Text-conditioned image generation has made significant progress in recen...
Novel architectures have recently improved generative image synthesis le...
The field of neural style transfer has experienced a surge of research
e...
Generative image synthesis with diffusion models has recently achieved
e...
By decomposing the image formation process into a sequential application...
Most recent view-invariant action recognition and performance assessment...
Deep metric learning (DML) is a cornerstone of many computer vision
appl...
Autoregressive models and their sequential factorization of the data
lik...
Deep Metric Learning (DML) aims to find representations suitable for
zer...
The search for specific objects or motifs is essential to art history as...
How would a static scene react to a local poke? What are the effects on ...
What would be the effect of locally poking a static scene? We present an...
The use of coarse-grained layouts for controllable synthesis of complex ...
Video understanding calls for a model to learn the characteristic interp...
Is a geometric model required to synthesize novel views from a single im...
There have been many successful implementations of neural style transfer...
Generating and representing human behavior are of major importance for
v...
Contrasting the previous evidence that neurons in the later layers of a
...
Designed to learn long-range interactions on sequential data, transforme...
It is tempting to think that machines are less prone to unfairness and
p...
Deep Metric Learning (DML) provides a crucial tool for visual similarity...
We address the problem of discovering part segmentations of articulated
...
To tackle increasingly complex tasks, it has become an essential ability...
Artificial Intelligence for Content Creation has the potential to reduce...
Visual Similarity plays an important role in many computer vision
applic...
Visual Similarity plays an important role in many computer vision
applic...
Neural networks have greatly boosted performance in computer vision by
l...
Learning the similarity between images constitutes the foundation for
nu...
Capturing photographs with wrong exposures remains a major source of err...
Learning visual similarity requires to learn relations, typically betwee...
Style transfer has recently received a lot of attention, since it allows...
Learning robust representations that allow to reliably establish relatio...
Deep generative models come with the promise to learn an explainable
rep...
Metric learning seeks to embed images of objects suchthat class-defined
...
Finding semantic correspondences is a challenging problem. With the
brea...
Learning the embedding space, where semantically similar objects are loc...
Large intra-class variation is the result of changes in multiple object
...
In this paper we present a self-supervised method for representation lea...
Self-supervised learning of convolutional neural networks can harness la...
Recently, style transfer has received a lot of attention. While much of ...
Deep generative models have demonstrated great performance in image
synt...
Exemplar learning of visual similarities in an unsupervised manner is a
...
Human pose analysis is presently dominated by deep convolutional network...
Understanding human activity and being able to explain it in detail surp...
Unsupervised learning of visual similarities is of paramount importance ...
Exemplar learning is a powerful paradigm for discovering visual similari...
Abnormality detection in video poses particular challenges due to the
in...