys.2026.116412_b59","series-title":"European Conference on Computer Vision","first-page":"358","article-title":"Motionclip: Exposing human motion generation to clip space","author":"Tevet","year":"2022"},{"key":"10.1016\/j.knosys.2026.116412_b60","series-title":"On-the-fly learning to transfer motion style with diffusion models: A semantic guidance approach","first-page":"arXiv","author":"Hu","year":"2024"},{"key":"10.1016\/j.knosys.2026.116412_b61","series-title":"International Conference on Machine Learning","first-page":"1050","article-title":"Dropout as a bayesian approximation: Representing model uncertainty in deep learning","author":"Gal","year":"2016"},{"key":"10.1016\/j.knosys.2026.116412_b62","series-title":"Uncertainty-guided continual learning with bayesian neural networks","author":"Ebrahimi","year":"2019"},{"key":"10.1016\/j.knosys.2026.116412_b63","series-title":"International Conference on Machine Learning","first-page":"1183","article-title":"Deep bayesian active learning with image data","author":"Gal","year":"2017"},{"key":"10.1016\/j.knosys.2026.116412_b64","series-title":"Generative adversarial active learning","author":"Zhu","year":"2017"},{"key":"10.1016\/j.knosys.2026.116412_b65","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"580","article-title":"Efficient active learning for image classification and segmentation using a sample selection and conditional generative adversarial network","author":"Mahapatra","year":"2018"},{"key":"10.1016\/j.knosys.2026.116412_b66","doi-asserted-by":"crossref","unstructured":"Christoph Mayer, Radu Timofte, Adversarial sampling for active learning, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2020, pp. 3071\u20133079.","DOI":"10.1109\/WACV45572.2020.9093556"},{"key":"10.1016\/j.knosys.2026.116412_b67","doi-asserted-by":"crossref","unstructured":"Amir Shahroudy, Jun Liu, Tian-Tsong Ng, Gang Wang, Ntu rgb+ d: A large scale dataset for 3d human activity analysis, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 1010\u20131019.","DOI":"10.1109\/CVPR.2016.115"},{"issue":"10","key":"10.1016\/j.knosys.2026.116412_b68","doi-asserted-by":"crossref","first-page":"2684","DOI":"10.1109\/TPAMI.2019.2916873","article-title":"Ntu rgb+ d 120: A large-scale benchmark for 3d human activity understanding","volume":"42","author":"Liu","year":"2019","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.knosys.2026.116412_b69","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116412_b70","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1016\/j.ins.2021.04.023","article-title":"Augmented skeleton based contrastive action learning with momentum lstm for unsupervised action recognition","volume":"569","author":"Rao","year":"2021","journal-title":"Inform. Sci."},{"key":"10.1016\/j.knosys.2026.116412_b71","doi-asserted-by":"crossref","unstructured":"Inwoong Lee, Doyoung Kim, Seoungyoon Kang, Sanghoon Lee, Ensemble deep learning for skeleton-based action recognition using temporal sliding lstm networks, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 1012\u20131020.","DOI":"10.1109\/ICCV.2017.115"},{"issue":"23","key":"10.1016\/j.knosys.2026.116412_b72","doi-asserted-by":"crossref","first-page":"11481","DOI":"10.3390\/app112311481","article-title":"A data augmentation method for skeleton-based action recognition with relative features","volume":"11","author":"Chen","year":"2021","journal-title":"Appl. Sci."},{"issue":"5","key":"10.1016\/j.knosys.2026.116412_b73","doi-asserted-by":"crossref","first-page":"3100","DOI":"10.1109\/TII.2019.2910876","article-title":"Encoding pose features to images with data augmentation for 3-D action recognition","volume":"16","author":"Huynh-The","year":"2019","journal-title":"IEEE Trans. Ind. Inform."},{"issue":"11","key":"10.1016\/j.knosys.2026.116412_b74","doi-asserted-by":"crossref","first-page":"5281","DOI":"10.1109\/TIP.2019.2913544","article-title":"Sample fusion network: An end-to-end data augmentation network for skeleton-based human action recognition","volume":"28","author":"Meng","year":"2019","journal-title":"IEEE Trans. Image Process."},{"issue":"1","key":"10.1016\/j.knosys.2026.116412_b75","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s40537-019-0263-7","article-title":"Enlarging smaller images before inputting into convolutional neural network: zero-padding vs. interpolation","volume":"6","author":"Hashemi","year":"2019","journal-title":"J. Big Data"},{"key":"10.1016\/j.knosys.2026.116412_b76","doi-asserted-by":"crossref","first-page":"7348","DOI":"10.1109\/ACCESS.2023.3238315","article-title":"Padding module: Learning the padding in deep neural networks","volume":"11","author":"Alrasheedi","year":"2023","journal-title":"IEEE Access"},{"key":"10.1016\/j.knosys.2026.116412_b77","doi-asserted-by":"crossref","unstructured":"Yu-Qi Yang, Peng-Shuai Wang, Yang Liu, Interpolation-aware padding for 3d sparse convolutional neural networks, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 7467\u20137475.","DOI":"10.1109\/ICCV48922.2021.00737"}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S095070512601138X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S095070512601138X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T01:00:17Z","timestamp":1785891617000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S095070512601138X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":77,"alternative-id":["S095070512601138X"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116412","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"SHMG: Semantic-guided Human Motion Generation for action recognition","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116412","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"116412"}}