19 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Corporación Universitaria de Colombia IdeasCO6 papers
- Integrated Detector Electronics AS (Norway)NO5 papers
- American UniversityUS2 papers
- Computer Vision Center2 papers
- Graz University of TechnologyAT2 papers
- Universitat Autònoma de BarcelonaES2 papers
- Centre National de la Recherche ScientifiqueFR1 paper
- Chinese Academy of SciencesCN1 paper
- École Normale Supérieure de LyonFR1 paper
- Gdańsk University of TechnologyPL1 paper
- George Washington UniversityUS1 paper
- Institut de Physique ThéoriqueFR1 paper
9 papers
Beyond Blur: A Fluid Perspective on Generative Diffusion Models
Grzegorz Gruszczynski, Jakub Meixner, Michal Jan Wlodarczyk +1
We propose a novel PDE-driven corruption process for generative image synthesis based on advection-diffusion processes which generalizes existing PDE-based approaches. Our forward…
Resurrecting Old Classes with New Data for Exemplar-Free Continual Learning
Dipam Goswami, Albin Soutif--Cormerais, Yuyang Liu +3
Continual learning methods are known to suffer from catastrophic forgetting, a phenomenon that is particularly hard to counter for methods that do not store exemplars of previous t…
Divide and not forget: Ensemble of selectively trained experts in Continual Learning
Grzegorz Rypeść, Sebastian Cygert, Valeriya Khan +3
Class-incremental learning is becoming more popular as it helps models widen their applicability while not forgetting what they already know. A trend in this area is to use a mixtu…
Evaluating Augmented Reality Communication: How Can We Teach Procedural Skill in AR?
Manuel Rebol, Krzysztof Pietroszek, Neal Sikka +5
Augmented reality (AR) has great potential for use in healthcare applications, especially remote medical training and supervision. In this paper, we analyze the usage of an AR comm…
Beyond Grids: Exploring Elastic Input Sampling for Vision Transformers
Adam Pardyl, Grzegorz Kurzejamski, Jan Olszewski +2
Vision transformers have excelled in various computer vision tasks but mostly rely on rigid input sampling using a fixed-size grid of patches. It limits their applicability in real…
A parameterized approximation scheme for the 2D-Knapsack problem with wide items
Michal Pilipczuk, Mathieu Mari, Timothe Picavet
We study a natural geometric variant of the classic Knapsack problem called 2D-Knapsack: we are given a set of axis-parallel rectangles and a rectangular bounding box, and the goal…
Contradicting Motivations in Civic Tech Software Development: Analysis of a Grassroots Project
Antti Knutas, Dominik Siemon, Natasha Tylosky +1
Grassroots civic tech, or software for social change, is an emerging practice where people create and then use software to create positive change in their community. In this interp…
Real-time Gesture Animation Generation from Speech for Virtual Human Interaction
Manuel Rebol, Christian Gütl, Krzysztof Pietroszek
We propose a real-time system for synthesizing gestures directly from speech. Our data-driven approach is based on Generative Adversarial Neural Networks to model the speech-gestur…
The unknotted strands of life: knots are very rare in RNA structures
Cristian Micheletti, Marco Di Stefano, Henri Orland
The ongoing effort to detect and characterize physical entanglement in biopolymers has so far established that knots are present in many globular proteins and also abound in viral…