{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T18:20:20Z","timestamp":1783362020639,"version":"3.54.6"},"reference-count":141,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T00:00:00Z","timestamp":1782691200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computer Science Review"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.cosrev.2026.101030","type":"journal-article","created":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T12:14:36Z","timestamp":1783080876000},"page":"101030","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Beyond benchmark accuracy: A generalization-centered analysis of deep learning for skeleton-based human activity recognition"],"prefix":"10.1016","volume":"62","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3846-0948","authenticated-orcid":false,"given":"Yi","family":"Xia","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2880-6618","authenticated-orcid":false,"given":"Sira","family":"Yongchareon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3908-6466","authenticated-orcid":false,"given":"Raymond","family":"Lutui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3326-4147","authenticated-orcid":false,"given":"Quan Z.","family":"Sheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.cosrev.2026.101030_bib0005","series-title":"European Conference on Computer Vision","first-page":"367","article-title":"S-JEPA: a joint embedding predictive architecture for skeletal action recognition","author":"Abdelfattah","year":"2024"},{"key":"10.1016\/j.cosrev.2026.101030_bib0010","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"18678","article-title":"Maskclr: attention-guided contrastive learning for robust action representation learning","author":"Abdelfattah","year":"2024"},{"key":"10.1016\/j.cosrev.2026.101030_bib0015","doi-asserted-by":"crossref","first-page":"907","DOI":"10.3390\/s25030907","article-title":"Federated learning for IOMT-enhanced human activity recognition with hybrid LSTM-GRU networks","volume":"25","author":"Albogamy","year":"2025","journal-title":"Sensors"},{"key":"10.1016\/j.cosrev.2026.101030_bib0020","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3517224","article-title":"Dexar: deep explainable sensor-based activity recognition in smart-home environments","volume":"6","author":"Arrotta","year":"2022","journal-title":"Proc. ACM Interact. Mob. Wearable Ubiquitous Technol."},{"key":"10.1016\/j.cosrev.2026.101030_bib0025","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops","article-title":"DHP19: dynamic vision sensor 3D human pose dataset","author":"Calabrese","year":"2019"},{"key":"10.1016\/j.cosrev.2026.101030_bib0030","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2024.111963","article-title":"Human movement science-informed multi-task spatio temporal graph convolutional networks for fitness action recognition and evaluation","volume":"164","author":"Chang","year":"2024","journal-title":"Appl. Soft Comput."},{"key":"10.1016\/j.cosrev.2026.101030_bib0035","series-title":"2015 IEEE International Conference on Image Processing (ICIP)","first-page":"168","article-title":"UTD-MHAD: a multimodal dataset for human action recognition utilizing a depth camera and a wearable inertial sensor","author":"Chen","year":"2015"},{"key":"10.1016\/j.cosrev.2026.101030_bib0040","doi-asserted-by":"crossref","first-page":"4982","DOI":"10.1038\/s41598-025-87752-8","article-title":"Two-stream spatio-temporal GCN-transformer networks for skeleton-based action recognition","volume":"15","author":"Chen","year":"2025","journal-title":"Sci. Rep."},{"key":"10.1016\/j.cosrev.2026.101030_bib0045","first-page":"1","article-title":"Deep learning for sensor-based human activity recognition: overview, challenges, and opportunities","volume":"54","author":"Chen","year":"2021","journal-title":"ACM Computing Surveys (CSUR)"},{"key":"10.1016\/j.cosrev.2026.101030_bib0050","series-title":"Proceedings of the 32nd ACM International Conference on Multimedia","first-page":"778","article-title":"Fine-grained side information guided dual-prompts for zero-shot skeleton action recognition","author":"Chen","year":"2024"},{"key":"10.1016\/j.cosrev.2026.101030_bib0055","doi-asserted-by":"crossref","first-page":"2293","DOI":"10.1109\/TMM.2024.3521718","article-title":"Vision-language meets the skeleton: progressively distillation with cross-modal knowledge for 3D action representation learning","volume":"27","author":"Chen","year":"2024","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.cosrev.2026.101030_bib0060","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","article-title":"Skeleton-based action recognition with non-linear dependency modeling and Hilbert-schmidt independence criterion","author":"Chen","year":"2025"},{"key":"10.1016\/j.cosrev.2026.101030_bib0065","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"13359","article-title":"Channel-wise topology refinement graph convolution for skeleton-based action