Domain Generalization for Activity Recognition via Adaptive Feature Fusion
Open accessAbstract
Human activity recognition requires the efforts to build a generalizable model using the training datasets with the hope to achieve good performance in test datasets. However, in real applications, the training and testing datasets may have totally different distributions due to various reasons such as different body shapes, acting styles, and habits, damaging the model’s generalization performance. While such a distribution gap can be reduced by existing domain adaptation approaches, they typically assume that the test data can be accessed in the training stage, which is not realistic. In this article, we consider a more practical and challenging scenario: domain-generalized activity recognition (DGAR) where the test dataset cannot be accessed during training. To this end, we propose Adaptive Feature Fusion for Activity Recognition (AFFAR) , a domain generalization approach that learns to fuse the domain-invariant and domain-specific representations to improve the model’s generalization performance. AFFAR takes the best of both worlds where domain-invariant representations enhance the transferability across domains and domain-specific representations leverage the model discrimination power from each domain. Extensive experiments on three public HAR datasets show its effectiveness. Furthermore, we apply AFFAR to a real application, i.e., the diagnosis of Children’s Attention Deficit Hyperactivity Disorder (ADHD), which also demonstrates the superiority of our approach.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
Domain-invariant representation methods for user generalization often rely on indirect modeling of user differences and require assumptions such as known domain boundaries or sufficient domain diversity.
“Although they achieve promising zero-shot performance, such methods usually rely on indirect modeling of user differences and require assumptions such as known domain boundaries or sufficient domain diversity.”
From Towards User-Generalizable Wearable-Sensor-Based Human Activity Recognition: A Multi-Task Contrastive Learning Approach (2025) · cites this paper as [18]
Alignment-based strategies introduce explicit mechanisms to enforce consistency across users or domains, adding extra training components and regularization overhead.
“Although these methods encourage generalization, they add extra training components and regularization overhead.”
From Towards User-Generalizable Wearable-Sensor-Based Human Activity Recognition: A Multi-Task Contrastive Learning Approach (2025) · cites this paper as [18]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Pan, S. J., & Yang, Q. (2010) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2009.191 · Cited by 23,387 · see citing works
An introduction to ROC analysis
Fawcett, T. (2006) · Pattern Recognition Letters · doi:10.1016/j.patrec.2005.10.010 · Cited by 21,879 · see citing works
International Conference on Learning Representations (ICLR 2013)
松尾, 豊. (2013) · 人工知能学会誌 = Journal of Japanese Society for Artificial Intelligence · Cited by 6,286 · see citing works
Weiss, K., Khoshgoftaar, T. M., & Wang, D. (2016) · Journal of Big Data · doi:10.1186/s40537-016-0043-6 · Cited by 6,260 · see citing works
Deep CORAL: Correlation Alignment for Deep Domain Adaptation
Sun, B., & Saenko, K. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-49409-8_35 · Cited by 3,757 · see citing works
A Survey on Human Activity Recognition using Wearable Sensors
Lara, O. D., & Labrador, M. A. (2013) · IEEE Communications Surveys & Tutorials · doi:10.1109/surv.2012.110112.00192 · Cited by 2,662 · see citing works
Advances in Neural Information Processing Systems 32 (NeurIPS 2019)
Wallach, H., Larochelle, H., Beygelzimer, A., d’Alché–Buc, F., Fox, E. B., & Garnett, R. (2020) · HAL · Cited by 2,450 · see citing works
ADHD Working Group of the Psychiatric Genomics Consortium (PGC), Demontis, D., Early Lifecourse & Genetic Epidemiology (EAGLE) Consortium, 23andMe Research Team, Walters, R. K., Martin, J., Mattheisen, M., Als, T. D., Agerbo, E., Baldursson, G., et al. (2019) · Nature Genetics · doi:10.1038/s41588-018-0269-7 · Cited by 2,203 · 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
Self-citationAdvances in Neural Information Processing Systems 5
Zemel, R. S., Williams, C. K. I., & Mozer, M. C. (1993) · Cited by 1,896 · see citing works
Introducing a New Benchmarked Dataset for Activity Monitoring
Reiss, A., & Stricker, D. (2012) · 2012 16th International Symposium on Wearable Computers · doi:10.1109/iswc.2012.13 · Cited by 1,456 · cited 5× · see citing works
“PAMAP2 [41] consists of data collected from 9 subjects performing 18 activities.”
