Related papers: CASCADE: Cross-scale Advective Super-resolution wi…
Recent researches have shown that deep forest ensemble achieves a considerable increase in classification accuracy compared with the general ensemble learning methods, especially when the training set is small. In this paper, we take…
Intelligent transportation systems (ITS) play a pivotal role in modern infrastructure but face security risks due to the broadcast-based nature of the in-vehicle Controller Area Network (CAN) buses. While numerous machine learning models…
Domain adaptation is critical for success in new, unseen environments. Adversarial adaptation models applied in feature spaces discover domain invariant representations, but are difficult to visualize and sometimes fail to capture…
In recent years, videos and images in 720p (HD), 1080p (FHD) and 4K (UHD) resolution have become more popular for display devices such as TVs, mobile phones and VR. However, these high resolution images cannot achieve the expected visual…
Climate models are essential to understand and project climate change, yet long-standing biases and uncertainties in their projections remain. This is largely associated with the representation of subgrid-scale processes, particularly…
Gaussian Splatting and its dynamic extensions are effective for reconstructing 3D scenes from 2D images when there is significant camera movement to facilitate motion parallax and when scene objects remain relatively static. However, in…
Atmospheric simulations for urban cities can be computationally intensive because of the need for high spatial resolution, such as a few meters, to accurately represent buildings and streets. Deep learning has recently gained attention…
Spatial fields in the Earth and environmental sciences are often available at multiple scales or resolutions. While coarse-scale data (e.g., from global circulation models) are often abundant, they lack the local detail provided by…
High-quality digital terrain models derived from airborne laser scanning (ALS) data are essential for a wide range of geospatial analyses, and their generation typically relies on robust ground filtering (GF) to separate point clouds across…
The Picard iteration for the Boussinesq model of natural convection can be an attractive solver because it stably decouples the fluid equations from the temperature equation (for contrast, the Newton iteration does not stably decouple).…
We construct incompressible velocity fields that exhibit faster than exponential dissipation for particular solutions to the advection-diffusion equation on $\mathbb{T}^d$. In 2D, we construct a velocity field in $L^\infty_{t,x}$ and…
Motion prediction is an important aspect for Autonomous Driving (AD) and Advance Driver Assistance Systems (ADAS). Current state-of-the-art motion prediction methods rely on High Definition (HD) maps for capturing the surrounding context of…
Many real-world processes have complex tail dependence structures that cannot be characterized using classical Gaussian processes. More flexible spatial extremes models exhibit appealing extremal dependence properties but are often…
We show that cascaded diffusion models are capable of generating high fidelity images on the class-conditional ImageNet generation benchmark, without any assistance from auxiliary image classifiers to boost sample quality. A cascaded…
Recent breakthrough results in compressed sensing (CS) have established that many high dimensional objects can be accurately recovered from a relatively small number of non- adaptive linear projection observations, provided that the objects…
Climate models often require post-processing in order to make accurate estimates of local climate risk. The most common post-processing applied is bias-correction and spatial resolution enhancement. However, the statistical methods…
Realistic reconstruction of dynamic 4D scenes from monocular videos is essential for understanding the physical world. Despite recent progress in neural rendering, existing methods often struggle to recover accurate 3D geometry and…
Temporal modeling in complex systems requires capturing dependencies across multiple time scales while managing inherent uncertainties. We propose HierCVAE, a novel architecture that integrates hierarchical attention mechanisms with…
Fixed representational capacity is a fundamental constraint in continual learning: practitioners must guess an appropriate model width before training, without knowing how many distinct concepts the data contains. We propose LACE…
Obtaining high-resolution maps of precipitation data can provide key insights to stakeholders to assess a sustainable access to water resources at urban scale. Mapping a nonstationary, sparse process such as precipitation at very high…