Test-time adaptation is a promising research direction that allows the s...
In this work, we improve the generative replay in a continual learning
s...
In this work, we investigate exemplar-free class incremental learning (C...
Currently, over half of the computing power at CERN GRID is used to run ...
Generative diffusion models, including Stable Diffusion and Midjourney, ...
Deep neural networks are widely known for their remarkable effectiveness...
Generating faithful visualizations of human faces requires capturing bot...
Diffusion models have achieved remarkable success in generating high-qua...
Implicit Neural Representations (INRs) are nowadays used to represent
mu...
The effectiveness of digital treatments can be measured by requiring pat...
We introduce a joint diffusion model that simultaneously learns meaningf...
Recent advances in visual representation learning allowed to build an
ab...
Hierarchical decomposition of control is unavoidable in large dynamical
...
Implicit neural representations (INRs) are a rapidly growing research fi...
We introduce a new method for internal replay that modulates the frequen...
Generative Adversarial Networks (GANs) are powerful models able to synth...
We introduce a new training paradigm that enforces interval constraints ...
Diffusion-based Deep Generative Models (DDGMs) offer state-of-the-art
pe...
Artificial Intelligence in higher education opens new possibilities for
...
Objective. This work investigates the use of deep convolutional neural
n...
Predicting fetal weight at birth is an important aspect of perinatal car...
Contemporary deep neural networks offer state-of-the-art results when ap...
A critical step in the fight against COVID-19, which continues to have a...
We introduce a neural network architecture that logarithmically reduces ...
We extend neural 3D representations to allow for intuitive and interpret...
Gaussian Processes (GPs) have been widely used in machine learning to mo...
The paper presents a deep neural network-based method for global and loc...
Recently introduced implicit field representations offer an effective wa...
In this work, we propose a method for large-scale topological localizati...
Matrix decompositions are ubiquitous in machine learning, including
appl...
Catastrophic forgetting of previously learned knowledge while learning n...
Designing a 3D game scene is a tedious task that often requires a substa...
In this paper, we propose an end-to-end multi-task neural network called...
We propose a new method for unsupervised continual knowledge consolidati...
Recently introduced self-supervised methods for image representation lea...
The problem of reducing processing time of large deep learning models is...
Convolutional neural networks (CNNs) are used in many areas of computer
...
We introduce a discriminative multimodal descriptor based on a pair of s...
The generation of plausible and controllable 3D human motion animations ...
This paper addresses the problem of media retrieval using a multimodal q...
Recently proposed 3D object reconstruction methods represent a mesh with...
Scanning real-life scenes with modern registration devices typically giv...
Predicting future states or actions of a given system remains a fundamen...
An estimated 15 million babies are born too early every year. Approximat...
In this work, we present HyperFlow - a novel generative model that lever...
In this work, we propose a novel end-to-end sinkhorn autoencoder with no...
Deep neural networks (DNNs) show promise in breast cancer screening, but...
In this paper, we present a framework for computing dense keypoint
corre...
Healing process assessment of the Achilles tendon is usually a complex
p...
Achilles tendon rupture is a debilitating injury, which is typically tre...