Zobrazeno 1 - 10
of 29
pro vyhledávání: '"LOESCH, Angélique"'
Self-supervised monocular depth estimation methods aim to be used in critical applications such as autonomous vehicles for environment analysis. To circumvent the potential imperfections of these approaches, a quantification of the prediction confide
Externí odkaz:
http://arxiv.org/abs/2311.06137
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 more attractive alternatives. While in the few-shot setup we observe that
Externí odkaz:
http://arxiv.org/abs/2310.19936
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 detection, learning local rather than global information in images has proven
Externí odkaz:
http://arxiv.org/abs/2310.16835
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 propose new constrained pretext tasks to learn object level normality
Externí odkaz:
http://arxiv.org/abs/2210.15741
Autor:
Bergaoui, Khalil, Naji, Yassine, Setkov, Aleksandr, Loesch, Angélique, Gouiffès, Michèle, Audigier, Romaric
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 modeling strategy, in which our model learns object-centric normal patte
Externí odkaz:
http://arxiv.org/abs/2203.03677
Publikováno v:
Published in: 2019 IEEE International Conference on Image Processing (ICIP)
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) purpose. We propose a new end-to-end model that jointly computes detect
Externí odkaz:
http://arxiv.org/abs/2201.09604
Autor:
Loesch, Angelique, Audigier, Romaric
Publikováno v:
Published in: 2021 IEEE International Conference on Image Processing (ICIP)
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 localizes semantic attributes and body parts within a person. But how
Externí odkaz:
http://arxiv.org/abs/2201.09594
The use of pseudo-labels prevails in order to tackle Unsupervised Domain Adaptive (UDA) Re-Identification (re-ID) with the best performance. Indeed, this family of approaches has given rise to several UDA re-ID specific frameworks, which are effectiv
Externí odkaz:
http://arxiv.org/abs/2112.12887
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 domain with annotated data to a domain of interest with only unlabeled
Externí odkaz:
http://arxiv.org/abs/2110.07897
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 will mislead a trained model. The most effective methods to defend aga
Externí odkaz:
http://arxiv.org/abs/2102.03156