Related papers: Hierarchical Recording Architecture for Three-Dime…
Image registration aims to establish spatial correspondence across pairs, or groups of images, and is a cornerstone of medical image computing and computer-assisted-interventions. Currently, most deep learning-based registration methods…
It is assumed that heat-assisted magnetic recording (HAMR) is the recording technique of the future. For pure hard magnetic grains in high density media with an average diameter of $5$nm and a height of $10$nm the switching probability is…
Recent advancements in deep learning have led to the widespread adoption of artificial intelligence (AI) in applications such as computer vision and natural language processing. As neural networks become deeper and larger, AI modeling…
In domains where computational resources and labeled data are limited, such as in robotics, deep networks with millions of weights might not be the optimal solution. In this paper, we introduce a connectivity scheme for pyramidal…
Contemporary registration devices for 3D visual information, such as LIDARs and various depth cameras, capture data as 3D point clouds. In turn, such clouds are challenging to be processed due to their size and complexity. Existing methods…
Reconstructing visual stimuli from fMRI signals is a central challenge bridging machine learning and neuroscience. Recent diffusion-based methods typically map fMRI activity to a single high-level embedding, using it as fixed guidance…
Registration-based atlas building often poses computational challenges in high-dimensional image spaces. In this paper, we introduce a novel hybrid atlas building algorithm that fast estimates atlas from large-scale image datasets with much…
Digital elevation modeling of planetary surfaces is essential for studying past and ongoing geological processes. Wide-angle imagery acquired during spacecraft descent promises to offer a low-cost option for high-resolution terrain…
Memory networks are neural networks with an explicit memory component that can be both read and written to by the network. The memory is often addressed in a soft way using a softmax function, making end-to-end training with backpropagation…
One viable solution for continuous reduction in energy-per-operation is to rethink functionality to cope with uncertainty by adopting computational approaches that are inherently robust to uncertainty. It requires a novel look at data…
Obtaining high-resolution (HR) segmentations from coarse annotations is a pervasive challenge in computer vision. Applications include inferring pixel-level segmentations from token-level labels in vision transformers, upsampling coarse…
A head-mounted display (HMD) using holography technology (holo-HMD) is expected to be the next generation of HMDs capable of reducing three-dimensional sickness. In HMDs, it is important to generate images that respond to head movement in…
The rise of deep learning technologies has quickly advanced many fields, including that of generative music systems. There exist a number of systems that allow for the generation of good sounding short snippets, yet, these generated…
Three-dimensional (3D) nanomagnetism is a rapidly developing field within magnetic materials research, where exploiting the third dimension unlocks opportunities for innovative applications in areas such as sensing, data storage, and…
Multiresolution Matrix Factorization (MMF) was recently introduced as an alternative to the dominant low-rank paradigm in order to capture structure in matrices at multiple different scales. Using ideas from multiresolution analysis (MRA),…
Speech recognition is a critical task in the field of artificial intelligence and has witnessed remarkable advancements thanks to large and complex neural networks, whose training process typically requires massive amounts of labeled data…
Deep-learning based noise reduction algorithms have proven their success especially for non-stationary noises, which makes it desirable to also use them for embedded devices like hearing aids (HAs). This, however, is currently not possible…
Polarization and wavelength multiplexing are the two most widely employed techniques to improve the capacity in the metasurfaces. Existing works have pushed each technique to its individual limits. For example, the polarization multiplexing…
We present SuperNormal, a fast, high-fidelity approach to multi-view 3D reconstruction using surface normal maps. With a few minutes, SuperNormal produces detailed surfaces on par with 3D scanners. We harness volume rendering to optimize a…
Hierarchical Temporal Memory is a new machine learning algorithm intended to mimic the working principle of neocortex, part of the human brain, which is responsible for learning, classification, and making predictions. Although many works…