Search Results for author: Radu Tudor Ionescu

Found 61 papers, 20 papers with code

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

1 code implementation3 Sep 2021 Tudor Mare, Georgian Duta, Mariana-Iuliana Georgescu, Adrian Sandru, Bogdan Alexe, Marius Popescu, Radu Tudor Ionescu

We propose a method for enhancing data sets containing faces without masks by creating synthetic masks and overlaying them on faces in the original images.


Contextual Convolutional Neural Networks

1 code implementation17 Aug 2021 Ionut Cosmin Duta, Mariana Iuliana Georgescu, Radu Tudor Ionescu

On the one hand, we integrate CoConv in the widely-used residual networks and show improved recognition performance over baselines on the core tasks and benchmarks for visual recognition, namely image classification on the ImageNet data set and object detection on the MS COCO data set.

Image Classification Object Detection

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

no code implementations22 Jul 2021 Cezara Benegui, Radu Tudor Ionescu

Our change to the ABC protocol results in a multi-modal protocol that lowers the false acceptance rate for the attack proposed in our previous work to a percentage as low as 0. 07%.

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

1 code implementation10 Apr 2021 Radu Tudor Ionescu, Adrian Gabriel Chifu

We employ two classification methods as baselines for our new data set, one based on low-level features (character n-grams) and one based on high-level features (average of CamemBERT word embeddings).

Satire Detection Unsupervised Domain Adaptation +1

Clustering Word Embeddings with Self-Organizing Maps. Application on LaRoSeDa - A Large Romanian Sentiment Data Set

no code implementations EACL 2021 Anca Tache, Gaman Mihaela, Radu Tudor Ionescu

Romanian is one of the understudied languages in computational linguistics, with few resources available for the development of natural language processing tools.

Sentiment Analysis Text Categorization +1

Self-paced ensemble learning for speech and audio classification

no code implementations22 Mar 2021 Nicolae-Catalin Ristea, Radu Tudor Ionescu

Instead of just combining the models, we propose a self-paced ensemble learning scheme in which models learn from each other over several iterations.

Audio Classification Classification +2

Unsupervised Medical Image Alignment with Curriculum Learning

no code implementations20 Feb 2021 Mihail Burduja, Radu Tudor Ionescu

To the best of our knowledge, we are the first to attempt to improve performance by training medical image registration models using curriculum learning, starting from an easy training setup in the first training stages, and gradually increasing the complexity of the setup.

Curriculum Learning Image Registration +1

UnibucKernel: Geolocating Swiss German Jodels Using Ensemble Learning

no code implementations18 Feb 2021 Mihaela Gaman, Sebastian Cojocariu, Radu Tudor Ionescu

In this work, we describe our approach addressing the Social Media Variety Geolocation task featured in the 2021 VarDial Evaluation Campaign.

Dialect Identification Ensemble Learning

Curriculum Learning: A Survey

no code implementations25 Jan 2021 Petru Soviany, Radu Tudor Ionescu, Paolo Rota, Nicu Sebe

Training machine learning models in a meaningful order, from the easy samples to the hard ones, using curriculum learning can provide performance improvements over the standard training approach based on random data shuffling, without any additional computational costs.

Curriculum Learning

Clustering Word Embeddings with Self-Organizing Maps. Application on LaRoSeDa -- A Large Romanian Sentiment Data Set

1 code implementation11 Jan 2021 Anca Maria Tache, Mihaela Gaman, Radu Tudor Ionescu

Romanian is one of the understudied languages in computational linguistics, with few resources available for the development of natural language processing tools.

Sentiment Analysis Text Categorization +1

Anomaly Detection in Video via Self-Supervised and Multi-Task Learning

1 code implementation CVPR 2021 Mariana-Iuliana Georgescu, Antonio Barbalau, Radu Tudor Ionescu, Fahad Shahbaz Khan, Marius Popescu, Mubarak Shah

To the best of our knowledge, we are the first to approach anomalous event detection in video as a multi-task learning problem, integrating multiple self-supervised and knowledge distillation proxy tasks in a single architecture.

Anomaly Detection Event Detection +3

Black-Box Ripper: Copying black-box models using generative evolutionary algorithms

1 code implementation NeurIPS 2020 Antonio Barbalau, Adrian Cosma, Radu Tudor Ionescu, Marius Popescu

To generate useful data samples for training the student, our framework (i) learns to generate images on a proxy data set (with images and classes different from those used to train the black-box) and (ii) applies an evolutionary strategy to make sure that each generated data sample exhibits a high response for a specific class when given as input to the black box.

