We introduce Replay, a collection of multi-view, multi-modal videos of h...
Methods for video motion prediction either estimate jointly the instanta...
We consider the problem of reconstructing a dynamic scene observed from ...
We present a method for fast 3D reconstruction and real-time rendering o...
We introduce the novel-view acoustic synthesis (NVAS) task: given the si...
Video provides us with the spatio-temporal consistency needed for visual...
Obtaining photorealistic reconstructions of objects from sparse views is...
Learning causal relationships in high-dimensional data (images, videos) ...
Prior work for articulated 3D shape reconstruction often relies on
speci...
We tackle the problem of learning the geometry of multiple categories of...
Following their success in natural language processing, transformers hav...
We present NeuroMorph, a new neural network architecture that takes as i...
Recent advances in using retrieval components over external knowledge so...
Transformers have shown outstanding results for natural language
underst...
In this work, we focus on the task of learning and representing dense
co...
We propose a method for building large collections of human poses with f...
Recent contributions have demonstrated that it is possible to recognize ...
Understanding causes and effects in mechanical systems is an essential
c...
We propose C3DPO, a method for extracting 3D models of deformable object...
DensePose supersedes traditional landmark detectors by densely mapping i...
In this work we integrate ideas from surface-based modeling with neural
...
Human activity recognition is typically addressed by training models to
...
In this work, we establish dense correspondences between RGB image and a...
Despite the large improvements in performance attained by using deep lea...
Generating adversarial examples is a critical step for evaluating and
im...
The ability to predict and therefore to anticipate the future is an impo...
We propose a method for hand pose estimation based on a deep regressor
t...
We present a large-scale study exploring the capability of temporal deep...
We present a method for gesture detection and localisation based on
mult...