Deep Learning for Skeleton-Based Human Activity Segmentation: An Autoencoder Approach
Open accessAbstract
Automatic segmentation is essential for enhancing human activity recognition, especially given the limitations of publicly available datasets that often lack diversity in daily activities. This study introduces a novel segmentation method that utilizes skeleton data for a more accurate and efficient analysis of human actions. By employing an autoencoder, this method extracts representative features and reconstructs the dataset, using the discrepancies between the original and reconstructed data to establish a segmentation threshold. This innovative approach allows for the automatic segmentation of activity datasets into distinct segments. Rigorous evaluations against ground truth across three publicly available datasets demonstrate the method’s effectiveness, achieving impressive average annotation error, precision, recall, and F1-score values of 3.6, 90%, 87%, and 88%, respectively. This illustrates the robustness of the proposed method in accurately identifying change points and segmenting continuous skeleton-based activities as compared to two other state-of-the-art techniques: one based on deep learning and another using the classical time-series segmentation algorithm. Additionally, the dynamic thresholding mechanism enhances the adaptability of the segmentation process to different activity dynamics improving overall segmentation accuracy. This performance highlights the potential of the proposed method to significantly advance the field of human activity recognition by improving the accuracy and efficiency of identifying and categorizing human movements.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Deep learning techniques, particularly those based on convolutional neural networks (CNNs), are widely used due to their performance in image recognition tasks.
“Deep learning techniques [78], particularly those based on convolutional neural networks (CNNs) [79], are widely used due to their performance in image recognition tasks.”
From A Review of Passenger Counting in Public Transport Concepts with Solution Proposal Based on Image Processing and Machine Learning (2024) · cites this paper as [78]
Cites
Reducing the dimensionality of data with neural networks
Hinton, G. E., & Salakhutdinov, R. R. (2006) · Science · doi:10.1126/science.1127647 · Cited by 20,928 · see citing works
Extracting and composing robust features with denoising autoencoders
Vincent, P., Larochelle, H., Bengio, Y., & Manzagol, P.-A. (2008) · Proceedings of the 25th international conference on Machine learning - ICML '08 · doi:10.1145/1390156.1390294 · Cited by 7,436 · see citing works
Human3.6M: Large Scale Datasets and Predictive Methods for 3D Human Sensing in Natural Environments
Ionescu, C., Papava, D., Olaru, V., & Sminchisescu, C. (2014) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.248 · Cited by 3,653 · cited 3× · see citing works
“These include managing complex and detailed activities, handling occlusion and noise in the data, addressing inter-class variability, and adapting to real-world scenarios [1,17,20].”
BackgroundInfluentialOptimal Detection of Changepoints With a Linear Computational Cost
Killick, R., Fearnhead, P., & Eckley, I. A. (2012) · Journal of the American Statistical Association · doi:10.1080/01621459.2012.737745 · Cited by 2,586 · see citing works
Real-time human pose recognition in parts from single depth images
Shotton, J., Sharp, T., Kipman, A., Fitzgibbon, A. W., Finocchio, M., Blake, A., Cook, M., & Moore, R. (2013) · Communications of the ACM · doi:10.1145/2398356.2398381 · Cited by 2,050 · see citing works
Deep learning for sensor-based activity recognition: A survey
Wang, J., Chen, Y., Hao, S., Peng, X., & Hu, L. (2019) · Pattern Recognition Letters · doi:10.1016/j.patrec.2018.02.010 · Cited by 2,014 · see citing works
NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding
Liu, J., Shahroudy, A., Pérez, M., Wang, G., Duan, L., & Kot, A. C. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2916873 · Cited by 1,841 · see citing works
Time-series clustering – A decade review
Aghabozorgi, S., Seyed Shirkhorshidi, A., & Ying Wah, T. (2015) · Information Systems · doi:10.1016/j.is.2015.04.007 · Cited by 1,826 · cited 3× · see citing works
“This visualization is structured across two distinct rows; the upper row showcases a series of skeleton frames performing varied 32], is adopted, reflecting a strategy consistent with approaches used in previous works for segmenting accelerometer-based human activity data [33,34].”
