We introduce Explicit Neural Surfaces (ENS), an efficient surface
recons...
The goal of this work is to understand the way actions are performed in
...
Recently the focus of the computer vision community has shifted from
exp...
We introduce ViewNeRF, a Neural Radiance Field-based viewpoint estimatio...
Understanding the 3D world without supervision is currently a major chal...
Coreference resolution aims at identifying words and phrases which refer...
Diffusion models currently achieve state-of-the-art performance for both...
The success of state-of-the-art deep neural networks heavily relies on t...
In recent years, generative adversarial networks (GANs) have been an act...
Face recognition, as one of the most successful applications in artifici...
Remarkable progress has been achieved in synthesizing photo-realistic im...
We propose a unified look at jointly learning multiple vision tasks and
...
In recent years, neural implicit representations have made remarkable
pr...
Dataset condensation aims at reducing the network training effort throug...
Despite the recent advances in multi-task learning of dense prediction
p...
Scene graph generation (SGG) aims to capture a wide variety of interacti...
Computational cost to train state-of-the-art deep models in many learnin...
In this paper, we look at the problem of cross-domain few-shot classific...
There is a growing interest in developing computer vision methods that c...
We propose an unsupervised foreground-background segmentation method via...
In this paper, we look at the problem of few-shot classification that ai...
In many machine learning problems, large-scale datasets have become the
...
Deep anomaly detection is a difficult task since, in high dimensions, it...
Multi-task learning (MTL) is to learn one single model that performs mul...
Efficient training of deep neural networks is an increasingly important
...
With the explosion of digital data in recent years, continuously learnin...
A practical shortcoming of deep neural networks is their specialization ...
It is widely believed that sharing gradients will not leak private train...
Recent semi-supervised learning methods have shown to achieve comparable...
Automatically generating natural language descriptions from an image is ...
The different families of saliency methods, either based on contrastive
...
Image deconvolution is the process of recovering convolutional degraded
...
Equivariance to random image transformations is an effective method to l...
The use of computational methods to evaluate aesthetics in photography h...
We introduce a method for learning landmark detectors from unlabelled vi...
Detecting temporal extents of human actions in videos is a challenging
c...
Normalization methods are a central building block in the deep learning
...
In this paper, we consider the problem of learning landmarks for object
...
A practical limitation of deep neural networks is their high degree of
s...
One of the key challenges of visual perception is to extract abstract mo...
There is a growing interest in learning data representations that work w...
Learning automatically the structure of object categories remains an
imp...
With the advent of large labelled datasets and high-capacity models, the...
We introduce the concept of "dynamic image", a novel compact representat...
We propose a new self-supervised CNN pre-training technique based on a n...
Modern discriminative predictors have been shown to match natural
intell...
Weakly supervised learning of object detection is an important problem i...