recognition","author":"Chen","year":"2021"},{"key":"10.1016\/j.cosrev.2026.101030_bib0070","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"183","article-title":"Skeleton-based action recognition with shift graph convolutional network","author":"Cheng","year":"2020"},{"key":"10.1016\/j.cosrev.2026.101030_bib0075","doi-asserted-by":"crossref","first-page":"1303","DOI":"10.1007\/s10044-023-01156-w","article-title":"Multi-scale spatial\u2013temporal convolutional neural network for skeleton-based action recognition","volume":"26","author":"Cheng","year":"2023","journal-title":"Pattern Analysis and Applications"},{"key":"10.1016\/j.cosrev.2026.101030_bib0080","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"20186","article-title":"Infogcn: representation learning for human skeleton-based action recognition","author":"Chi","year":"2022"},{"key":"10.1016\/j.cosrev.2026.101030_bib0085","series-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"290","article-title":"Enhancing skeleton-based action recognition in real-world scenarios through realistic data augmentation","author":"Cormier","year":"2024"},{"key":"10.1016\/j.cosrev.2026.101030_bib0090","doi-asserted-by":"crossref","first-page":"8230","DOI":"10.1109\/ACCESS.2024.3353138","article-title":"Audio-and video-based human activity recognition systems in healthcare","volume":"12","author":"Cristina","year":"2024","journal-title":"IEEE Access"},{"key":"10.1016\/j.cosrev.2026.101030_bib0095","doi-asserted-by":"crossref","first-page":"2533","DOI":"10.1109\/TPAMI.2022.3169976","article-title":"Toyota smarthome untrimmed: real-world untrimmed videos for activity detection","volume":"45","author":"Dai","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.cosrev.2026.101030_bib0100","doi-asserted-by":"crossref","DOI":"10.1016\/j.cosrev.2025.100879","article-title":"A systematic review of deep learning-based models for elderly and human activity recognition","author":"Dalal","year":"2026","journal-title":"Comput. Sci. Rev."},{"key":"10.1016\/j.cosrev.2026.101030_bib0105","series-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"1150","article-title":"Generative adversarial graph convolutional networks for human action synthesis","author":"Degardin","year":"2022"},{"key":"10.1016\/j.cosrev.2026.101030_bib0110","series-title":"Proceedings of the 2019 2nd International Conference on Signal Processing and Machine Learning","first-page":"79","article-title":"An attention-enhanced recurrent graph convolutional network for skeleton-based action recognition","author":"Ding","year":"2019"},{"key":"10.1016\/j.cosrev.2026.101030_bib0115","series-title":"European Conference on Computer Vision","first-page":"401","article-title":"Skateformer: skeletal-temporal transformer for human action recognition","author":"Do","year":"2024"},{"key":"10.1016\/j.cosrev.2026.101030_bib0120","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"1110","article-title":"Hierarchical recurrent neural network for skeleton based action recognition","author":"Du","year":"2015"},{"key":"10.1016\/j.cosrev.2026.101030_bib0125","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"13634","article-title":"Skeletr: towards skeleton-based action recognition in the wild","author":"Duan","year":"2023"},{"key":"10.1016\/j.cosrev.2026.101030_bib0130","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"2969","article-title":"Revisiting skeleton-based action recognition","author":"Duan","year":"2022"},{"key":"10.1016\/j.cosrev.2026.101030_bib0135","doi-asserted-by":"crossref","first-page":"420","DOI":"10.1007\/s11263-012-0550-7","article-title":"Exploring the trade-off between accuracy and observational latency in action recognition","volume":"101","author":"Ellis","year":"2013","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.cosrev.2026.101030_bib0140","series-title":"The Eleventh International Conference on Learning Representations","article-title":"Hyperbolic self-paced learning for self-supervised skeleton-based action representations","author":"Franco","year":"2023"},{"key":"10.1016\/j.cosrev.2026.101030_bib0145","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110333","article-title":"Improving self-supervised action recognition from extremely augmented skeleton sequences","volume":"150","author":"Guo","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.cosrev.2026.101030_bib0150","article-title":"MAR-GCN: meta-action refinement graph convolutional network for skeleton-based action recognition","volume":"310","author":"Guo","year":"2026","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.cosrev.2026.101030_bib0155","series-title":"Proceedings of the IEEE International Conference on Image Processing (ICIP)","first-page":"439","article-title":"Syntactically guided generative embeddings for zero-shot skeleton action recognition","author":"Gupta","year":"2021"},{"key":"10.1016\/j.cosrev.2026.101030_bib0160","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1049\/iet-cvi.2017.0062","article-title":"Skeleton-based human activity recognition for elderly monitoring systems","volume":"12","author":"Hbali","year":"2018","journal-title":"IET Comput. Vis."