# Triple Spectral Fusion for Sensor-based Human Activity Recognition

arXiv: https://arxiv.org/abs/2605.02743 · HTML: https://mlsanity.com/paper/2605.02743/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 72 references that are in the map.
- First posted on arXiv 4 May 2026.

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling](https://mlsanity.com/paper/1803.01271/) (2018)
- [Deep Learning for Sensor-based Human Activity Recognition: Overview, Challenges and Opportunities](https://mlsanity.com/paper/2001.07416/) (2020)
- [A Survey on Heterogeneous Graph Embedding: Methods, Techniques, Applications and Sources](https://mlsanity.com/paper/2011.14867/) (2020)
- [XSleepNet: Multi-View Sequential Model for Automatic Sleep Staging](https://mlsanity.com/paper/2007.05492/) (2020)
- [DeepSense: A Unified Deep Learning Framework for Time-Series Mobile Sensing Data Processing](https://mlsanity.com/paper/1611.01942/) (2016)
- [Self-supervised Contrastive Representation Learning for Semi-supervised Time-Series Classification](https://mlsanity.com/paper/2208.06616/) (2022)
- [Human Activity Recognition from Wearable Sensor Data Using Self-Attention](https://mlsanity.com/paper/2003.09018/) (2020)
- [Past, Present, and Future of Sensor-Based Human Activity Recognition Using Wearables: A Surveying Tutorial on a Still Challenging Task](https://mlsanity.com/paper/2411.14452/) (2024)
- [Layout Agnostic Human Activity Recognition in Smart Homes through Textual Descriptions Of Sensor Triggers (TDOST)](https://mlsanity.com/paper/2405.12368/) (2024)
- [Privacy and Utility Preserving Sensor-Data Transformations](https://mlsanity.com/paper/1911.05996/) (2019)
- [Predictive Maintenance for General Aviation Using Convolutional Transformers](https://mlsanity.com/paper/2110.03757/) (2021)
- [Detecting Unseen Falls from Wearable Devices using Channel-wise Ensemble of Autoencoders](https://mlsanity.com/paper/1610.03761/) (2016)
- [HiSC4D: Human-centered interaction and 4D Scene Capture in Large-scale Space Using Wearable IMUs and LiDAR](https://mlsanity.com/paper/2409.04398/) (2024)
- [DiversityOne: A Multi-Country Smartphone Sensor Dataset for Everyday Life Behavior Modeling](https://mlsanity.com/paper/2502.03347/) (2025)
- [Decomposing and Fusing Intra- and Inter-Sensor Spatio-Temporal Signal for Multi-Sensor Wearable Human Activity Recognition](https://mlsanity.com/paper/2501.10917/) (2025)
- [Deep Lookup Network](https://mlsanity.com/paper/2509.13662/) (2025)

## Abstract (arXiv)

The field of sensor-based human activity recognition (HAR) mainly uses posture, motion and context data of Inertial Measurement Units (IMUs) to identify daily activities. Despite the advancements in learning-based methods, it is challenging to perform information fusion from the temporal perspective due to the complexities in fusing heterogeneous sensor data and establishing long-term context correlations. This paper proposes a novel triple spectral fusion framework tailored for HAR. First, we develop an adaptive complementary filtering technique for noise suppression and organize each IMU's sensors into posture and motion modality nodes. Given that IMU nodes form a dynamic heterogeneous graph, we then apply adaptive filtering within the graph Fourier domain to merge both homogeneous and heterogeneous node information. Furthermore, an adaptive wavelet frequency selection approach is implemented to suppress context redundancy and shorten the length of features. This approach enhances both timestamp-based graph aggregation and the correlation of long-term contexts. Our framework uses adaptive filtering in the Fourier, graph Fourier, and wavelet domains, enabling effective multi-sensor fusion and context correlation. Extensive experiments on ten benchmark datasets demonstrate the superior performance of our framework. Project page: https://github.com/crocodilegogogo/TSF-TPAMI2026.