USAD: An Unsupervised Data Augmentation Spatio-Temporal Attention Diffusion Network

2025-07-03

AI Summary

To address three key challenges in human activity recognition (HAR)—scarce labels for rare classes, insufficient spatiotemporal feature representation, and difficulty in model lightweight deployment—this paper proposes a Statistical-guided Temporal-Spatial Diffusion Network (STD-Net). STD-Net introduces an unsupervised statistical-guided diffusion model to generate high-fidelity synthetic samples, effectively mitigating class imbalance. It further incorporates multi-scale convolutional layers with dual-path spatiotemporal attention, cross-branch fusion units, and an adaptive multi-loss optimization strategy to enhance discriminative feature learning. Evaluated on WISDM, PAMAP2, and OPPORTUNITY datasets, STD-Net achieves state-of-the-art accuracies of 98.84%, 93.81%, and 80.92%, respectively. Moreover, the model is successfully deployed on resource-constrained embedded devices, demonstrating both computational efficiency and practical applicability.

Technology Category

• Planning, Routing, and Scheduling: Activity and Plan Recognition
• Computer Vision: Video Understanding & Activity Analysis
• Machine Learning: Hardware-aware ML

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding

Abstract

The primary objective of human activity recognition (HAR) is to infer ongoing human actions from sensor data, a task that finds broad applications in health monitoring, safety protection, and sports analysis. Despite proliferating research, HAR still faces key challenges, including the scarcity of labeled samples for rare activities, insufficient extraction of high-level features, and suboptimal model performance on lightweight devices. To address these issues, this paper proposes a comprehensive optimization approach centered on multi-attention interaction mechanisms. First, an unsupervised, statistics-guided diffusion model is employed to perform data augmentation, thereby alleviating the problems of labeled data scarcity and severe class imbalance. Second, a multi-branch spatio-temporal interaction network is designed, which captures multi-scale features of sequential data through parallel residual branches with 3*3, 5*5, and 7*7 convolutional kernels. Simultaneously, temporal attention mechanisms are incorporated to identify critical time points, while spatial attention enhances inter-sensor interactions. A cross-branch feature fusion unit is further introduced to improve the overall feature representation capability. Finally, an adaptive multi-loss function fusion strategy is integrated, allowing for dynamic adjustment of loss weights and overall model optimization. Experimental results on three public datasets, WISDM, PAMAP2, and OPPORTUNITY, demonstrate that the proposed unsupervised data augmentation spatio-temporal attention diffusion network (USAD) achieves accuracies of 98.84%, 93.81%, and 80.92% respectively, significantly outperforming existing approaches. Furthermore, practical deployment on embedded devices verifies the efficiency and feasibility of the proposed method.

Problem

• Addresses scarcity of labeled data for rare human activities
• Enhances spatio-temporal feature extraction in activity recognition
• Optimizes model performance for lightweight embedded devices

Innovation

• Unsupervised diffusion model for data augmentation
• Multi-branch spatio-temporal interaction network
• Adaptive multi-loss function fusion strategy