},{"key":"10.1016\/j.cosrev.2026.101030_bib0165","series-title":"European Conference on Computer Vision","first-page":"107","article-title":"RT-pose: a 4D radar tensor-based 3D human pose estimation and localization benchmark","author":"Ho","year":"2024"},{"key":"10.1016\/j.cosrev.2026.101030_bib0170","doi-asserted-by":"crossref","first-page":"807","DOI":"10.1109\/TCSVT.2016.2628339","article-title":"Skeleton optical spectra-based action recognition using convolutional neural networks","volume":"28","author":"Hou","year":"2018","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"11","key":"10.1016\/j.cosrev.2026.101030_bib0175","doi-asserted-by":"crossref","first-page":"10578","DOI":"10.1109\/TCSVT.2024.3410301","article-title":"Global and local contrastive learning for self-supervised skeleton-based action recognition","volume":"34","author":"Hu","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"24","key":"10.1016\/j.cosrev.2026.101030_bib0180","doi-asserted-by":"crossref","first-page":"40166","DOI":"10.1109\/JIOT.2024.3450929","article-title":"Unsupervised domain adaptation for skeleton recognition with Fourier analysis","volume":"11","author":"Hu","year":"2024","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.cosrev.2026.101030_bib0185","doi-asserted-by":"crossref","first-page":"11896","DOI":"10.1109\/TNNLS.2023.3347593","article-title":"GRA: graph representation alignment for semi-supervised action recognition","volume":"35","author":"Huang","year":"2024","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.cosrev.2026.101030_bib0190","doi-asserted-by":"crossref","first-page":"1325","DOI":"10.1109\/TPAMI.2013.248","article-title":"Human3. 6m: large scale datasets and predictive methods for 3D human sensing in natural environments","volume":"36","author":"Ionescu","year":"2013","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.cosrev.2026.101030_bib0195","series-title":"2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","first-page":"10990","article-title":"ETRI-activity3D: a large-scale RGB-D dataset for robots to recognize daily activities of the elderly","author":"Jang","year":"2020"},{"key":"10.1016\/j.cosrev.2026.101030_bib0200","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"3192","article-title":"Towards understanding action recognition","author":"Jhuang","year":"2013"},{"key":"10.1016\/j.cosrev.2026.101030_bib0205","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1016\/j.patrec.2025.02.020","article-title":"Selective directed graph convolutional network for skeleton-based action recognition","volume":"190","author":"Ke","year":"2025","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.cosrev.2026.101030_bib0210","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"3288","article-title":"A new representation of skeleton sequences for 3D action recognition","author":"Ke","year":"2017"},{"key":"10.1016\/j.cosrev.2026.101030_bib0215","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"8658","article-title":"Mmact: a large-scale dataset for cross modal human action understanding","author":"Kong","year":"2019"},{"key":"10.1016\/j.cosrev.2026.101030_bib0220","doi-asserted-by":"crossref","first-page":"1366","DOI":"10.1007\/s11263-022-01594-9","article-title":"Human action recognition and prediction: a survey","volume":"130","author":"Kong","year":"2022","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.cosrev.2026.101030_bib0225","doi-asserted-by":"crossref","first-page":"951","DOI":"10.1177\/0278364913478446","article-title":"Learning human activities and object affordances from RGB-D videos","volume":"32","author":"Koppula","year":"2013","journal-title":"Int. J. Robot. Res."},{"key":"10.1016\/j.cosrev.2026.101030_bib0230","series-title":"2017 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)","first-page":"585","article-title":"Skeleton-based action recognition using LSTM and CNN","author":"Li","year":"2017"},{"issue":"11","key":"10.1016\/j.cosrev.2026.101030_bib0235","doi-asserted-by":"crossref","first-page":"16966","DOI":"10.1109\/TNNLS.2023.3297853","article-title":"Al-sar: active learning for skeleton-based action recognition","volume":"35","author":"Li","year":"2023","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.cosrev.2026.101030_bib0240","series-title":"European Conference on Computer Vision","first-page":"447","article-title":"SA-dvae: improving zero-shot skeleton-based action recognition by disentangled variational autoencoders","author":"Li","year":"2024"},{"key":"10.1016\/j.cosrev.2026.101030_bib0245","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"16266","article-title":"UAV-human: a large benchmark for human behavior understanding with unmanned aerial vehicles","author":"Li","year":"2021"},{"key":"10.1016\/j.cosrev.2026.101030_bib0250","series-title":"2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition-Workshops","first-page":"9","article-title":"Action