Related papers: Vertex and front-tracking methods for the modeling…
Large foundation models (FMs) are transforming Earth science by integrating heterogeneous multimodal data, such as multi-platform imagery, gridded reanalysis data, diverse geophysical and geochemical observations, and domain-specific text,…
Facial micro-expression recognition (MER) is a challenging task, due to the transience, subtlety, and dynamics of micro-expressions (MEs). Most existing methods resort to hand-crafted features or deep networks, in which the former often…
FFT-based solvers introduced in the 1990s for the numerical homogenization of heterogeneous elastic materials have been extended to a wide range of physical properties. In parallel, alternative algorithms and modified discrete Green…
Movement is fundamental to life, shaping population dynamics, biodiversity patterns, and ecosystem structure. Recent advances in tracking technology have enabled fundamental questions about movement to be tackled, leading to the development…
In this work, we present a multiscale kinetic framework for consensus-based image segmentation. By interpreting an image as a system of interacting particles, each pixel is characterised by its spatial position and an internal feature…
The quantitative description of marine systems is constrained by a major issue of scale separation: most marine biochemical processes occur at sub-centimeter scales, while the contribution to the Earth's biogeochemical cycles is expressed…
Optical flow is a useful input for various applications, including 3D reconstruction, pose estimation, tracking, and structure-from-motion. Despite its utility, the field of dense long-term tracking, especially over wide baselines, has not…
Heterogeneous interfaces are central to many energy-related applications in the nanoscale. From the first-principles electronic structure perspective, one of the outstanding problems is accurately and efficiently calculating how the…
In affine formation control problems, the construction of the framework with universal rigidity and affine localizability is a critical prerequisite, but it has not yet been well addressed, especially when additional agents join the…
Understanding and predicting microstructure evolution is fundamental to materials science, as it governs the resulting properties and performance of materials. Traditional simulation methods, such as phase-field models, offer high-fidelity…
The detection of traversable regions on staircases and the physical modeling constitutes pivotal aspects of the mobility of legged robots. This paper presents an onboard framework tailored to the detection of traversable regions and the…
Surface meshes are widely used shape representations and capture finer geometry data than point clouds or volumetric grids, but are challenging to apply CNNs directly due to their non-Euclidean structure. We use parallel frames on surface…
We introduce a stochastic model of diffeomorphisms, whose action on a variety of data types descends to stochastic evolution of shapes, images and landmarks. The stochasticity is introduced in the vector field which transports the data in…
Tip-driven growth processes underlie the development of many plants. To date, tip-driven growth processes have been modelled as an elongating path or series of segments without taking into account lateral expansion during elongation.…
In this paper we focus on the finite-dimensional approximation of quasi-static evolutions of critical points of the phase-field model of brittle fracture. In a space discretized setting, we first discuss an alternating minimization scheme…
Fine-tuning pre-trained foundation models has gained significant popularity in various research fields. Existing methods for fine-tuning can be roughly divided into two categories, namely Parameter-Efficient Fine-Tuning and High-Performance…
Many models in natural and social sciences are comprised of sets of inter-acting entities whose intensity of interaction decreases with distance. This often leads to structures of interest in these models composed of dense packs of…
With rapid urbanization in the modern era, traffic signals from various sensors have been playing a significant role in monitoring the states of cities, which provides a strong foundation in ensuring safe travel, reducing traffic congestion…
Parameter-efficient fine-tuning (PEFT) has attracted significant attention due to the growth of pre-trained model sizes and the need to fine-tune (FT) them for superior downstream performance. Despite a surge in new PEFT methods, a…
Recent advancements in graph neural networks (GNNs) and heterogeneous GNNs (HGNNs) have advanced node embeddings and relationship learning for various tasks. However, existing methods often rely on domain-specific predefined meta-paths,…