MethodView invariant human action recognition using histograms of 3D joints
Xia, L., Chen, C.-C., & Aggarwal, J. K. (2012) · 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops · doi:10.1109/cvprw.2012.6239233 · Cited by 1,512 · see citing works
Selective review of offline change point detection methods
Truong, C., Oudre, L., & Vayatis, N. (2019) · Signal Processing · doi:10.1016/j.sigpro.2019.107299 · Cited by 1,368 · see citing works
Revisiting Skeleton-based Action Recognition
Duan, H., Zhao, Y., Chen, K., Lin, D., & Dai, B. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.00298 · Cited by 902 · see citing works
Zhu, Z. (2017) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2017.06.013 · Cited by 869 · see citing works
Sensor-based and vision-based human activity recognition: A comprehensive survey
Minh Dang, L., Min, K., Wang, H., Jalil Piran, M., Hee Lee, C., & Moon, H. (2020) · Pattern Recognition · doi:10.1016/j.patcog.2020.107561 · Cited by 730 · cited 2× · see citing works
“These advancements hold promise for enhancing applications in human–computer interaction, sports analysis, and healthcare monitoring [17,18].”
BackgroundHuman Activity Recognition and Pattern Discovery
Kim, E., Helal, S., & Cook, D. J. (2010) · IEEE Pervasive Computing · doi:10.1109/mprv.2010.7 · Cited by 697 · see citing works
Human Action Recognition From Various Data Modalities: A Review
Sun, Z., Ke, Q., Rahmani, H., Bennamoun, M., Wang, G., & Liu, J. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3183112 · Cited by 691 · see citing works
Going deeper into action recognition: A survey
Herath, S., Harandi, M. T., & Porikli, F. (2017) · Image and Vision Computing · doi:10.1016/j.imavis.2017.01.010 · Cited by 646 · see citing works
View Adaptive Neural Networks for High Performance Skeleton-Based Human Action Recognition
Zhang, P., Lan, C., Xing, J., Zeng, W., Xue, J., & Zheng, N. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2896631 · Cited by 523 · see citing works
A Comprehensive Survey of Vision-Based Human Action Recognition Methods
Zhang, H.-B., Zhang, Y.-X., Zhong, B., Lei, Q., Yang, L., Du, J.-X., & Chen, D.-S. (2019) · Sensors · doi:10.3390/s19051005 · Cited by 503 · cited 2× · see citing works
“The utilization of skeleton data, extracted from depth data, such as those acquired with the Kinect sensor, has garnered substantial attention in human activity recognition [8–12].”
BackgroundMethodPareek, P., & Thakkar, A. (2020) · Artificial Intelligence Review · doi:10.1007/s10462-020-09904-8 · Cited by 466 · see citing works
Change-point detection in time-series data by relative density-ratio estimation
Liu, S., Yamada, M., Collier, N., & Sugiyama, M. (2013) · Neural Networks · doi:10.1016/j.neunet.2013.01.012 · Cited by 450 · see citing works
Vision-based human activity recognition: a survey
Beddiar, D., Nini, B., Sabokrou, M., & Hadid, A. (2020) · Multimedia tools and applications · doi:10.1007/s11042-020-09004-3 · Cited by 444 · see citing works
An algorithm for optimal partitioning of data on an interval
Jackson, B., Scargle, J. D., Barnes, D., Arabhi, S., Alt, A., Gioumousis, P., Gwin, E., San, P., Tan, L., & Tsai, T. T. (2005) · IEEE Signal Processing Letters · doi:10.1109/lsp.2001.838216 · Cited by 433 · see citing works
3D skeleton-based human action classification: A survey
Presti, L. L., & Cascia, M. L. (2015) · Pattern Recognition · doi:10.1016/j.patcog.2015.11.019 · Cited by 393 · see citing works
A Comparative Review of Recent Kinect-Based Action Recognition Algorithms
Wang, L., Huynh, D. Q., & Koniusz, P. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2925285 · Cited by 261 · see citing works
A Human Activity Recognition System Using Skeleton Data from RGBD Sensors
Cippitelli, E., Gasparrini, S., Gambi, E., & Spinsante, S. (2016) · Computational Intelligence and Neuroscience · doi:10.1155/2016/4351435 · Cited by 226 · see citing works
Change-Point Detection in Time-Series Data by Direct Density-Ratio Estimation
Kawahara, Y., & Sugiyama, M. (2009) · SIAM International Conference on Data Mining · doi:10.1137/1.9781611972795.34 · Cited by 170 · see citing works
Denoising Adversarial Autoencoders
Creswell, A., & Bharath, A. A. (2018) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2018.2852738 · Cited by 154 · see citing works
Human Action Recognition from Various Data Modalities: A ReviewPreprint
Rahmani, H., Bennamoun, M., & Ke, Q. (2021) · doi:10.36227/techrxiv.13708270 · Cited by 99 · see citing works
