Marius Popescu — accepted AI-conference papers

2024

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

Nicolae-C?t?lin Ristea, Florinel-Alin Croitoru, Radu Tudor Ionescu, Marius Popescu, Fahad Shahbaz Khan, Mubarak Shah

CVPR 2024poster

We propose an efficient abnormal event detection model based on a lightweight masked auto-encoder (AE) applied at the video frame level. The novelty of the proposed model is threefold. First we introduce an approach to weight tokens based on motion gradients thus shifting the focus from the static b…

Cited by 37 Source ↗PDF ↗code ↗Scholar ↗

2024

“Vorbești Românește?” A Recipe to Train Powerful Romanian LLMs with English Instructions

Mihai Masala, Denis Ilie-Ablachim, Alexandru Dima, Dragos Georgian Corlatescu, Miruna-Andreea Zavelca, Ovio Olaru +7

EMNLP 2024finding

In recent years, Large Language Models (LLMs) have achieved almost human-like performance on various tasks. While some LLMs have been trained on multilingual data, most of the training data is in English; hence, their performance in English greatly exceeds other languages. To our knowledge, we are t…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2023

AD-NLP: A Benchmark for Anomaly Detection in Natural Language Processing

Matei Bejan, Andrei Manolache, Marius Popescu

EMNLP 2023long main

Deep learning models have reignited the interest in Anomaly Detection research in recent years. Methods for Anomaly Detection in text have shown strong empirical results on ad-hoc anomaly setups that are usually made by downsampling some classes of a labeled dataset. This can lead to reproducibility…

Cited by 0 Source ↗code ↗Scholar ↗

2022

Rethinking the Authorship Verification Experimental Setups

Florin Brad, Andrei Manolache, Elena Burceanu, Antonio Barbalau, Radu Tudor Ionescu, Marius Popescu

EMNLP 2022main

One of the main drivers of the recent advances in authorship verification is the PAN large-scale authorship dataset. Despite generating significant progress in the field, inconsistent performance differences between the closed and open test sets have been reported. To this end, we improve the experi…

Cited by 5 Source ↗PDF ↗code ↗Scholar ↗

2022

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

Andrei Manolache, Florin Brad, Antonio Barbalau, Radu Tudor Ionescu, Marius Popescu

NeurIPS 2022accept

The Dark Web represents a hotbed for illicit activity, where users communicate on different market forums in order to exchange goods and services. Law enforcement agencies benefit from forensic tools that perform authorship analysis, in order to identify and profile users based on their textual cont…

Cited by 22 Source ↗PDF ↗code ↗Scholar ↗

2021

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

Tudor-Alexandru Mare, Georgian Duta, Iuliana Georgescu, Adrian Sandru, Bogdan Alexe, Marius Popescu +1

NeurIPS 2021poster

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 data sets (e.g., CelebA, CASIA-WebFace) used for training these systems were released before the pandemic, so they now s…

Cited by 24 Source ↗code ↗Scholar ↗

2021

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

Mariana-Iuliana Georgescu, Antonio Barbalau, Radu Tudor Ionescu, Fahad Shahbaz Khan, Marius Popescu, Mubarak Shah

CVPR 2021poster

Anomaly detection in video is a challenging computer vision problem. Due to the lack of anomalous events at training time, anomaly detection requires the design of learning methods without full supervision. In this paper, we approach anomalous event detection in video through self-supervised and mul…

Cited by 383 PDF ↗Scholar ↗

2020

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

Antonio Barbalau, Adrian Cosma, Radu Tudor Ionescu, Marius Popescu

NeurIPS 2020oral

We study the task of replicating the functionality of black-box neural models, for which we only know the output class probabilities provided for a set of input images. We assume back-propagation through the black-box model is not possible and its training images are not available, e.g. the model co…

Cited by 64 Source ↗PDF ↗code ↗Scholar ↗

2017

Unmasking the Abnormal Events in Video

Radu Tudor Ionescu, Sorina Smeureanu, Bogdan Alexe, Marius Popescu

ICCV 2017poster

We propose a novel framework for abnormal event detection in video that requires no training sequences. Our framework is based on unmasking, a technique previously used for authorship verification in text documents, which we adapt to our task. We iteratively train a binary classifier to distinguish…

Cited by 398 PDF ↗Scholar ↗

2016

How Hard Can It Be? Estimating the Difficulty of Visual Search in an Image

Radu Tudor Ionescu, Bogdan Alexe, Marius Leordeanu, Marius Popescu, Dim P. Papadopoulos, Vittorio Ferrari

CVPR 2016poster

We address the problem of estimating image difficulty defined as the human response time for solving a visual search task. We collect human annotations of image difficulty for the PASCAL VOC 2012 data set through a crowd-sourcing platform. We then analyze what human interpretable image properties ca…

Cited by 164 PDF ↗Scholar ↗