Radu Tudor Ionescu

research

∙ 09/06/2023

RoDia: A New Dataset for Romanian Dialect Identification from Speech

Dialect identification is a critical task in speech processing and langu...

0 Codrut Rotaru, et al. ∙

research

∙ 08/31/2023

CL-MAE: Curriculum-Learned Masked Autoencoders

Masked image modeling has been demonstrated as a powerful pretext task f...

0 Neelu Madan, et al. ∙

research

∙ 08/09/2023

JEDI: Joint Expert Distillation in a Semi-Supervised Multi-Dataset Student-Teacher Scenario for Video Action Recognition

We propose JEDI, a multi-dataset semi-supervised learning method, which ...

0 Lucian Bicsi, et al. ∙

research

∙ 08/02/2023

Reverse Stable Diffusion: What prompt was used to generate this image?

Text-to-image diffusion models such as Stable Diffusion have recently at...

0 Florinel-Alin Croitoru, et al. ∙

research

∙ 07/27/2023

Cascaded Cross-Modal Transformer for Request and Complaint Detection

We propose a novel cascaded cross-modal transformer (CCMT) that combines...

0 Nicolae-Catalin Ristea, et al. ∙

research

∙ 06/21/2023

Self-Distilled Masked Auto-Encoders are Efficient Video Anomaly Detectors

We propose an efficient abnormal event detection model based on a lightw...

0 Nicolae-Catalin Ristea, et al. ∙

research

∙ 06/01/2023

Class Anchor Margin Loss for Content-Based Image Retrieval

The performance of neural networks in content-based image retrieval (CBI...

0 Alexandru Ghita, et al. ∙

research

∙ 02/20/2023

iQPP: A Benchmark for Image Query Performance Prediction

To date, query performance prediction (QPP) in the context of content-ba...

0 Eduard Poesina, et al. ∙

research

∙ 12/15/2022

FreCDo: A Large Corpus for French Cross-Domain Dialect Identification

We present a novel corpus for French dialect identification comprising 4...

0 Mihaela Gaman, et al. ∙

research

∙ 12/09/2022

Audiovisual Masked Autoencoders

Can we leverage the audiovisual information already present in video to ...

0 Mariana-Iuliana Georgescu, et al. ∙

research

∙ 11/28/2022

Lightning Fast Video Anomaly Detection via Adversarial Knowledge Distillation

We propose a very fast frame-level model for anomaly detection in video,...

0 Nicolae-Catalin Ristea, et al. ∙

research

∙ 10/22/2022

Diversity-Promoting Ensemble for Medical Image Segmentation

Medical image segmentation is an actively studied task in medical imagin...

0 Mariana-Iuliana Georgescu, et al. ∙

research

∙ 09/25/2022

Self-Supervised Masked Convolutional Transformer Block for Anomaly Detection

Anomaly detection has recently gained increasing attention in the field ...

54 Neelu Madan, et al. ∙

research

∙ 09/10/2022

Diffusion Models in Vision: A Survey

Denoising diffusion models represent a recent emerging topic in computer...

187 Florinel-Alin Croitoru, et al. ∙

research

∙ 07/16/2022

SSMTL++: Revisiting Self-Supervised Multi-Task Learning for Video Anomaly Detection

A self-supervised multi-task learning (SSMTL) framework for video anomal...

0 Antonio Barbalau, et al. ∙

research

∙ 07/07/2022

VeriDark: A Large-Scale Benchmark for Authorship Verification on the Dark Web

The DarkWeb represents a hotbed for illicit activity, where users commun...

10 Andrei Manolache, et al. ∙

research

∙ 05/18/2022

LeRaC: Learning Rate Curriculum

Most curriculum learning methods require an approach to sort the data sa...

0 Florinel-Alin Croitoru, et al. ∙

research

∙ 04/08/2022

Multimodal Multi-Head Convolutional Attention with Various Kernel Sizes for Medical Image Super-Resolution

Super-resolving medical images can help physicians in providing more acc...

0 Mariana-Iuliana Georgescu, et al. ∙

research

∙ 03/17/2022

SepTr: Separable Transformer for Audio Spectrogram Processing

Following the successful application of vision transformers in multiple ...

0 Nicolae-Catalin Ristea, et al. ∙

research

∙ 02/14/2022

Discriminability-enforcing loss to improve representation learning

During the training process, deep neural networks implicitly learn to re...

0 Florinel-Alin Croitoru, et al. ∙

research

∙ 02/10/2022

Feature-level augmentation to improve robustness of deep neural networks to affine transformations

Recent studies revealed that convolutional neural networks do not genera...

0 Adrian Sandru, et al. ∙

research

∙ 01/28/2022

Self-paced learning to improve text row detection in historical documents with missing labels

An important preliminary step of optical character recognition systems i...

0 Mihaela Gaman, et al. ∙

research

∙ 11/20/2021

Teacher-Student Training and Triplet Loss to Reduce the Effect of Drastic Face Occlusion

We study a series of recognition tasks in two realistic scenarios requir...