BackgroundInfluentialLearning to Generalize: Meta-Learning for Domain Generalization
Li, D., Yang, Y., Song, Y.-Z., & Hospedales, T. M. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11596 · Cited by 1,313 · see citing works
Sensor-Based Activity Recognition
Chen, L., Hoey, J., Nugent, C. D., Cook, D. J., & Yu, Z. (2012) · IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews) · doi:10.1109/tsmcc.2012.2198883 · Cited by 1,074 · see citing works
Generalizing to unseen domains: A survey on domain generalization
Wang, J., Lan, C., Liu, C., Ouyang, Y., Qin, T., Lu, W., Chen, Y., Zeng, W., & Yu, P. (2022) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2022.3178128 · Cited by 1,046 · see citing works
Self-citationTransfer Learning for Visual Categorization: A Survey
Shao, L., Zhu, F., & Li, X. (2015) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2014.2330900 · Cited by 895 · see citing works
Domain Generalization by Solving Jigsaw Puzzles
Carlucci, F. M., D’Innocente, A., Bucci, S., Barbara Caputo, B., & Tommasi, T. (2019) · 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/cvpr.2019.00233 · Cited by 838 · see citing works
Time-series Generative Adversarial Networks
Yoon, J., Jarrett, D. P., & van der Schaar, M. (2019) · neural information processing systems · Cited by 755 · see citing works
Deep Learning for Sensor-based Human Activity Recognition
Chen, K., Zhang, D., Yao, L., Guo, B., Yu, Z., & Liu, Y. (2022) · ACM Computing Surveys · doi:10.1145/3447744 · Cited by 690 · cited 1× · see citing works
“Over these years, many eforts have been done to achieve accurate and robust activity recognition including traditional machine learning methods[28] combined with feature extraction, and deep learning methods [8, 53].”
BackgroundAttention-Deficit Hyperactivity Disorder
Barkley, R. A. (1998) · Scientific American · doi:10.1038/scientificamerican0998-66 · Cited by 688 · see citing works
Human Activity Recognition Using Wearable Sensors by Deep Convolutional Neural Networks
Jiang, W., & Yin, Z. (2015) · Proceedings of the 23rd ACM international conference on Multimedia · doi:10.1145/2733373.2806333 · Cited by 676 · see citing works
Domain Generalization for Object Recognition with Multi-task Autoencoders
Ghifary, M., Kleijn, W. B., Zhang, M., & Balduzzi, D. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.293 · Cited by 664 · see citing works
Self-challenging Improves Cross-Domain Generalization
Huang, Z., Wang, H., Xing, E. P., & Huang, D. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58536-5_8 · Cited by 597 · see citing works
Driver Fatigue Detection Systems: A Review
Sikander, G., & Anwar, S. (2018) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2018.2868499 · Cited by 556 · see citing works
Ensembles of Deep LSTM Learners for Activity Recognition using Wearables
Guan, Y., & Plötz, T. (2017) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3090076 · Cited by 511 · see citing works
Learning to Learn Single Domain Generalization
Qiao, F., Zhao, L., & Peng, X. (2020) · 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/cvpr42600.2020.01257 · Cited by 476 · see citing works
Transfer learning for activity recognition: a survey
Cook, D., Feuz, K. D., & Krishnan, N. C. (2013) · Knowledge and Information Systems · doi:10.1007/s10115-013-0665-3 · Cited by 447 · see citing works
Generalizing Across Domains via Cross-Gradient TrainingPreprint
Shankar, S., Piratla, V., Chakrabarti, S., Chaudhuri, S., Jyothi, P., & Sarawagi, S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1804.10745 · Cited by 379 · see citing works
DLOW: Domain Flow for Adaptation and Generalization
Gong, R., Li, W., Chen, Y., & Gool, L. V. (2019) · 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/cvpr.2019.00258 · Cited by 368 · see citing works
Self-citationBarshan, B., & Yüksek, M. C. (2013) · The Computer Journal · doi:10.1093/comjnl/bxt075 · Cited by 346 · see citing works
Deep Learning for Fall Detection: Three-Dimensional CNN Combined With LSTM on Video Kinematic Data
Lü, N., Wu, Y., Li, F., & Song, J. (2018) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2018.2808281 · Cited by 341 · see citing works
Deep Learning for Sensor-based Human Activity Recognition: Overview, Challenges and Opportunities
Chen, K., Zhang, D., Yao, L., Guo, B., Yu, Z., & Liu, Y. (2020) · arXiv · doi:10.48550/arxiv.2001.07416 · Cited by 314 · cited 1× · see citing works
“Over these years, many eforts have been done to achieve accurate and robust activity recognition including traditional machine learning methods[28] combined with feature extraction, and deep learning methods [8, 53].”
