The success of active learning relies on the exploration of the underlyi...
Despite the recent efforts in accurate 3D annotations in hand and object...
Estimating the pose and shape of hands and objects under interaction fin...
Given an imperfect predictor, we exploit additional features at test tim...
Synthetic data is becoming increasingly common for training computer vis...
We present an algorithm that learns a coarse 3D representation of object...
Across photography, marketing, and website design, being able to direct ...
Predictor combination aims to improve a (target) predictor of a learning...
The automatic extraction of animal 3D pose from images without markers
i...
Deep learning has achieved remarkable performance in various tasks thank...
We present an algorithm to generate diverse foreground objects and compo...
We show implicit filter level sparsity manifests in convolutional neural...
We present a new predictor combination algorithm that improves a given t...
Estimating 3D hand meshes from single RGB images is challenging, due to
...
We investigate filter level sparsity that emerges in convolutional neura...
Unsupervised image-to-image translation techniques are able to map local...
In bin-picking scenarios, multiple instances of an object of interest ar...
Current unsupervised image-to-image translation techniques struggle to f...
Crucial to the success of training a depth-based 3D hand pose estimator ...
In this paper, we investigate the use of generative adversarial networks...
Large databases are often organized by hand-labeled metadata, or criteri...
We propose a novel method called deep convolutional decision jungle (CDJ...
Online action detection (OAD) is challenging since 1) robust yet
computa...
Existing approaches for diffusion on graphs, e.g., for label propagation...
In many learning tasks, the structure of the target space of a function ...
The common graph Laplacian regularizer is well-established in semi-super...