-
Style Tokens
Global Style Tokens (GSTs) are a recently-proposed method to learn latent disentangled representations of high-dimensional data. GSTs can be used within Tacotron, a... -
Global Style Tokens
Global Style Tokens (GSTs) are a recently-proposed method to learn latent disentangled representations of high-dimensional data. GSTs can be used within Tacotron, a... -
Text-Predicted Global Style Tokens
Global Style Tokens (GSTs) are a recently-proposed method to learn latent disentangled representations of high-dimensional data. GSTs can be used within Tacotron, a... -
MNIST and USPS
The MNIST and USPS datasets are used for binary classification tasks. -
3D Intervertebral Disc Localization and Segmentation Dataset
The dataset is a collection of 3D multi-modality MRI spine images for intervertebral disc localization and segmentation. -
DukeMTMC-VideoReID
The video-based person re-identification (ReID) aims to identify the given pedestrian video sequence across multiple non-overlapping cameras. -
Custom traffic gesture dataset
Custom traffic gesture dataset containing measurements of eight different gestures for 35 participants. -
DreaMo: Articulated 3D Reconstruction From A Single Casual Video
A dataset of 42 animal video clips with diverse species and insufficient view coverage from the Internet. -
Rainfall datasets
Rainfall datasets from major cities across the United States -
Cross-View Training
The dataset used in the paper for semi-supervised sequence modeling with cross-view training. -
CUB 200-2011
The CUB 200-2011 dataset contains 200 classes of bird species in 11,788 images with approximately 30 examples per class in the training set. -
GP-Tree: A Gaussian Process Classifier for Few-Shot Incremental Learning
Gaussian processes (GPs) are non-parametric, flexible models that work well in many tasks. Combining GPs with deep learning methods via deep kernel learning (DKL) is especially...
