Abstract Visual odometry (VO) is fundamental to autonomous navigation, robotics, and augmented reality. While self-supervised learning has eliminated the need for expensive ground-truth labels in monocular VO, dynamic objects and occlusions that violate the static scene assumption lead to erroneous pose estimates. Existing uncertainty-based methods filter unreliable regions but rely solely on single-frame information, neglecting temporal consistency across consecutive frames. We present Combined Projected Uncertainty (CoProU), a principled probabilistic formulation that propagates and fuses uncertainties across temporal frames. Our key insight is that robust uncertainty estimation requires combining target frame uncertainty with projected uncertainty from reference frames, enabling effective identification of dynamic regions and temporal inconsistencies. We demonstrate CoProU’s versatility through two complementary frameworks. CoProU-VO-2F employs a decoupled architecture with CNN-based pose encoder and vision transformer-based depth encoder for two-frame visual odometry. CoProU-VO-MF extends our approach to multi-frame scenarios using a unified transformer architecture with coupled encoders that produce shared representations for ego-motion and geometry estimation. This demonstrates that CoProU, though originally formulated for frame pairs, generalizes naturally to multi-frame settings through pairwise application. Comprehensive experiments validate our contributions. CoProU-VO-2F achieves substantial improvements over state-of-the-art two-frame methods, reducing ATE by up to 63% on KITTI and 33% on nuScenes. CoProU-VO-MF achieves 45% lower average ATE across KITTI, nuScenes, and Waymo compared to the large-scale pretrained VGGT baseline. Extensive ablation studies confirm the effectiveness of temporal uncertainty propagation and CoProU’s adaptability across different architectural paradigms. Please check out our Project Page .

With the widespread adoption of wearable devices, human activity recognition (HAR), which is an essential branch of multivariate time series classification (MTSC), has been broadly applied in areas such as intelligent health monitoring, smart homes, and sports training. Traditional time series processing methods focus on time-domain features and often neglect frequency-domain characteristics; however, much of the critical information related to human activities is usually reflected in the frequency components of signals. To address this issue, we propose a Fourier transform convolution fusion module for extracting frequency-domain features and integrating them with time-domain features. Based on this module, we further propose an innovative Fourier transform convolution network (FTCNet). FTC-Net efficiently integrates time-domain and frequencydomain features by combining the Fourier transform convolution fusion module with an efficient channel attention block (ECA block), which enhances the model's ability to extract key features. The experimental results show that FTC-Net achieved excellent classification performance across 11 HAR-related datasets, with an average accuracy of $87.85 \%$, significantly outperforming current mainstream models. The results of ablation studies also demonstrate the positive impact of frequency-domain features on model performance. FTC-Net offers a new solution for complex human activity recognition tasks and opens new research directions for integrating time-domain and frequency-domain features.

A wireless body area network (WBAN) is a crucial technology for implementing intelligent health monitoring. Traditional WBANs focus on the monitoring and classification of single physiological signals, which cannot meet the comprehensive requirements for monitoring human health and behavior. This paper proposes a local feature channel fusion convolutional neural network (CNN) model that can monitor and analyze multiple physiological signals collected by WBANs and can be used for disease identification and human activity recognition. The model employs convolution kernels to perform convolution operations on each channel, extracting local features of each channel and then performing channel fusion convolution operations to effectively integrate information between different channels. Additionally, the model incorporates an attention mechanism to dynamically adjust feature weights, highlight important features, and suppress redundant information. Experiments conducted on 11 WBAN-related datasets from the UEA database demonstrate that the proposed model achieves optimal classification performance.