recognition based on a bag of 3D points","author":"Li","year":"2010"},{"key":"10.1016\/j.cosrev.2026.101030_bib0255","doi-asserted-by":"crossref","first-page":"5396","DOI":"10.1109\/TITS.2025.3528391","article-title":"Dual-STGAT: dual spatio-temporal graph attention networks with feature fusion for pedestrian crossing intention prediction","volume":"26","author":"Lian","year":"2025","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.cosrev.2026.101030_bib0260","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops","article-title":"Three-stream convolutional neural network with multi-task and ensemble learning for 3D action recognition","author":"Liang","year":"2019"},{"key":"10.1016\/j.cosrev.2026.101030_bib0265","series-title":"2022 IEEE 5th International Conference on Multimedia Information Processing and Retrieval (MIPR)","first-page":"387","article-title":"Cross-domain knowledge transfer for skeleton-based action recognition based on graph convolutional gradient reversal layer","author":"Liao","year":"2022"},{"key":"10.1016\/j.cosrev.2026.101030_bib0270","series-title":"Proceedings of the 28th ACM International Conference on Multimedia","first-page":"2490","article-title":"MS2 l: multi-task self-supervised learning for skeleton based action recognition","author":"Lin","year":"2020"},{"key":"10.1016\/j.cosrev.2026.101030_bib0275","series-title":"European Conference on Computer Vision","first-page":"75","article-title":"Idempotent unsupervised representation learning for skeleton-based action recognition","author":"Lin","year":"2024"},{"key":"10.1016\/j.cosrev.2026.101030_bib0280","series-title":"Proceedings of the Workshop on Visual Analysis in Smart and Connected Communities","first-page":"1","article-title":"PKU-MMD: a large scale benchmark for skeleton-based human action understanding","author":"Liu","year":"2017"},{"key":"10.1016\/j.cosrev.2026.101030_bib0285","doi-asserted-by":"crossref","DOI":"10.1016\/j.sigpro.2024.109486","article-title":"Enhancing action recognition from low-quality skeleton data via part-level knowledge distillation","volume":"221","author":"Liu","year":"2024","journal-title":"Signal Process."},{"key":"10.1016\/j.cosrev.2026.101030_bib0290","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1007\/s40747-024-01743-2","article-title":"Advancing skeleton-based human behavior recognition: multi-stream fusion spatiotemporal graph convolutional networks","volume":"11","author":"Liu","year":"2025","journal-title":"Complex Intell. Syst."},{"key":"10.1016\/j.cosrev.2026.101030_bib0295","author":"Liu"},{"key":"10.1016\/j.cosrev.2026.101030_bib0300","series-title":"Proceedings of the 32nd ACM International Conference on Multimedia","first-page":"4909","article-title":"Multi-modality co-learning for efficient skeleton-based action recognition","author":"Liu","year":"2024"},{"key":"10.1016\/j.cosrev.2026.101030_bib0305","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.cosrev.2026.101030_bib0310","series-title":"European Conference on Computer Vision","first-page":"816","article-title":"Spatio-temporal LSTM with trust gates for 3D human action recognition","author":"Liu","year":"2016"},{"key":"10.1016\/j.cosrev.2026.101030_bib0315","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"1647","article-title":"Global context-aware attention LSTM networks for 3D action recognition","author":"Liu","year":"2017"},{"key":"10.1016\/j.cosrev.2026.101030_bib0320","series-title":"2024 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","first-page":"1","article-title":"Hdbn: a novel hybrid dual-branch network for robust skeleton-based action recognition","author":"Liu","year":"2024"},{"key":"10.1016\/j.cosrev.2026.101030_bib0325","author":"Liu"},{"key":"10.1016\/j.cosrev.2026.101030_bib0330","article-title":"SHoTGCN: spatial high-order temporal GCN for skeleton-based action recognition","author":"Liu","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.cosrev.2026.101030_bib0335","article-title":"Local and global spatial-temporal transformer for skeleton-based action recognition","author":"Liu","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.cosrev.2026.101030_bib0340","article-title":"SG-CLR: semantic representation-guided contrastive learning for self-supervised skeleton-based action recognition","author":"Liu","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.cosrev.2026.101030_bib0345","article-title":"A systematic review of skeleton-based action recognition: methods, challenges, and future directions","author":"Liu","year":"2025","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.cosrev.2026.101030_bib0350","article-title":"Skeleton-prompt: skeleton-based action recognition with visual prompt tuning and 2D-to-3D pretraining","volume":"162","author":"Lu","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.cosrev.2026.101030_bib0355","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1109\/TIP.2024.3522818","article-title":"Momentum