Concept

Limited liability company

Related publications (40)

Composite Relationship Fields with Transformers for Scene Graph Generation

Alexandre Massoud Alahi, David Mizrahi, George Adaimi

Scene graph generation (SGG) methods extract relationships between objects. While most methods focus on improving top-down approaches, which build a scene graph based on detected objects from an off-the-shelf object detector, there is a limited amount of w ...

2023

PAE: Towards More Efficient and BBB-Secure AE from a Single Public Permutation

Ritam Bhaumik

Four recent trends have emerged in the evolution of authenticated encryption schemes: (1) Regarding simplicity, the adoption of public permutations as primitives allows for sparing a key schedule and the need for storing round keys; (2) using the sums of p ...

Springer2023

Recycling of Load-Bearing 3D Printable Double Network Granular Hydrogels

Esther Amstad, Matteo Hirsch, Alvaro Lino Boris Charlet, Sanjay Phileas Schreiber

Sustainable materials, such as recyclable polymers, become increasingly important as they are often environmentally friendlier than their one-time-use counterparts. In parallel, the trend toward more customized products demands for fast prototyping methods ...

WILEY-V C H VERLAG GMBH2022

A Novel Method to Quantify Self-Healing Capabilities of Fiber-Reinforced Polymers

Véronique Michaud, Amaël Maximilien Cohades, Robin Samuel Trigueira, Cecilia Scazzoli

The present work investigates a novel and practical method to evaluate the healing efficiency of carbon-reinforced polymer composites. The method should be representative of damage occurring during the lifetime of a composite part, should tend to damage th ...

FRONTIERS MEDIA SA2022

Cross Modal Focal Loss for RGBD Face Anti-Spoofing

Sébastien Marcel

Automatic methods for detecting presentation attacks are essential to ensure the reliable use of facial recognition technology. Most of the methods available in the litera- ture for presentation attack detection (PAD) fails in gen- eralizing to unseen atta ...

IEEE2021

Deep Domain Adaptation in Earth Observation

Devis Tuia, Benjamin Alexander Kellenberger, Nicolas Courty

When applied to new datasets, acquired at different time moments, with different sensors or under different acquisition conditions, deep learning models might fail spectacularly. This is because they have learned from the data distribution observed during ...

Wiley2021

Bioluminescent-based imaging and quantification of glucose uptake in vivo

Riccardo Sinisi, Elena Goun, Pavlo Khodakivskyi, Arkadiy Bazhin, Aleksey Yevtodiyenko, Tamara Maric, Georgy Mikhaylov

Glucose is a major source of energy for most living organisms, and its aberrant uptake is linked to many pathological conditions. However, our understanding of disease-associated glucose flux is limited owing to the lack of robust tools. To date, positron- ...

NATURE PUBLISHING GROUP2019

Exploiting semi-supervised training through a dropout regularization in end-to-end speech recognition

Petr Motlicek, Subhadeep Dey

In this paper, we explore various approaches for semi- supervised learning in an end-to-end automatic speech recog- nition (ASR) framework. The first step in our approach in- volves training a seed model on the limited amount of labelled data. Additional u ...

2019

Torn between international competition and municipal claims: Analysing key influence factors on municipal utilities’ business strategies in the German and Swiss energy transition

Susan Marie Mühlemeier

After the nuclear accident in Fukushima, amongst others Germany and Switzerland decided to accelerate the sustainability transition of their energy systems not only by expanding the share of renewables actively but also by quitting nuclear power. Regarding ...

2017

Rusty dinosaurs and the surviving species in the new energy system? Analysing urban utilities in the German and Swiss energy transition

Claudia Rebeca Binder Signer, Susan Marie Mühlemeier

2017

Graph Chatbot

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.