Multiple sequence to sequence models were used to establish an end-to-en...
As one of the fundamental techniques for image editing, image cropping
d...
Recognizing written domain numeric utterances (e.g. I need 1.25.) can be...
For bidirectional joint image-text modeling, we develop variational
hete...
In this paper, we propose a novel low-tubal-rank tensor recovery model, ...
We treat shape co-segmentation as a representation learning problem and
...
We introduce CoSegNet, a deep neural network architecture for co-segment...
We present LOGAN, a deep neural network aimed at learning generic shape
...
Training recurrent neural networks (RNNs) with backpropagation through t...
We propose a convolutional neural network (CNN) denoising based method f...
This paper proposes a generic method to revise traditional neural networ...
We advocate the use of implicit fields for learning generative models of...
Data-driven generative modeling has made remarkable progress by leveragi...
The developments of deep neural networks (DNN) in recent years have ushe...
We develop deep Poisson-gamma dynamical systems (DPGDS) to model sequent...
Semantic role theory is a widely used approach for event representation....
Semantic role theory considers roles as a small universal set of unanaly...
Many distributed machine learning (ML) systems adopt the non-synchronous...
In most convolution neural networks (CNNs), downsampling hidden layers i...
Many machine learning problems involve iteratively and alternately optim...
We introduce SCORES, a recursive neural network for shape composition. O...
Gaokao is the annual academic qualification examination for college
admi...
We present Semantic WordRank (SWR), an unsupervised method for generatin...
In this paper, we present a reverberation removal approach for speaker
v...
The Fact Extraction and VERification (FEVER) shared task was launched to...
We contribute the first large-scale dataset of scene sketches, SketchySc...
We present a generative neural network which enables us to generate plau...
This short paper presents the video browsing tool of VIREO team which ha...
We present a semi-supervised co-analysis method for learning 3D shape st...
A problem not well understood in video hyperlinking is what qualifies a
...
We introduce P2P-NET, a general-purpose deep neural network which learns...
We introduce P2P-NET, a general-purpose deep neural network which learns...
We introduce BranchGAN, a novel training method that enables uncondition...
To train an inference network jointly with a deep generative topic model...
One of the commonly used approaches to modeling univariate extremes is t...
We for the first time combine generated adversarial network (GAN) with
w...
Recent deep learning (DL) models have moved beyond static network
archit...
We study the problem of conditional generative modeling based on designa...
Our task is to generate an effective summary for a given document with
s...
Developing a safe and efficient collision avoidance policy for multiple
...
Generative Adversarial Networks (GANs) have recently achieved significan...
Deep learning models can take weeks to train on a single GPU-equipped
ma...
We introduce a novel neural network architecture for encoding and synthe...
Conditional Generative Adversarial Networks (GANs) for cross-domain
imag...
Chest X-ray (CXR) is one of the most commonly prescribed medical imaging...
Many problems in image processing and computer vision (e.g. colorization...
A natural image usually conveys rich semantic content and can be viewed ...
Apprenticeship learning has recently attracted a wide attention due to i...
Robot awareness of human actions is an essential research problem in rob...
We study the problem of automatically building hypernym taxonomies from
...