18 citations · 58 across the 14 of their papers we have counts for
15 papers
Faithful Grounded Visual Reasoning via Learned Proxy-Tokens
Tom Hodemon, Mohamed Chaouch, Aboubacar Tuo +1
Multimodal Large Language Models (MLLMs) have achieved remarkable success in Visual Question Answering (VQA), yet their "black-box" nature hinders deployment in critical domains. G…
Benchmarking Adversarial Robustness and Adversarial Training Strategies for Object Detection
Alexis Winter, Jean-Vincent Martini, Romaric Audigier +2
Object detection models are critical components of automated systems, such as autonomous vehicles and perception-based robots, but their sensitivity to adversarial attacks poses a…
MonoProb: Self-Supervised Monocular Depth Estimation with Interpretable Uncertainty
Rémi Marsal, Florian Chabot, Angelique Loesch +2
Self-supervised monocular depth estimation methods aim to be used in critical applications such as autonomous vehicles for environment analysis. To circumvent the potential imperfe…
Towards Few-Annotation Learning for Object Detection: Are Transformer-based Models More Efficient ?
Quentin Bouniot, Angélique Loesch, Romaric Audigier +1
For specialized and dense downstream tasks such as object detection, labeling data requires expertise and can be very expensive, making few-shot and semi-supervised models much mor…
Proposal-Contrastive Pretraining for Object Detection from Fewer Data
Quentin Bouniot, Romaric Audigier, Angélique Loesch +1
The use of pretrained deep neural networks represents an attractive way to achieve strong results with few data available. When specialized in dense problems such as object detecti…
Spatio-temporal predictive tasks for abnormal event detection in videos
Yassine Naji, Aleksandr Setkov, Angélique Loesch +2
Abnormal event detection in videos is a challenging problem, partly due to the multiplicity of abnormal patterns and the lack of their corresponding annotations. In this paper, we…
Object-centric and memory-guided normality reconstruction for video anomaly detection
Khalil Bergaoui, Yassine Naji, Aleksandr Setkov +3
This paper addresses video anomaly detection problem for videosurveillance. Due to the inherent rarity and heterogeneity of abnormal events, the problem is viewed as a normality mo…
End-to-end Person Search Sequentially Trained on Aggregated Dataset
Angelique Loesch, Jaonary Rabarisoa, Romaric Audigier
In video surveillance applications, person search is a challenging task consisting in detecting people and extracting features from their silhouette for re-identification (re-ID) p…
Describe me if you can! Characterized Instance-level Human Parsing
Angelique Loesch, Romaric Audigier
Several computer vision applications such as person search or online fashion rely on human description. The use of instance-level human parsing (HP) is therefore relevant since it…
Deadlock-free asynchronous message reordering in Rust with multiparty session types
Zak Cutner, Nobuko Yoshida, Martin Vassor
Rust is a modern systems language focused on performance and reliability. Complementing Rust's promise to provide "fearless concurrency", developers frequently exploit asynchronous…
Improving Unsupervised Domain Adaptive Re-Identification via Source-Guided Selection of Pseudo-Labeling Hyperparameters
Fabian Dubourvieux, Angélique Loesch, Romaric Audigier +2
Unsupervised Domain Adaptation (UDA) for re-identification (re-ID) is a challenging task: to avoid a costly annotation of additional data, it aims at transferring knowledge from a…
Optimal Transport as a Defense Against Adversarial Attacks
Quentin Bouniot, Romaric Audigier, Angélique Loesch
Deep learning classifiers are now known to have flaws in the representations of their class. Adversarial attacks can find a human-imperceptible perturbation for a given image that…
PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization
Thomas Defard, Aleksandr Setkov, Angelique Loesch +1
We present a new framework for Patch Distribution Modeling, PaDiM, to concurrently detect and localize anomalies in images in a one-class learning setting. PaDiM makes use of a pre…
Improving Few-Shot Learning through Multi-task Representation Learning Theory
Quentin Bouniot, Ievgen Redko, Romaric Audigier +2
In this paper, we consider the framework of multi-task representation (MTR) learning where the goal is to use source tasks to learn a representation that reduces the sample complex…
Unsupervised Domain Adaptation for Person Re-Identification through Source-Guided Pseudo-Labeling
Fabian Dubourvieux, Romaric Audigier, Angelique Loesch +2
Person Re-Identification (re-ID) aims at retrieving images of the same person taken by different cameras. A challenge for re-ID is the performance preservation when a model is used…