Combining Deep Learning and String Kernels for the Localization of Swiss German Tweets

no code implementations7 Oct 2020 Mihaela Gaman, Radu Tudor Ionescu

From simple models for regression, such as Support Vector Regression, to deep neural networks, such as Long Short-Term Memory networks and character-level convolutional neural networks, and, finally, to ensemble models based on meta-learners, such as XGBoost, our interest is focused on approaching the problem from a few different perspectives, in an attempt to minimize the prediction error.

Dialect Identification

SuPEr-SAM: Using the Supervision Signal from a Pose Estimator to Train a Spatial Attention Module for Personal Protective Equipment Recognition

no code implementations25 Sep 2020 Adrian Sandru, Georgian-Emilian Duta, Mariana-Iuliana Georgescu, Radu Tudor Ionescu

Typical approaches for PPE detection based on deep learning are (i) to train an object detector for items such as those listed above or (ii) to train a person detector and a classifier that takes the bounding boxes predicted by the detector and discriminates between people wearing and people not wearing the corresponding PPE items.

Adversarial Attacks on Deep Learning Systems for User Identification based on Motion Sensors

no code implementations2 Sep 2020 Cezara Benegui, Radu Tudor Ionescu

In this study, we focus on deep learning methods for explicit authentication based on motion sensor signals.

Face Recognition

To augment or not to augment? Data augmentation in user identification based on motion sensors

no code implementations1 Sep 2020 Cezara Benegui, Radu Tudor Ionescu

In order to prevent some of the possible attacks, these explicit authentication systems can be enhanced by considering a two-factor authentication scheme, in which the second factor is an implicit authentication system based on analyzing motion sensor data captured by accelerometers or gyroscopes.

Data Augmentation Face Recognition

A Background-Agnostic Framework with Adversarial Training for Abnormal Event Detection in Video

1 code implementation27 Aug 2020 Mariana-Iuliana Georgescu, Radu Tudor Ionescu, Fahad Shahbaz Khan, Marius Popescu, Mubarak Shah

Following the standard formulation of abnormal event detection as outlier detection, we propose a background-agnostic framework that learns from training videos containing only normal events.

Abnormal Event Detection In Video Event Detection +1

Estimating Magnitude and Phase of Automotive Radar Signals under Multiple Interference Sources with Fully Convolutional Networks

1 code implementation11 Aug 2020 Nicolae-Cătălin Ristea, Andrei Anghel, Radu Tudor Ionescu

In order to train our network in a real-world scenario, we introduce a new data set of realistic automotive radar signals with multiple targets and multiple interferers.

Autonomous Driving

Teacher-Student Training and Triplet Loss for Facial Expression Recognition under Occlusion

no code implementations3 Aug 2020 Mariana-Iuliana Georgescu, Radu Tudor Ionescu

First of all, we employ the classic teacher-student training strategy, in which the teacher is a CNN trained on fully-visible faces and the student is a CNN trained on occluded faces.

Facial Expression Recognition Knowledge Distillation +1

The Unreasonable Effectiveness of Machine Learning in Moldavian versus Romanian Dialect Identification

1 code implementation30 Jul 2020 Mihaela Găman, Radu Tudor Ionescu

We conduct a subjective evaluation by human annotators, showing that humans attain much lower accuracy rates compared to machine learning (ML) models.

Dialect Identification Ensemble Learning

Fully Convolutional Neural Networks for Automotive Radar Interference Mitigation

1 code implementation21 Jul 2020 Nicolae-Cătălin Ristea, Andrei Anghel, Radu Tudor Ionescu

Moreover, considering the lack of databases for this task, we release as open source a large scale data set that closely replicates real world automotive scenarios for single-interference cases, allowing others to objectively compare their future work in this domain.

Signal Processing

Are you wearing a mask? Improving mask detection from speech using augmentation by cycle-consistent GANs

no code implementations17 Jun 2020 Nicolae-Cătălin Ristea, Radu Tudor Ionescu

Original and translated utterances are converted into spectrograms which are provided as input to a set of ResNet neural networks with various depths.

