24 June 2025 in IEEE Transactions on Consumer Electronics
Multi-person motion detection remains a challenging problem due to the highly complex spatiotemporal dynamics it involves. Effective motion forecasting requires capturing both the internal joint movement patterns of individuals and the interactions among multiple individuals. While existing Transformer-based models have demonstrated remarkable performance, they predominantly focus on spatiotemporal features, often neglecting crucial relational interactions between joints. To address this limitation, we propose the Temporal-Spatial-Relation Former (TSRFormer), a novel model for multi-person 3D pose forecasting that integrates both spatiotemporal and relational features. The proposed TSRFormer consists of two complementary branches: the first branch leverages the Spatial Transformer and Temporal Transformer to extract spatial and temporal dependencies of motion joints, while the second branch employs a convolutional network to capture inter-person relationships. These branches interact and exchange information within the proposed computational mode, enabling a holistic understanding of motion dynamics from multiple perspectives. The experiments on benchmark datasets demonstrate that TSRFormer achieves competitive performance, particularly excelling in long-term motion prediction, thereby validating its effectiveness in capturing complex temporal dependencies and relational interactions in multi-person scenarios.
18 December 2025 in Digital Signal Processing
27 December 2024 in IEEE Transactions on Cognitive and Developmental Systems
Language models have been undergoing rapid growth and remarkable success, while requiring massive computing resource. The brain-inspired spiking neural networks(SNNs), with advantages of better biological interpretability and less energy consumption, provides a likely alternative to process language tasks in a more sustainable way. However, there are still major difficulties in representing and processing text information with SNN-based models. Comprehensively exploring the neurodynamic diversity, we propose a spiking neural network model that could taking respective advantages from both integrator and resonator neurons to address text classification tasks. With collaborations of these two dynamically different spiking neurons, our network model outperforms previous SNN-based text classification model in an all-round way with much less time steps, and even shows some extent of potential to reach the performance of a topologically equivalent artificial neural network.
30 July 2026 in Digital Signal Processing