In image retrieval, standard evaluation metrics rely on score ranking, a...
Vision-language foundation models such as CLIP have shown impressive
zer...
Recently, diffusion-based generative models have achieved remarkable suc...
Out-of-distribution (OOD) detection is a critical requirement for the
de...
Predicting multiple trajectories for road users is important for automat...
Transformers have proved to be very effective for visual recognition tas...
Vision-Language Pretraining (VLP) and Foundation models have been the go...
Transformer models achieve state-of-the-art results for image segmentati...
Predictive performance of machine learning models trained with empirical...
State-of-the-art methods for optical flow estimation rely on deep learni...
Image Retrieval is commonly evaluated with Average Precision (AP) or
Rec...
Deep architecture have proven capable of solving many tasks provided a
s...
Multi-input multi-output architectures propose to train multiple subnetw...
In image retrieval, standard evaluation metrics rely on score ranking, e...
This paper addresses the problem of multi-step time series forecasting f...
Medical image segmentation remains particularly challenging for complex ...
Reliably quantifying the confidence of deep neural classifiers is a
chal...
Probabilistic forecasting consists in predicting a distribution of possi...
Forecasting complex dynamical phenomena in settings where only partial
k...
Leveraging physical knowledge described by partial differential equation...
This paper addresses the problem of time series forecasting for
non-stat...
In computer vision, disentangling techniques aim at improving latent
rep...
Multimodal attentional networks are currently state-of-the-art models fo...
Multimodal representation learning is gaining more and more interest wit...
In this paper, we introduce a new model for leveraging unlabeled data to...
Designing powerful tools that support cooking activities has rapidly gai...
Regularization is a big issue for training deep neural networks. In this...
Regularization is a big issue for training deep neural networks. In this...
Existing region-based object detectors are limited to regions with fixed...
Bilinear models provide an appealing framework for mixing and merging
in...
We address the issue of speeding up the training of convolutional networ...
Convolutional neural networks (CNN) are widely used in computer vision,
...
The goal of our research is to develop methods advancing automatic visua...
Our approach is among the three best to tackle the M2CAI Workflow challe...
In this paper, we investigate a new framework for image classification t...