contrastive teacher for semi-supervised skeleton action recognition","volume":"34","author":"Lu","year":"2025","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.cosrev.2026.101030_bib0360","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"2801","article-title":"drive&act: a multi-modal dataset for fine-grained driver behavior recognition in autonomous vehicles","author":"Martin","year":"2019"},{"key":"10.1016\/j.cosrev.2026.101030_bib0365","article-title":"MoCap database hdm05","volume":"2","author":"M\u00fcller","year":"2007","journal-title":"Institut f\u00fcr Informatik II, Universit\u00e4t Bonn"},{"key":"10.1016\/j.cosrev.2026.101030_bib0370","first-page":"42","article-title":"3D flow estimation for human action recognition from colored point clouds","volume":"5","author":"Munaro","year":"2013","journal-title":"Biol. Inspir. Cogn. Archit."},{"key":"10.1016\/j.cosrev.2026.101030_bib0375","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"122","article-title":"Multi-modal domain adaptation for fine-grained action recognition","author":"Munro","year":"2020"},{"key":"10.1016\/j.cosrev.2026.101030_bib0380","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"5889","article-title":"Efficient skeleton-based action recognition for real-time embedded systems","author":"Noor","year":"2024"},{"key":"10.1016\/j.cosrev.2026.101030_bib0385","series-title":"2013 IEEE Workshop on Applications of Computer Vision (WACV)","first-page":"53","article-title":"Berkeley mhad: a comprehensive multimodal human action database","author":"Ofli","year":"2013"},{"key":"10.1016\/j.cosrev.2026.101030_bib0390","doi-asserted-by":"crossref","first-page":"7398","DOI":"10.1109\/TCSVT.2022.3219864","article-title":"View-normalized and subject-independent skeleton generation for action recognition","volume":"33","author":"Pan","year":"2022","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.cosrev.2026.101030_bib0395","doi-asserted-by":"crossref","DOI":"10.3389\/fcomp.2023.1203901","article-title":"SKELTER: unsupervised skeleton action denoising and recognition using transformers","volume":"5","author":"Paoletti","year":"2023","journal-title":"Front. Comput. Sci."},{"key":"10.1016\/j.cosrev.2026.101030_bib0400","article-title":"Skeleton-based action recognition via spatial and temporal transformer networks","volume":"208","author":"Plizzari","year":"2021","journal-title":"Comput. Vis. Image Underst."},{"key":"10.1016\/j.cosrev.2026.101030_bib0405","series-title":"International Conference on Pattern Recognition","first-page":"245","article-title":"EchoGCN: an echo graph convolutional network for skeleton-based action recognition","author":"Qian","year":"2025"},{"key":"10.1016\/j.cosrev.2026.101030_bib0410","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"18395","article-title":"LLMs are good action recognizers","author":"Qu","year":"2024"},{"key":"10.1016\/j.cosrev.2026.101030_bib0415","doi-asserted-by":"crossref","first-page":"1400","DOI":"10.3390\/s23031400","article-title":"BERT for activity recognition using sequences of skeleton features and data augmentation with GAN","volume":"23","author":"Ramirez","year":"2023","journal-title":"Sensors"},{"key":"10.1016\/j.cosrev.2026.101030_bib0420","doi-asserted-by":"crossref","DOI":"10.34133\/cbsystems.0100","article-title":"A survey on 3D skeleton-based action recognition using learning method","volume":"5","author":"Ren","year":"2024","journal-title":"Cyborg and Bionic Systems"},{"key":"10.1016\/j.cosrev.2026.101030_bib0425","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"1010","article-title":"NTU rgb+ d: a large scale dataset for 3D human activity analysis","author":"Shahroudy","year":"2016"},{"key":"10.1016\/j.cosrev.2026.101030_bib0430","series-title":"2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021)","first-page":"1","article-title":"The imaginative generative adversarial network: automatic data augmentation for dynamic skeleton-based hand gesture and human action recognition","author":"Shen","year":"2021"},{"key":"10.1016\/j.cosrev.2026.101030_bib0435","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"12026","article-title":"Two-stream adaptive graph convolutional networks for skeleton-based action recognition","author":"Shi","year":"2019"},{"key":"10.1016\/j.cosrev.2026.101030_bib0440","doi-asserted-by":"crossref","first-page":"9532","DOI":"10.1109\/TIP.2020.3028207","article-title":"Skeleton-based action recognition with multi-stream adaptive graph convolutional networks","volume":"29","author":"Shi","year":"2020","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.cosrev.2026.101030_bib0445","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"1227","article-title":"An attention enhanced graph convolutional LSTM network for skeleton-based action recognition","author":"Si","year":"2019"},{"key":"10.1016\/j.cosrev.2026.101030_bib0450","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1145\/3729215","article-title":"A survey