Data Augmentation

A Generic and Model-Agnostic Exemplar Synthetization Framework for Explainable AI

1 code implementation6 Jun 2020 Antonio Barbalau, Adrian Cosma, Radu Tudor Ionescu, Marius Popescu

In this work, we focus on explainable AI and propose a novel generic and model-agnostic framework for synthesizing input exemplars that maximize a desired response from a machine learning model.

Non-linear Neurons with Human-like Apical Dendrite Activations

no code implementations2 Feb 2020 Mariana-Iuliana Georgescu, Radu Tudor Ionescu, Nicolae-Catalin Ristea, Nicu Sebe

We show that a standard neuron followed by the novel apical dendrite activation (ADA) can learn the XOR logical function with 100% accuracy.

Convolutional Neural Networks with Intermediate Loss for 3D Super-Resolution of CT and MRI Scans

1 code implementation5 Jan 2020 Mariana-Iuliana Georgescu, Radu Tudor Ionescu, Nicolae Verga

We evaluate our method in the context of 2D and 3D super-resolution of CT and MRI scans from two databases, comparing it to relevant related works from the literature and baselines based on various interpolation schemes, using 2x and 4x scaling factors.

Image Super-Resolution

Convolutional Neural Networks for User Identificationbased on Motion Sensors Represented as Image

no code implementations8 Dec 2019 Cezara Benegui, Radu Tudor Ionescu

To pre-train the CNN and the RNN models for multi-class user classification, we use a different set of users than the set used for few-shot user identification, ensuring a realistic scenario.

General Classification

Forward and Backward Feature Selection for Query Performance Prediction

no code implementations4 Dec 2019 Sébastien Déjean, Radu Tudor Ionescu, Josiane Mothe, Md Zia Ullah

We found that: (1) our model based on a limited number of selected features is as good as more complex models for QPP and better than non-selective models; (2) our model is more efficient than complex models during inference time since it requires fewer features; (3) the predictive model is readable and understandable; and (4) one of our new QPP features is consistently selected across different collections, proving its usefulness.

Feature Selection Model Selection

Curriculum Self-Paced Learning for Cross-Domain Object Detection

no code implementations15 Nov 2019 Petru Soviany, Radu Tudor Ionescu, Paolo Rota, Nicu Sebe

To alleviate this problem, researchers proposed various domain adaptation methods to improve object detection results in the cross-domain setting, e. g. by translating images with ground-truth labels from the source domain to the target domain using Cycle-GAN.

Domain Adaptation Object Detection

Recognizing Facial Expressions of Occluded Faces using Convolutional Neural Networks

no code implementations12 Nov 2019 Mariana-Iuliana Georgescu, Radu Tudor Ionescu

In this paper, we present an approach based on convolutional neural networks (CNNs) for facial expression recognition in a difficult setting with severe occlusions.

Facial Expression Recognition Virtual Reality

Image Difficulty Curriculum for Generative Adversarial Networks (CuGAN)

1 code implementation20 Oct 2019 Petru Soviany, Claudiu Ardei, Radu Tudor Ionescu, Marius Leordeanu

All strategies are first based on ranking the training images by their difficulty scores, which are estimated by a state-of-the-art image difficulty predictor.

Curriculum Learning Image Generation +1

A Report on the Third VarDial Evaluation Campaign

no code implementations WS 2019 Marcos Zampieri, Shervin Malmasi, Yves Scherrer, Tanja Samard{\v{z}}i{\'c}, Francis Tyers, Miikka Silfverberg, Natalia Klyueva, Tung-Le Pan, Chu-Ren Huang, Radu Tudor Ionescu, Andrei M. Butnaru, Tommi Jauhiainen

In this paper, we present the findings of the Third VarDial Evaluation Campaign organized as part of the sixth edition of the workshop on Natural Language Processing (NLP) for Similar Languages, Varieties and Dialects (VarDial), co-located with NAACL 2019.

Dialect Identification Morphological Analysis

Clustering Images by Unmasking - A New Baseline

no code implementations2 May 2019 Mariana-Iuliana Georgescu, Radu Tudor Ionescu

We propose a novel agglomerative clustering method based on unmasking, a technique that was previously used for authorship verification of text documents and for abnormal event detection in videos.

Authorship Verification Event Detection +3

Vector of Locally-Aggregated Word Embeddings (VLAWE): A Novel Document-level Representation

1 code implementation NAACL 2019 Radu Tudor Ionescu, Andrei M. Butnaru

The Vector of Locally-Aggregated Word Embeddings (VLAWE) representation of a document is then computed by accumulating the differences between each codeword vector and each word vector (from the document) associated to the respective codeword.

