Learned video compression (LVC) has witnessed remarkable advancements in...
To solve the problem of poor performance of deep neural network models d...
Balancing efficiency and accuracy is a long-standing problem for deployi...
Bilevel optimization (BO) is useful for solving a variety of important
m...
We propose a family of First Hitting Diffusion Models (FHDM), deep gener...
One of the key challenges of learning an online recommendation model is ...
AI-based molecule generation provides a promising approach to a large ar...
Diffusion-based generative models have achieved promising results recent...
Vehicle Ad-hoc Networks (VANETs) act as the core of vehicular communicat...
This paper reviews the Challenge on Super-Resolution of Compressed Image...
While multi-class 3D detectors are needed in many robotics applications,...
This report, commissioned by the WTW research network, investigates the ...
Bootstrap is a principled and powerful frequentist statistical tool for
...
Many modern machine learning applications, such as multi-task learning,
...
With emerging non-volatile memories entering the mainstream market, seve...
Motivated by the rising abundance of observational data with continuous
...
Despite the great success of deep learning, recent works show that large...
Large scale deep learning provides a tremendous opportunity to improve t...
State-of-the-art NLP models can often be fooled by human-unaware
transfo...
Feature selection is a widely used dimension reduction technique to sele...
It is a recognized fact that the classification accuracy of unseen class...
Recent works in domain adaptation always learn domain invariant features...
Recurrent neural networks (RNNs) are widely used as a memory model for
s...
We propose signed splitting steepest descent (S3D), which progressively ...
In this paper, we focus on the coordinate representation in human pose
e...
Recent empirical works show that large deep neural networks are often hi...
Randomized classifiers have been shown to provide a promising approach f...
We propose a new Stein self-repulsive dynamics for obtaining diversified...
We consider the post-training quantization problem, which discretizes th...
We propose MaxUp, an embarrassingly simple, highly effective technique
f...
Stochastic gradient Markov chain Monte Carlo (MCMC) algorithms have rece...
While being the de facto standard coordinate representation in human pos...
Existing human pose estimation approaches often only consider how to imp...
Emerging Non-Volatile Memories (NVMs) are promising contenders for build...
We propose two novel samplers to produce high-quality samples from a giv...
Convolutional Neural Networks (CNNs) currently achieve state-of-the-art
...
Face alignment has witnessed substantial progress in the last decade. On...