on deep learning hardware accelerators for heterogeneous HPC platforms","volume":"57","author":"Silvano","year":"2025","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.cosrev.2026.101030_bib0455","article-title":"Two-stream convolutional networks for action recognition in videos","volume":"27","author":"Simonyan","year":"2014","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cosrev.2026.101030_bib0460","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"6931","article-title":"SKI models: skeleton induced vision-language embeddings for understanding activities of daily living","author":"Sinha","year":"2025"},{"key":"10.1016\/j.cosrev.2026.101030_bib0465","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","article-title":"An end-to-end spatio-temporal attention model for human action recognition from skeleton data","author":"Song","year":"2017"},{"key":"10.1016\/j.cosrev.2026.101030_bib0470","first-page":"3200","article-title":"Human action recognition from various data modalities: a review","volume":"45","author":"Sun","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.cosrev.2026.101030_bib0475","series-title":"2012 IEEE International Conference on Robotics and Automation","first-page":"842","article-title":"Unstructured human activity detection from RGBD images","author":"Sung","year":"2012"},{"key":"10.1016\/j.cosrev.2026.101030_bib0480","series-title":"2019 IEEE International Conference on Image Processing (ICIP)","first-page":"6","article-title":"Cross-modal knowledge distillation for action recognition","author":"Thoker","year":"2019"},{"key":"10.1016\/j.cosrev.2026.101030_bib0485","series-title":"Proceedings of the Conference on Robots and Vision","article-title":"Cross-graph domain adaptation for skeleton-based human action recognition","author":"Tian","year":"2024"},{"key":"10.1016\/j.cosrev.2026.101030_bib0490","series-title":"2012 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"5026","article-title":"MuJoCo: a physics engine for model-based control","author":"Todorov","year":"2012"},{"key":"10.1016\/j.cosrev.2026.101030_bib0495","doi-asserted-by":"crossref","first-page":"1819","DOI":"10.1109\/TMM.2022.3168137","article-title":"Joint-bone fusion graph convolutional network for semi-supervised skeleton action recognition","volume":"25","author":"Tu","year":"2022","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.cosrev.2026.101030_bib0500","doi-asserted-by":"crossref","first-page":"1567","DOI":"10.3390\/s25051567","article-title":"Skeleton reconstruction using generative adversarial networks for human activity recognition under occlusion","volume":"25","author":"Vernikos","year":"2025","journal-title":"Sensors"},{"key":"10.1016\/j.cosrev.2026.101030_bib0505","series-title":"Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part VI 14","first-page":"816","article-title":"Large-scale training of shadow detectors with noisily-annotated shadow examples","author":"Vicente","year":"2016"},{"key":"10.1016\/j.cosrev.2026.101030_bib0510","series-title":"2012 IEEE Conference on Computer Vision and Pattern Recognition","first-page":"1290","article-title":"Mining actionlet ensemble for action recognition with depth cameras","author":"Wang","year":"2012"},{"key":"10.1016\/j.cosrev.2026.101030_bib0515","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"2649","article-title":"Cross-view action modeling, learning and recognition","author":"Wang","year":"2014"},{"key":"10.1016\/j.cosrev.2026.101030_bib0520","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1109\/TIP.2019.2925285","article-title":"A comparative review of recent kinect-based action recognition algorithms","volume":"29","author":"Wang","year":"2019","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.cosrev.2026.101030_bib0525","series-title":"2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020)","first-page":"160","article-title":"EV-action: electromyography-vision multi-modal action dataset","author":"Wang","year":"2020"},{"key":"10.1016\/j.cosrev.2026.101030_bib0530","doi-asserted-by":"crossref","first-page":"968","DOI":"10.1049\/cvi2.12296","article-title":"2D human skeleton action recognition with spatial constraints","volume":"18","author":"Wang","year":"2024","journal-title":"IET Comput. Vis."},{"key":"10.1016\/j.cosrev.2026.101030_bib0535","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1016\/j.knosys.2018.05.029","article-title":"Action recognition based on joint trajectory maps with convolutional neural networks","volume":"158","author":"Wang","year":"2018","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.cosrev.2026.101030_bib0540","series-title":"Proceedings of the 30th ACM International Conference on Multimedia","first-page":"1670","article-title":"Skeleton-based action recognition via adaptive cross-form learning","author":"Wang","year":"2022"},{"key":"10.1016\/j.cosrev.2026.101030_bib0545","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.127529","article-title":"Active generation network of human skeleton for action recognition","volume":"281","author":"Wang","year":"2025","journal-title":"Expert Syst. Appl."