Document-level Text Classification +1

MOROCO: The Moldavian and Romanian Dialectal Corpus

1 code implementation ACL 2019 Andrei M. Butnaru, Radu Tudor Ionescu

In this work, we introduce the MOldavian and ROmanian Dialectal COrpus (MOROCO), which is freely available for download at https://github. com/butnaruandrei/MOROCO.

Continuous Trade-off Optimization between Fast and Accurate Deep Face Detectors

no code implementations27 Nov 2018 Petru Soviany, Radu Tudor Ionescu

All the approaches are based on separating the test images in two batches, an easy batch that is fed to a faster face detector and a difficult batch that is fed to a more accurate yet slower detector.

Face Detection

Transductive Learning with String Kernels for Cross-Domain Text Classification

no code implementations2 Nov 2018 Radu Tudor Ionescu, Andrei M. Butnaru

Although classifiers for a target domain can be trained on labeled text data from a related source domain, the accuracy of such classifiers is usually lower in the cross-domain setting.

Classification Cross-Domain Text Classification +2

CocoNet: A deep neural network for mapping pixel coordinates to color values

1 code implementation29 May 2018 Paul Andrei Bricman, Radu Tudor Ionescu

It is important to note that we have to train an individual neural network for each input image, i. e. one network encodes a single image only.

Image Compression Image Denoising

UnibucKernel Reloaded: First Place in Arabic Dialect Identification for the Second Year in a Row

no code implementations COLING 2018 Andrei M. Butnaru, Radu Tudor Ionescu

Furthermore, our top macro-F1 score (58. 92%) is significantly better than the second best score (57. 59%) in the 2018 ADI Shared Task, according to the statistical significance test performed by the organizers.

Dialect Identification

Local Learning with Deep and Handcrafted Features for Facial Expression Recognition

no code implementations29 Apr 2018 Mariana-Iuliana Georgescu, Radu Tudor Ionescu, Marius Popescu

We present an approach that combines automatic features learned by convolutional neural networks (CNN) and handcrafted features computed by the bag-of-visual-words (BOVW) model in order to achieve state-of-the-art results in facial expression recognition.

Facial Expression Recognition General Classification

Real-Time Deep Learning Method for Abandoned Luggage Detection in Video

no code implementations3 Mar 2018 Sorina Smeureanu, Radu Tudor Ionescu

Recent terrorist attacks in major cities around the world have brought many casualties among innocent citizens.

Motion Estimation Object Detection

Detecting abnormal events in video using Narrowed Normality Clusters

no code implementations12 Jan 2018 Radu Tudor Ionescu, Sorina Smeureanu, Marius Popescu, Bogdan Alexe

To detected abnormal events in the test video, we analyze each test sample and consider its maximum normality score provided by the trained one-class SVM models, based on the intuition that a test sample can belong to only one cluster of normality.

Event Detection Outlier Detection

Can string kernels pass the test of time in Native Language Identification?

no code implementations WS 2017 Radu Tudor Ionescu, Marius Popescu

While most of our kernels are based on character p-grams (also known as n-grams) extracted from essays or speech transcripts, we also use a kernel based on i-vectors, a low-dimensional representation of audio recordings, provided by the shared task organizers.

Native Language Identification

From Image to Text Classification: A Novel Approach based on Clustering Word Embeddings

no code implementations25 Jul 2017 Andrei M. Butnaru, Radu Tudor Ionescu

In this paper, we propose a novel approach for text classification based on clustering word embeddings, inspired by the bag of visual words model, which is widely used in computer vision.

General Classification Text Categorization +1

Learning to Identify Arabic and German Dialects using Multiple Kernels

no code implementations WS 2017 Radu Tudor Ionescu, Andrei Butnaru

We present a machine learning approach for the Arabic Dialect Identification (ADI) and the German Dialect Identification (GDI) Closed Shared Tasks of the DSL 2017 Challenge.

Dialect Identification

UnibucKernel: An Approach for Arabic Dialect Identification Based on Multiple String Kernels

no code implementations WS 2016 Radu Tudor Ionescu, Marius Popescu

Our approach is shallow and simple, but the empirical results obtained in the ADI Shared Task prove that it achieves very good results.

Dialect Identification Text Categorization

Cannot find the paper you are looking for? You can Submit a new open access paper.