3D human action segmentation and recognition using pose kinetic energy
Shan, J., & Akella, S. (2014) · doi:10.1109/arso.2014.7020983 · Cited by 97 · see citing works
A Comprehensive Survey of RGB-Based and Skeleton-Based Human Action Recognition
Wang, C., & Yan, J. (2023) · IEEE Access · doi:10.1109/access.2023.3282311 · Cited by 79 · see citing works
Skeleton Graph-Neural-Network-Based Human Action Recognition: A Survey
Feng, M., & Meunier, J. (2022) · Sensors · doi:10.3390/s22062091 · Cited by 72 · see citing works
Extracting and Composing Robust Features With Broad Learning System
Yang, K., Liu, Y., Yu, Z., & Chen, C. L. P. (2021) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2021.3137792 · Cited by 68 · see citing works
Deep learning‐based action recognition with 3D skeleton: A survey
Xing, Y., & Zhu, J. (2021) · CAAI Transactions on Intelligence Technology · doi:10.1049/cit2.12014 · Cited by 63 · see citing works
Online human action recognition based on incremental learning of weighted covariance descriptors
Tang, C., Li, W., Wang, P., & Wang, L. (2018) · Information Sciences · doi:10.1016/j.ins.2018.08.003 · Cited by 49 · see citing works
Recent evolution of modern datasets for human activity recognition: a deep survey
Singh, R. K., Sonawane, A., & Srivastava, R. (2019) · Multimedia Systems · doi:10.1007/s00530-019-00635-7 · Cited by 39 · see citing works
Time Series Segmentation through Automatic Feature Learning
Ortiz, J. (2018) · LatinX in AI at Neural Information Processing Systems Conference (LXAI) · doi:10.52591/lxai201812038 · Cited by 33 · see citing works
Gaugel, S., & Reichert, M. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.106078 · Cited by 31 · see citing works
Evaluation of 2D and 3D posture for human activity recognition
Hossen, M. A., Naim, A. G., & Abas, P. E. (2023) · AIP conference proceedings · doi:10.1063/5.0111224 · Cited by 6 · see citing works
Self-citationHossen, M. A., & Abas, P. E. (2023) · International Journal of Computing and Digital Systems · doi:10.12785/ijcds/1401110 · Cited by 3 · see citing works
Self-citationInvestigation of the Unsupervised Machine Learning Techniques for Human Activity Discovery
Hossen, M. A., Ong, W.-H., & Caesarendra, W. (2022) · Lecture notes in electrical engineering · doi:10.1007/978-981-19-1804-9_38 · Cited by 3 · see citing works
Self-citation
Flagged first, then by citations
Cited by
Sorted by citations
Machine Learning for Human Activity Recognition: State-of-the-Art Techniques and Emerging Trends
Hossen, M. A., & Abas, P. E. (2025) · Journal of Imaging · doi:10.3390/jimaging11030091 · Cited by 67 · see citing works
Self-citationDutta, M., Sujan, M. S. U., Mojumdar, M. U., Chakraborty, N. R., Marouf, A. A., Rokne, J. G., & Alhajj, R. (2024) · Technologies · doi:10.3390/technologies12110214 · Cited by 27 · see citing works
Joudaki, M., Imani, M., & Arabnia, H. R. (2025) · Technologies · doi:10.3390/technologies13020053 · Cited by 23 · see citing works
Radovan, A., Mršić, L., Đambić, G., & Mihaljević, B. (2024) · Eng · doi:10.3390/eng5040172 · Cited by 24 · see citing works
Li, J., Guo, W., & Zhang, W. (2025) · Future Internet · doi:10.3390/fi17120558
Almaqbali, S., Marhoubi, A. H., & Ali, O. (2025) · International Seminar on Research of Information Technology and Intelligent Systems (ISRITI) · doi:10.1109/isriti68345.2025.11393354
Wei, C., Jiang, X., Lin, X., & Wang, D. (2026) · International Conference on Artificial Intelligence, Internet of Things and Cloud Computing Technology (AIoTC) · doi:10.1109/aiotc71250.2026.11688723
- Authors
- Hossen, M. A., Naim, A. G., & Abas, P. E.
- Affiliations
- Universiti Brunei Darussalam (BN)
- Corresponding author
- Abas, Pg Emeroylariffion
- Venue
- Technologies
- Publisher
- MDPI AG
- Published
- 2024-06-27
- Volume
- 12
- Issue
- 7
- Pages
- 96
- ISSN
- 2227-7080 (ISSN-L)
- OpenAlex
- W4400123551
- Cited by
- 7
- References
- 40
- Citations by year
- 2026: 1 · 2025: 4 · 2024: 2
- FWCI
- 0.98
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Technologies (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Universiti Brunei Darussalam (UBD/RSCH/1.3/FICBF(b)/2024/023)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Human Pose and Action Recognition
- Physical Sciences › Computer Science › Signal Processing › Time Series Analysis and Forecasting
- Keywords
- activity segmentation, autoencoder, change point detection, dynamic thresholding, human motion analysis
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