},{"issue":"7","key":"10.1016\/j.cosrev.2026.101030_bib0550","doi-asserted-by":"crossref","first-page":"5672","DOI":"10.1109\/TPAMI.2025.3552604","article-title":"Hulk: a universal knowledge translator for human-centric tasks","volume":"47","author":"Wang","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.cosrev.2026.101030_bib0555","series-title":"European Conference on Computer Vision","first-page":"490","article-title":"Addbiomechanics dataset: capturing the physics of human motion at scale","author":"Werling","year":"2024"},{"key":"10.1016\/j.cosrev.2026.101030_bib0560","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"5949","article-title":"Scd-net: spatiotemporal clues disentanglement network for self-supervised skeleton-based action recognition","author":"Wu","year":"2024"},{"key":"10.1016\/j.cosrev.2026.101030_bib0565","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2022.109231","article-title":"SpatioTemporal focus for skeleton-based action recognition","volume":"136","author":"Wu","year":"2023","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.cosrev.2026.101030_bib0570","series-title":"Proceedings of the 32nd ACM International Conference on Multimedia","first-page":"4660","article-title":"Frequency guidance matters: skeletal action recognition by frequency-aware mixed transformer","author":"Wu","year":"2024"},{"key":"10.1016\/j.cosrev.2026.101030_bib0575","doi-asserted-by":"crossref","first-page":"4391","DOI":"10.1109\/TIP.2024.3433581","article-title":"SelfGCN: graph convolution network with self-attention for skeleton-based action recognition","volume":"33","author":"Wu","year":"2024","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.cosrev.2026.101030_bib0580","series-title":"2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops","first-page":"20","article-title":"View invariant human action recognition using histograms of 3D joints","author":"Xia","year":"2012"},{"key":"10.1016\/j.cosrev.2026.101030_bib0585","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"10276","article-title":"Generative action description prompts for skeleton-based action recognition","author":"Xiang","year":"2023"},{"key":"10.1016\/j.cosrev.2026.101030_bib0590","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"6225","article-title":"Dynamic semantic-based spatial graph convolution network for skeleton-based human action recognition","author":"Xie","year":"2024"},{"key":"10.1016\/j.cosrev.2026.101030_bib0595","doi-asserted-by":"crossref","first-page":"164","DOI":"10.1016\/j.neucom.2023.03.001","article-title":"Transformer for skeleton-based action recognition: a review of recent advances","volume":"537","author":"Xin","year":"2023","journal-title":"Neurocomputing"},{"key":"10.1016\/j.cosrev.2026.101030_bib0600","doi-asserted-by":"crossref","first-page":"5784","DOI":"10.1109\/TMM.2025.3543034","article-title":"Language knowledge-assisted representation learning for skeleton-based action recognition","volume":"27","author":"Xu","year":"2025","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.cosrev.2026.101030_bib0605","doi-asserted-by":"crossref","first-page":"51689","DOI":"10.1109\/ACCESS.2023.3274658","article-title":"A transformer-based unsupervised domain adaptation method for skeleton behavior recognition","volume":"11","author":"Yan","year":"2023","journal-title":"IEEE Access"},{"key":"10.1016\/j.cosrev.2026.101030_bib0610","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","article-title":"Spatial temporal graph convolutional networks for skeleton-based action recognition","author":"Yan","year":"2018"},{"key":"10.1016\/j.cosrev.2026.101030_bib0615","series-title":"European Conference on Computer Vision","first-page":"113","article-title":"Crossglg: LLM guides one-shot skeleton-based 3D action recognition in a cross-level manner","author":"Yan","year":"2024"},{"key":"10.1016\/j.cosrev.2026.101030_bib0620","doi-asserted-by":"crossref","first-page":"2351","DOI":"10.1007\/s11263-023-01967-8","article-title":"View-invariant skeleton action representation learning via motion retargeting","volume":"132","author":"Yang","year":"2024","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.cosrev.2026.101030_bib0625","doi-asserted-by":"crossref","first-page":"18756","DOI":"10.52202\/075280-0822","article-title":"Mm-fi: multi-modal non-intrusive 4D human dataset for versatile wireless sensing","volume":"36","author":"Yang","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cosrev.2026.101030_bib0630","series-title":"2022 IEEE International Conference on Multimedia and Expo (ICME)","first-page":"01","article-title":"Mke-gcn: multi-modal knowledge embedded graph convolutional network for skeleton-based action recognition in the wild","author":"Yang","year":"2022"},{"key":"10.1016\/j.cosrev.2026.101030_bib0635","series-title":"IECON 2022\u201348th Annual Conference