Related papers: Forecasting as Rendering: A 2D Gaussian Splatting …
3D Gaussian Splatting (3DGS) has enabled high-fidelity virtualization with fast rendering and optimization for novel view synthesis. On the other hand, triangle mesh models still remain a popular choice for surface reconstruction but suffer…
Precipitation forecasting relies on heterogeneous data. Weather radar is accurate, but coverage is geographically limited and costly to maintain. Weather stations provide accurate but sparse point measurements, while satellites offer dense,…
3D Gaussian splatting (3DGS) has recently emerged as an alternative representation that leverages a 3D Gaussian-based representation and introduces an approximated volumetric rendering, achieving very fast rendering speed and promising…
Synthetic time series are essential tools for data augmentation, stress testing, and algorithmic prototyping in quantitative finance. However, in cryptocurrency markets, characterized by 24/7 trading, extreme volatility, and rapid regime…
While machine learning has witnessed significant advancements, the emphasis has largely been on data acquisition and model creation. However, achieving a comprehensive assessment of machine learning solutions in real-world settings…
With the growing availability of multi-domain time series data, there is an increasing demand for general forecasting models pre-trained on multi-source datasets to support diverse downstream prediction scenarios. Existing time series…
This paper introduces a novel spatiotemporal feature representation model designed to address the limitations of traditional methods in multidimensional time series (MTS) analysis. The proposed approach converts MTS into one-dimensional…
We introduce a temporal feature encoding architecture called Time Series Representation Model (TSRM) for multivariate time series forecasting and imputation. The architecture is structured around CNN-based representation layers, each…
Unsupervised/self-supervised time series representation learning is a challenging problem because of its complex dynamics and sparse annotations. Existing works mainly adopt the framework of contrastive learning with the time-based…
Irregularly sampled multivariate event streams remain a stubbornly difficult modality for generative modeling: tokenization-based approaches break down when inter-event intervals vary by orders of magnitude, and neural temporal point…
Recent advancements in high-fidelity dynamic scene reconstruction have leveraged dynamic 3D Gaussians and 4D Gaussian Splatting for realistic scene representation. However, to make these methods viable for real-time applications such as…
This paper shows that time series forecasting Transformer (TSFT) suffers from severe over-fitting problem caused by improper initialization method of unknown decoder inputs, esp. when handling non-stationary time series. Based on this…
Time-evolving traffic flow forecasting are playing a vital role in intelligent transportation systems and smart cities. However, the dynamic traffic flow forecasting is a highly nonlinear problem with complex temporal-spatial dependencies.…
Temporal Graph Clustering (TGC) is a new task with little attention, focusing on node clustering in temporal graphs. Compared with existing static graph clustering, it can find the balance between time requirement and space requirement…
Existing offline feed-forward methods for joint scene understanding and reconstruction on long image streams often repeatedly perform global computation over an ever-growing set of past observations, causing runtime and GPU memory to…
Accurate time series forecasting is crucial for optimizing resource allocation, industrial production, and urban management, particularly with the growth of cyber-physical and IoT systems. However, limited training sample availability in…
While novel view synthesis (NVS) for dynamic scenes has seen significant progress, reconstructing temporally consistent geometric surfaces remains a challenge. Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) offer powerful…
3D Gaussian Splatting (3DGS) has emerged as an efficient and high-fidelity paradigm for novel view synthesis. To adapt 3DGS for dynamic content, deformable 3DGS incorporates temporally deformable primitives with learnable latent embeddings…
Time-series classification (TSC) has advanced significantly with deep learning, yet most models rely solely on raw numerical inputs, overlooking alternative representations. While texture-based encodings such as Gramian Angular Fields (GAF)…
3D Gaussian Splatting (3DGS) has emerged as a leading neural rendering technique for high-fidelity view synthesis, prompting the development of dedicated 3DGS accelerators for resource-constrained platforms. The conventional decoupled…