1.8k citations · 2.9k across the 66 of their papers we have counts for
45 papers · 1 filter
RoboVAD: A Large Cross-Domain Evaluation Benchmark for Anomaly Detection in Robotic Arm Manipulation Videos
Alexandru-Bogdan Dura, Sebastian Balmus, Radu Tudor Ionescu
Video anomaly detection (VAD) is an actively studied task, having wide applications in typical scenarios such as public surveillance and road traffic safety. The task is also relev…
Rip Current Segmentation: A Novel Benchmark and YOLOv8 Baseline Results
Andrei Dumitriu, Florin Tatui, Florin Miron +2
Rip currents are the leading cause of fatal accidents and injuries on many beaches worldwide, emphasizing the importance of automatically detecting these hazardous surface water cu…
An Open Hyperspectral Dataset with Sea-Land-Cloud Ground-Truth from the HYPSO-1 Satellite
Jon A. Justo, Joseph Garrett, Dennis D. Langer +3
Hyperspectral Imaging, employed in satellites for space remote sensing, like HYPSO-1, faces constraints due to few labeled data sets, affecting the training of AI models demanding…
JEDI: Joint Expert Distillation in a Semi-Supervised Multi-Dataset Student-Teacher Scenario for Video Action Recognition
Lucian Bicsi, Bogdan Alexe, Radu Tudor Ionescu +1
We propose JEDI, a multi-dataset semi-supervised learning method, which efficiently combines knowledge from multiple experts, learned on different datasets, to train and improve th…
CL-MAE: Curriculum-Learned Masked Autoencoders
Neelu Madan, Nicolae-Catalin Ristea, Kamal Nasrollahi +2
Masked image modeling has been demonstrated as a powerful pretext task for generating robust representations that can be effectively generalized across multiple downstream tasks. T…
Reverse Stable Diffusion: What prompt was used to generate this image?
Florinel-Alin Croitoru, Vlad Hondru, Radu Tudor Ionescu +1
Text-to-image diffusion models have recently attracted the interest of many researchers, and inverting the diffusion process can play an important role in better understanding the…
Class Anchor Margin Loss for Content-Based Image Retrieval
Alexandru Ghita, Radu Tudor Ionescu
The performance of neural networks in content-based image retrieval (CBIR) is highly influenced by the chosen loss (objective) function. The majority of objective functions for neu…
Self-Distilled Masked Auto-Encoders are Efficient Video Anomaly Detectors
Nicolae-Catalin Ristea, Florinel-Alin Croitoru, Radu Tudor Ionescu +3
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 threef…
iQPP: A Benchmark for Image Query Performance Prediction
Eduard Poesina, Radu Tudor Ionescu, Josiane Mothe
To date, query performance prediction (QPP) in the context of content-based image retrieval remains a largely unexplored task, especially in the query-by-example scenario, where th…
Audiovisual Masked Autoencoders
Mariana-Iuliana Georgescu, Eduardo Fonseca, Radu Tudor Ionescu +3
Can we leverage the audiovisual information already present in video to improve self-supervised representation learning? To answer this question, we study various pretraining archi…
Lightning Fast Video Anomaly Detection via Adversarial Knowledge Distillation
Florinel-Alin Croitoru, Nicolae-Catalin Ristea, Dana Dascalescu +3
We propose a very fast frame-level model for anomaly detection in video, which learns to detect anomalies by distilling knowledge from multiple highly accurate object-level teacher…
Self-Supervised Masked Convolutional Transformer Block for Anomaly Detection
Neelu Madan, Nicolae-Catalin Ristea, Radu Tudor Ionescu +4
Anomaly detection has recently gained increasing attention in the field of computer vision, likely due to its broad set of applications ranging from product fault detection on indu…
Diffusion Models in Vision: A Survey
Florinel-Alin Croitoru, Vlad Hondru, Radu Tudor Ionescu +1
Denoising diffusion models represent a recent emerging topic in computer vision, demonstrating remarkable results in the area of generative modeling. A diffusion model is a deep ge…
SSMTL++: Revisiting Self-Supervised Multi-Task Learning for Video Anomaly Detection
Antonio Barbalau, Radu Tudor Ionescu, Mariana-Iuliana Georgescu +6
A self-supervised multi-task learning (SSMTL) framework for video anomaly detection was recently introduced in literature. Due to its highly accurate results, the method attracted…
SepTr: Separable Transformer for Audio Spectrogram Processing
Nicolae-Catalin Ristea, Radu Tudor Ionescu, Fahad Shahbaz Khan
Following the successful application of vision transformers in multiple computer vision tasks, these models have drawn the attention of the signal processing community. This is bec…
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…
Feature-level augmentation to improve robustness of deep neural networks to affine transformations
Adrian Sandru, Mariana-Iuliana Georgescu, Radu Tudor Ionescu
Recent studies revealed that convolutional neural networks do not generalize well to small image transformations, e.g. rotations by a few degrees or translations of a few pixels. T…
Self-paced learning to improve text row detection in historical documents with missing labels
Mihaela Gaman, Lida Ghadamiyan, Radu Tudor Ionescu +1
An important preliminary step of optical character recognition systems is the detection of text rows. To address this task in the context of historical data with missing labels, we…
Teacher-Student Training and Triplet Loss to Reduce the Effect of Drastic Face Occlusion
Mariana-Iuliana Georgescu, Georgian Duta, Radu Tudor Ionescu
We study a series of recognition tasks in two realistic scenarios requiring the analysis of faces under strong occlusion. On the one hand, we aim to recognize facial expressions of…
Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detection
Nicolae-Catalin Ristea, Neelu Madan, Radu Tudor Ionescu +4
Anomaly detection is commonly pursued as a one-class classification problem, where models can only learn from normal training samples, while being evaluated on both normal and abno…
UBnormal: New Benchmark for Supervised Open-Set Video Anomaly Detection
Andra Acsintoae, Andrei Florescu, Mariana-Iuliana Georgescu +5
Detecting abnormal events in video is commonly framed as a one-class classification task, where training videos contain only normal events, while test videos encompass both normal…
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…
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…
Unsupervised Medical Image Alignment with Curriculum Learning
Mihail Burduja, Radu Tudor Ionescu
We explore different curriculum learning methods for training convolutional neural networks on the task of deformable pairwise 3D medical image registration. To the best of our kno…