Related papers: Hierarchical Stacking Optimization Using Dirichlet…
This work details a highly efficient implementation of the 3D scale-invariant feature transform (SIFT) algorithm, for the purpose of machine learning from large sets of volumetric medical image data. The primary operations of the 3D SIFT…
Aiming at selecting a small subset of nodes with maximum influence on networks, the Influence Maximization (IM) problem has been extensively studied. Since it is #P-hard to compute the influence spread given a seed set, the state-of-the-art…
Fueled by advances in distributed deep learning (DDL), recent years have witnessed a rapidly growing demand for resource-intensive distributed/parallel computing to process DDL computing jobs. To resolve network communication bottleneck and…
The atomistic structure of the graphene buffer layer on Si-terminated SiC is studied using a modified environment-dependent interatomic potential (EDIP). The investigation of equilibrium state by conjuguate gradients suffers from a complex…
Graph algorithms mainly belong to two categories, topology-driven and data-driven. Data-driven approach maintains a worklist of active nodes, the nodes on which work has to be done. Topology-driven approach sweeps over the entire graph to…
Object categories are typically organized into a multi-granularity taxonomic hierarchy. When classifying categories at different hierarchy levels, traditional uni-modal approaches focus primarily on image features, revealing limitations in…
Readability criteria, such as distance or neighborhood preservation, are often used to optimize node-link representations of graphs to enable the comprehension of the underlying data. With few exceptions, graph drawing algorithms typically…
Achieving fine-grained and structurally sound controllability is a cornerstone of advanced visual generation. Existing part-based frameworks treat user-provided parts as an unordered set and therefore ignore their intrinsic spatial and…
Differentiable vector graphics have enabled powerful gradient-based optimization of vector primitives directly from raster images. However, existing frameworks formulate this as a flat optimization problem, forcing hundreds to thousands of…
In this work, we present a novel approach to process the DIC measurements of multiple biaxial stretching protocols. In particular, we develop a optimization-based approach, which calculates the smoothed nodal displacements using a moving…
Developing effective multimodal fusion approaches has become increasingly essential in many real-world scenarios, such as health care and finance. The key challenge is how to preserve the feature expressiveness in each modality while…
Deep learning (DL) methods have been extensively applied to various image recovery problems, including magnetic resonance imaging (MRI) and computed tomography (CT) reconstruction. Beyond supervised models, other approaches have been…
Deep Learning in Image Registration (DLIR) methods have been tremendously successful in image registration due to their speed and ability to incorporate weak label supervision at training time. However, existing DLIR methods forego many of…
Autonomous operation of service robotics in human-centric scenes remains challenging due to the need for understanding of changing environments and context-aware decision-making. While existing approaches like topological maps offer…
Masked Image Modeling (MIM) is a powerful self-supervised strategy for visual pre-training without the use of labels. MIM applies random crops to input images, processes them with an encoder, and then recovers the masked inputs with a…
In this work we developed a RAFT polymerization model taking into account the main reactions of the experimental RAFT process and implemented that model in dissipative particle dynamics (DPD). With a help of a kinetic model based on the…
Neural solvers based on the divide-and-conquer approach for Vehicle Routing Problems (VRPs) in general, and capacitated VRP (CVRP) in particular, integrates the global partition of an instance with local constructions for each subproblem to…
Tip decomposition is a crucial kernel for mining dense subgraphs in bipartite networks, with applications in spam detection, analysis of affiliation networks etc. It creates a hierarchy of vertex-induced subgraphs with varying densities…
Stacking order in van der Waals materials determines the coupling between atomic layers and is therefore key to the materials' properties. By exploring different stacking orders, many novel physical phenomena have been realized in…
Graph representation learning has become a ubiquitous component in many scenarios, ranging from social network analysis to energy forecasting in smart grids. In several applications, ensuring the fairness of the node (or graph)…