of the IEEE Industrial Electronics Society","first-page":"1","article-title":"Spatial transformer network with transfer learning for small-scale fine-grained skeleton-based TAI chi action recognition","author":"Yuan","year":"2022"},{"key":"10.1016\/j.cosrev.2026.101030_bib0640","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1016\/j.neucom.2022.09.071","article-title":"Action recognition based on RGB and skeleton data sets: a survey","volume":"512","author":"Yue","year":"2022","journal-title":"Neurocomputing"},{"key":"10.1016\/j.cosrev.2026.101030_bib0645","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"6917","article-title":"Behavioral recognition of skeletal data based on targeted dual fusion strategy","author":"Yun","year":"2024"},{"key":"10.1016\/j.cosrev.2026.101030_bib0650","article-title":"Self-supervised skeleton-based action representation learning: a benchmark and beyond","author":"Zhang","year":"2026","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.cosrev.2026.101030_bib0655","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"2117","article-title":"View adaptive recurrent neural networks for high performance human action recognition from skeleton data","author":"Zhang","year":"2017"},{"key":"10.1016\/j.cosrev.2026.101030_bib0660","doi-asserted-by":"crossref","first-page":"1061","DOI":"10.1109\/TIP.2019.2937724","article-title":"EleAtt-RNN: adding attentiveness to neurons in recurrent neural networks","volume":"29","author":"Zhang","year":"2019","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.cosrev.2026.101030_bib0665","series-title":"2021 IEEE International Conference on Multimedia and Expo (ICME)","first-page":"1","article-title":"Multi-scale enhanced active learning for skeleton-based action recognition","author":"Zhang","year":"2021"},{"key":"10.1016\/j.cosrev.2026.101030_bib0670","series-title":"Adjunct Proceedings of the 2020 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2020 ACM International Symposium on Wearable Computers","first-page":"368","article-title":"IndRNN based long-term temporal recognition in the spatial and frequency domain","author":"Zhao","year":"2020"},{"key":"10.1016\/j.cosrev.2026.101030_bib0675","author":"Zhou"},{"key":"10.1016\/j.cosrev.2026.101030_bib0680","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"3825","article-title":"Self-supervised action representation learning from partial spatio-temporal skeleton sequences","author":"Zhou","year":"2023"},{"key":"10.1016\/j.cosrev.2026.101030_bib0685","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"2049","article-title":"Blockgcn: redefine topology awareness for skeleton-based action recognition","author":"Zhou","year":"2024"},{"key":"10.1016\/j.cosrev.2026.101030_bib0690","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"18761","article-title":"Part-aware unified representation of language and skeleton for zero-shot action recognition","author":"Zhu","year":"2024"},{"key":"10.1016\/j.cosrev.2026.101030_bib0695","doi-asserted-by":"crossref","first-page":"496","DOI":"10.1109\/TIP.2022.3230249","article-title":"Multilevel spatial\u2013temporal excited graph network for skeleton-based action recognition","volume":"32","author":"Zhu","year":"2022","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.cosrev.2026.101030_bib0700","doi-asserted-by":"crossref","DOI":"10.1016\/j.sigpro.2023.108953","article-title":"Time-to-space progressive network using overlap skeleton contexts for action recognition","volume":"207","author":"Zhuang","year":"2023","journal-title":"Signal Process."},{"issue":"3","key":"10.1016\/j.cosrev.2026.101030_bib0705","doi-asserted-by":"crossref","first-page":"2101","DOI":"10.1109\/TCSVT.2024.3491133","article-title":"DSDC-GCN: decoupled static-dynamic co-occurrence graph convolutional networks for skeleton-based action recognition","volume":"35","author":"Zhuang","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."}],"container-title":["Computer Science Review"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1574013726001383?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1574013726001383?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T17:58:09Z","timestamp":1783360689000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1574013726001383"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":141,"alternative-id":["S1574013726001383"],"URL":"https:\/\/doi.org\/10.1016\/j.cosrev.2026.101030","relation":{},"ISSN":["1574-0137"],"issn-type":[{"value":"1574-0137","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Beyond benchmark accuracy: A generalization-centered analysis of deep learning for skeleton-based human activity recognition","name":"articletitle","label":"Article Title"},{"value":"Computer Science Review","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.cosrev.2026.101030","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Author(s). Published by Elsevier Inc.","name":"copyright","label":"Copyright"}],"article-number":"101030"}}