BackgroundGeneralizing to Unseen Domains: A Survey on Domain Generalization
Wang, J., Lan, C., Liu, C., Ouyang, Y., & Qin, T. (2021) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2021/628 · Cited by 309 · see citing works
Self-citationDomain Generalization Using a Mixture of Multiple Latent Domains
Matsuura, T., & Harada, T. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i07.6846 · Cited by 301 · see citing works
Going Deeper into First-Person Activity Recognition
Ma, M., Fan, H., & Kitani, K. (2016) · 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/cvpr.2016.209 · Cited by 281 · see citing works
(2011) · Cited by 277 · see citing works
Stratified Transfer Learning for Cross-domain Activity Recognition
Wang, J., Chen, Y., Hu, L., Peng, X., & Yu, P. S. (2018) · IEEE International Conference on Pervasive Computing and Communications · doi:10.1109/percom.2018.8444572 · Cited by 277 · see citing works
Self-citationApplication of pretrained deep neural networks to large vocabulary speech recognition
Jaitly, N., Nguyen, P., Senior, A., & Vanhoucke, V. (2012) · Interspeech (USB) · doi:10.21437/interspeech.2012-10 · Cited by 244 · see citing works
Wang, S., Yu, L., Kang Li, B., et al. (2020) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2020.3015224 · Cited by 207 · see citing works
Batch normalization embeddings for deep domain generalization
Segù, M., Tonioni, A., & Tombari, F. (2022) · Pattern Recognition · doi:10.1016/j.patcog.2022.109115 · Cited by 159 · see citing works
Scaling Human Activity Recognition via Deep Learning-based Domain Adaptation
Khan, M. A. A. H., Roy, N., & Misra, A. (2018) · IEEE International Conference on Pervasive Computing and Communications · doi:10.1109/percom.2018.8444585 · Cited by 150 · see citing works
Soleimani, E., & Nazerfard, E. (2021) · Neurocomputing · doi:10.1016/j.neucom.2020.10.056 · Cited by 146 · see citing works
Best Sources Forward: Domain Generalization through Source-Specific Nets
Mancini, M., Bulò, S. R., Barbara Caputo, B., & Ricci, E. (2018) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2018.8451318 · Cited by 144 · see citing works
A Systematic Study of Unsupervised Domain Adaptation for Robust Human-Activity Recognition
Chang, Y., Mathur, A., Isopoussu, A., Song, J., & Kawsar, F. (2020) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3380985 · Cited by 140 · see citing works
Domain Generalization and Adaptation Using Low Rank Exemplar SVMs
Li, W., Xu, Z., Xu, D., Dai, D., & Gool, L. V. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2704624 · Cited by 121 · see citing works
Improve Unsupervised Domain Adaptation with Mixup TrainingPreprint
Yan, S., Song, H., Li, N., Zou, L., & Liu, R. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.00677 · Cited by 120 · see citing works
Cross-Dataset Activity Recognition via Adaptive Spatial-Temporal Transfer Learning
Qin, X., Chen, Y., Wang, J., & Yu, C. (2019) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3369818 · Cited by 90 · see citing works
Self-citationGeneralizing to unseen domains via distribution matchingPreprint
Albuquerque, I., Monteiro, J., Darvishi-Bayazi, M.-J., Falk, T. H., & Mitliagkas, I. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.00804 · Cited by 87 · see citing works
Li, X., Luo, J., & Younes, R. (2020) · 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 · doi:10.1145/3410530.3414367 · Cited by 71 · see citing works
Jiang, X., Chen, Y., Huang, W., Zhang, T., Gao, C., Xing, Y., & Zheng, Y. (2020) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3313831.3376374 · Cited by 29 · see citing works
Self-citationHeterogeneous transfer learning for activity recognition using heuristic search techniques
Feuz, K., & Cook, D. J. (2014) · International Journal of Pervasive Computing and Communications · doi:10.1108/ijpcc-03-2014-0020 · Cited by 27 · see citing works
Unsupervised domain adaptation for activity recognition across heterogeneous datasets
Sanabria, A. R., & Ye, J. (2020) · Pervasive and Mobile Computing · doi:10.1016/j.pmcj.2020.101147 · Cited by 25 · see citing works
Domain Generalization with Optimal Transport and Metric Learning.Preprint
Zhou, F., Jiang, Z., Shui, C., Wang, B., & Chaib-draa, B. (2020) · arXiv (Cornell University) · Cited by 17 · see citing works
Domain Generalization Needs Stochastic Weight Averaging for Robustness on Domain Shifts.Preprint
Cha, J., Cho, H., Lee, K., Park, S., Lee, Y., & Park, S. (2021) · arXiv (Cornell University) · Cited by 13 · see citing works
Domain Specific Learning for Sentiment Classification and Activity Recognition
Wang, H., Xue, Y., Zhen, X., & Tu, X. (2018) · IEEE Access · doi:10.1109/access.2018.2871349 · Cited by 10 · see citing works
Batch Normalization Embeddings for Deep Domain GeneralizationPreprint
Segù, M., Tonioni, A., & Tombari, F. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.12672 · Cited by 9 · see citing works
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805
Flagged first, then by citations
Research works printed but not linked: 10
- Thomas G. Dietterich. 2002. Ensemble learning. The Handbook of Brain Theory and Neural Networks 2 (2002), 110-125.
