A cross-modal pre-training framework with video data for improving performance and generalization of distributed acoustic sensing

Fiber-optic distributed acoustic sensing (DAS) has emerged as a critical Internet-of-Things (IoT) sensing technology with broad industrial applications. However, the two-dimensional spatial-temporal morphology of DAS signals presents analytical challenges where conventional methods prove suboptimal, while being well-suited for deep learning approaches. Although our previous work, DAS Masked Autoencoder (DAS-MAE), established state-of-the-art performance and generalization without labels, it is not satisfactory in frequency analysis in temporal-dominated DAS data. Moreover, the limitation of effective training data fails to address the substantial data requirements inherent to Transformer architectures in DAS-MAE. To overcome these limitations, we present an enhanced framework incorporating short-time Fourier transform (STFT) for explicit temporal-frequency feature extraction and pioneering video-to-DAS cross-modal pre-training to mitigate data constraints. This approach learns high-level representations (e.g., event classification) through label-free reconstruction tasks. Experimental results demonstrate transformative improvements: 0.1% error rate in few-shot classification (90.9% relative improvement over DAS-MAE) and 4.7% recognition error in external damage prevention applications (75.4% improvement over from-scratch training). As the first work to pioneer video-to-DAS cross-modal pre-training, available training resources are expanded by bridging computer vision and distributed sensing areas. The enhanced performance and generalization facilitate DAS deployment across diverse industrial scenarios while advancing cross-modal representation learning for industrial IoT sensing.

DAS-MAE: A self-supervised pre-training framework for universal and high-performance representation learning of distributed fiber-optic acoustic sensing

Distributed fiber-optic acoustic sensing (DAS) has emerged as a transformative approach for distributed vibration measurement with high spatial resolution and long measurement range while maintaining cost-efficiency. However, the two-dimensional spatial-temporal DAS signals present analytical challenges. The abstract signal morphology lacking intuitive physical correspondence complicates human interpretation, and its unique spatial-temporal coupling renders conventional image processing methods suboptimal. This study investigates spatial-temporal characteristics and proposes a self-supervised pre-training framework that learns signals' representations through a mask-reconstruction task. This framework is named the DAS Masked AutoEncoder (DAS-MAE). The DAS-MAE learns high-level representations (e.g., event class) without using labels. It achieves up to 1% error and 64.5% relative improvement (RI) over the semi-supervised baseline in few-shot classification tasks. In a practical external damage prevention application, DAS-MAE attains a 5.0% recognition error, marking a 75.7% RI over supervised training from scratch. These results demonstrate the high-performance and universal representations learned by the DAS-MAE framework, highlighting its potential as a foundation model for analyzing massive unlabeled DAS signals.

Point2Quad: Generating Quad Meshes from Point Clouds via Face Prediction

Quad meshes are essential in geometric modeling and computational mechanics. Although learning-based methods for triangle mesh demonstrate considerable advancements, quad mesh generation remains less explored due to the challenge of ensuring coplanarity, convexity, and quad-only meshes. In this paper, we present Point2Quad, the first learning-based method for quad-only mesh generation from point clouds. The key idea is learning to identify quad mesh with fused pointwise and facewise features. Specifically, Point2Quad begins with a k-NN-based candidate generation considering the coplanarity and squareness. Then, two encoders are followed to extract geometric and topological features that address the challenge of quad-related constraints, especially by combining in-depth quadrilaterals-specific characteristics. Subsequently, the extracted features are fused to train the classifier with a designed compound loss. The final results are derived after the refinement by a quad-specific post-processing. Extensive experiments on both clear and noise data demonstrate the effectiveness and superiority of Point2Quad, compared to baseline methods under comprehensive metrics.