5 Mariana-Iuliana Georgescu, et al. ∙

research

∙ 11/17/2021

Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detection

Anomaly detection is commonly pursued as a one-class classification prob...

19 Nicolae-Catalin Ristea, et al. ∙

research

∙ 11/16/2021

UBnormal: New Benchmark for Supervised Open-Set Video Anomaly Detection

Detecting abnormal events in video is commonly framed as a one-class cla...

15 Andra Acsintoae, et al. ∙

research

∙ 10/12/2021

CyTran: Cycle-Consistent Transformers for Non-Contrast to Contrast CT Translation

We propose a novel approach to translate unpaired contrast computed tomo...

0 Nicolae-Catalin Ristea, et al. ∙

research

∙ 09/03/2021

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

The COVID-19 pandemic raises the problem of adapting face recognition sy...

13 Tudor Mare, et al. ∙

research

∙ 08/17/2021

Contextual Convolutional Neural Networks

We propose contextual convolution (CoConv) for visual recognition. CoCon...

0 Ionut Cosmin Duta, et al. ∙

research

∙ 07/22/2021

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

We propose an enhanced version of the Authentication with Built-in Camer...

0 Cezara Benegui, et al. ∙

research

∙ 05/13/2021

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

In this work, we introduce a corpus for satire detection in Romanian new...

0 Ana-Cristina Rogoz, et al. ∙

research

∙ 04/10/2021

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

In this paper, we introduce FreSaDa, a French Satire Data Set, which is ...

0 Radu Tudor Ionescu, et al. ∙

research

∙ 03/22/2021

Self-paced ensemble learning for speech and audio classification

Combining multiple machine learning models into an ensemble is known to ...

0 Nicolae-Catalin Ristea, et al. ∙

research

∙ 02/20/2021

Unsupervised Medical Image Alignment with Curriculum Learning

We explore different curriculum learning methods for training convolutio...

0 Mihail Burduja, et al. ∙

research

∙ 02/18/2021

UnibucKernel: Geolocating Swiss German Jodels Using Ensemble Learning

In this work, we describe our approach addressing the Social Media Varie...

0 Mihaela Gaman, et al. ∙

research

∙ 01/25/2021

Curriculum Learning: A Survey

Training machine learning models in a meaningful order, from the easy sa...

0 Petru Soviany, et al. ∙

research

∙ 01/11/2021

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

Romanian is one of the understudied languages in computational linguisti...

0 Anca Maria Tache, et al. ∙

research

∙ 12/21/2020

Natural vs Balanced Distribution in Deep Learning on Whole Slide Images for Cancer Detection

The class distribution of data is one of the factors that regulates the ...

7 Ismat Ara Reshma, et al. ∙

research

∙ 11/15/2020

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

Anomaly detection in video is a challenging computer vision problem. Due...

0 Mariana-Iuliana Georgescu, et al. ∙

research

∙ 10/21/2020

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

We study the task of replicating the functionality of black-box neural m...

0 Antonio Barbalau, et al. ∙

research

∙ 10/14/2020

Automotive Radar Interference Mitigation with Unfolded Robust PCA based on Residual Overcomplete Auto-Encoder Blocks

Deep learning methods for automotive radar interference mitigation can s...

0 Nicolae-Catalin Ristea, et al. ∙

research

∙ 10/07/2020

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

In this work, we introduce the methods proposed by the UnibucKernel team...

0 Mihaela Gaman, et al. ∙

research

∙ 09/25/2020

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

We propose a deep learning method to automatically detect personal prote...

0 Adrian Sandru, et al. ∙

research

∙ 09/02/2020

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

For the time being, mobile devices employ implicit authentication mechan...

0 Cezara Benegui, et al. ∙

research

∙ 09/01/2020

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

Nowadays, commonly-used authentication systems for mobile device users, ...

0 Cezara Benegui, et al. ∙

research

∙ 08/27/2020

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

Abnormal event detection in video is a complex computer vision problem t...

32 Mariana-Iuliana Georgescu, et al. ∙

research

∙ 08/11/2020

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

Radar sensors are gradually becoming a wide-spread equipment for road ve...

17 Nicolae-Catalin Ristea, et al. ∙

research

∙ 08/03/2020

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

In this paper, we study the task of facial expression recognition under ...

0 Mariana-Iuliana Georgescu, et al. ∙

research

∙ 08/01/2020

Accurate and Efficient Intracranial Hemorrhage Detection and Subtype Classification in 3D CT Scans with Convolutional and Long Short-Term Memory Neural Networks

In this paper, we present our system for the RSNA Intracranial Hemorrhag...

6 Mihail Burduja, et al. ∙

research

∙ 07/30/2020

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

In this work, we provide a follow-up on the Moldavian versus Romanian Cr...

0 Mihaela Gaman, et al. ∙

research

∙ 06/17/2020

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

The task of detecting whether a person wears a face mask from speech is ...

0 Nicolae-Catalin Ristea, et al. ∙

Radu Tudor Ionescu

Featured Co-authors