- Chelsea Finn, Pieter Abbeel, and Sergey Levine. 2017. Model-agnostic meta-learning for fast adaptation of deep net- works. In International Conference on Machine Learning. PMLR, 1126-1135.
- Yaroslav Ganin, Evgeniya Ustinova, Hana Ajakan, Pascal Germain, Hugo Larochelle, François Laviolette, Mario Marchand, and Victor Lempitsky. 2016. Domain-adversarial training of neural networks. The Journal of Machine Learning Research 17, 1 (2016), 2096-2030.
- Arthur Gretton, Karsten M. Borgwardt, Malte J. Rasch, Bernhard Schölkopf, and Alexander Smola. 2012. A kernel two-sample test. Journal of Machine Learning Research 13, (March 2012), 723-773.
- Ishaan Gulrajani and David Lopez-Paz. 2021. In search of lost domain generalization. In International Conference on Learning Representations (ICLR'21).
- Nishkam Ravi, Nikhil Dandekar, Preetham Mysore, and Michael L. Littman. 2005. Activity recognition from accelerom- eter data. In AAAI, Vol. 5. 1541-1546.
- Shiori Sagawa, Pang Wei Koh, Tatsunori B. Hashimoto, and Percy Liang. 2020. Distributionally robust neural networks for group shifts: On the importance of regularization for worst-case generalization. In International Conference on Learning Representations (ICLR'20).
- Mihaela C. Stoian, Sameer Bansal, and Sharon Goldwater. 2020. Analyzing ASR pretraining for low-resource speech- to-text translation. In ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP'20). IEEE, 7909-7913.
- Vladimir Vapnik. 1992. Principles of risk minimization for learning theory. In Advances in Neural Information Process- ing Systems. 831-838.
- Mi Zhang and Alexander A. Sawchuk. 2012. USC-HAD: A daily activity dataset for ubiquitous activity recognition using wearable sensors. In ACM UbiComp. ACM, 1036-1043.
Cited by
Sorted by citations
Hong, Z., Li, Z., Zhong, S., Lyu, W., Wang, H., Ding, Y., He, T., & Zhang, D. (2024) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3659597 · Cited by 67 · see citing works
Qin, X., Wang, J., Ma, S., Lu, W., Zhu, Y., Xie, X., & Chen, Y. (2023) · Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining · doi:10.1145/3580305.3599360 · Cited by 29 · see citing works
Self-citationGuo, P., & Nakayama, M. (2025) · Sensors · doi:10.3390/s25226988 · Cited by 6 · see citing works
- Authors
- Qin, X., Wang, J., Chen, Y., Lu, W., & Jiang, X.
- Affiliations
- Institute of Computing Technology (CN)
- Microsoft Research Asia (China) (CN)
- Beijing Key Laboratory of Mobile Computing and Pervasive Devices, Institute of Computing Technology, CAS, University of Chinese Academy of Sciences, Beijing, China
- Chinese Academy of Sciences (CN)
- Venue
- ACM Transactions on Intelligent Systems and Technology
- Published
- 2022-11-09
- Volume
- 14
- Issue
- 1
- Pages
- 1-21
- ISSN
- 2157-6904 (ISSN-L)
- 2157-6912
- OpenAlex
- W4289517877
- Cited by
- 55
- References
- 56
- Citations by year
- 2026: 13 · 2025: 18 · 2024: 14 · 2023: 9 · 2022: 1
- FWCI
- 3.45
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- ACM Transactions on Intelligent Systems and Technology (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University) (cc-by)
- Funders
- National Key Research and Development Plan of China (2021YFC2501202)
- Natural Science Foundation of China (61972383, 61902377, 62101530, 61902379)
- Science and Technology Service Network Initiative, Chinese Academy of Sciences (KFJ-STS-QYZD-2021-11-001)
- Youth Innovation Promotion Association CAS
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Physical Sciences › Engineering › Biomedical Engineering › Gait Recognition and Analysis
- Keywords
- domain generalization, human activity recognition, adaptive feature fusion, domain-invariant features, domain-specific representations, distribution shift, cross-domain transferability, ADHD diagnosis, wearable sensor data
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
