Class-Incremental Learning (CIL) aims to build classification models fro...
This paper presents a new approach to image similarity search in the con...
Solving jigsaw puzzles requires to grasp the visual features of a sequen...
Recent advances in visual representation learning allowed to build an
ab...
3D human whole-body pose estimation aims to localize precise 3D keypoint...
Exemplar-free class-incremental learning is very challenging due to the
...
A large body of recent work targets semantically conditioned image
gener...
3D human pose estimation is a challenging task because of the difficulty...
Plasticity and stability are needed in class-incremental learning in ord...
When learning disconnected distributions, Generative adversarial network...
Recent work on Observer Network has shown promising results on
Out-Of-Di...
Advances in computer vision are pushing the limits of im-age manipulatio...
This paper focuses on non-asymptotic diffusion time in asynchronous goss...
Standard formulations of GANs, where a continuous function deforms a
con...
In this paper I investigate the effect of random seed selection on the
a...
Illustrations are an essential transmission instrument. For an historian...
In this paper, we tackle the detection of out-of-distribution (OOD) obje...
In this paper, we show how uncertainty estimation can be leveraged to en...
In this work we compare the capacity and achievable rate of uncoded fast...
In this paper we propose a highly scalable convolutional neural network,...
In deep metric learning, the training procedure relies on sampling
infor...
We tackle the image reassembly problem with wide space between the fragm...
Recent breakthroughs in representation learning of unseen classes and
ex...
Human pose estimation and action recognition are related tasks since bot...
3D human pose estimation is frequently seen as the task of estimating 3D...
Learning an effective similarity measure between image representations i...
Learning rich and compact representations is an open topic in many field...
Archaeologists are in dire need of automated object reconstruction metho...
Most image retrieval methods use global features that aggregate local
di...
Recent advances in the machine learning community allowed different use ...
Designing powerful tools that support cooking activities has rapidly gai...
We address the issue of speeding up the training of convolutional neural...
Action recognition and human pose estimation are closely related but bot...
In this paper, we propose an end-to-end trainable regression approach fo...
In this paper we propose a fast online Kernel SVM algorithm under tight
...
We address the issue of speeding up the training of convolutional networ...