activity
20172022
most citedHow hard can it be? Estimating the difficulty of visual search in an image

6 citations · 20 across the 17 of their papers we have counts for

collaborators

46 papers

cs.CV2022

Discriminability-enforcing loss to improve representation learning

Florinel-Alin Croitoru, Diana-Nicoleta Grigore, Radu Tudor Ionescu

During the training process, deep neural networks implicitly learn to represent the input data samples through a hierarchy of features, where the size of the hierarchy is determine…

cs.CV20214 cited

A realistic approach to generate masked faces applied on two novel masked face recognition data sets

Tudor Mare, Georgian Duta, Mariana-Iuliana Georgescu +4

The COVID-19 pandemic raises the problem of adapting face recognition systems to the new reality, where people may wear surgical masks to cover their noses and mouths. Traditional…

cs.CV2021

Contextual Convolutional Neural Networks

Ionut Cosmin Duta, Mariana Iuliana Georgescu, Radu Tudor Ionescu

We propose contextual convolution (CoConv) for visual recognition. CoConv is a direct replacement of the standard convolution, which is the core component of convolutional neural n…

cs.CR2021

Improving the Authentication with Built-in Camera Protocol Using Built-in Motion Sensors: A Deep Learning Solution

Cezara Benegui, Radu Tudor Ionescu

We propose an enhanced version of the Authentication with Built-in Camera (ABC) protocol by employing a deep learning solution based on built-in motion sensors. The standard ABC pr…

cs.CL2021

SaRoCo: Detecting Satire in a Novel Romanian Corpus of News Articles

Ana-Cristina Rogoz, Mihaela Gaman, Radu Tudor Ionescu

In this work, we introduce a corpus for satire detection in Romanian news. We gathered 55,608 public news articles from multiple real and satirical news sources, composing one of t…

cs.CL2021

FreSaDa: A French Satire Data Set for Cross-Domain Satire Detection

Radu Tudor Ionescu, Adrian Gabriel Chifu

In this paper, we introduce FreSaDa, a French Satire Data Set, which is composed of 11,570 articles from the news domain. In order to avoid reporting unreasonably high accuracy rat…