Co-speech gesture generation is crucial for automatic digital avatar
ani...
We propose an efficient deep learning method for single image defocus
de...
Zero-shot text-to-speech aims at synthesizing voices with unseen speech
...
Conventional reinforcement learning (RL) needs an environment to collect...
Transcranial temporal interference stimulation (tTIS) has been reported ...
Unsupervised video domain adaptation is a practical yet challenging task...
Unsupervised cross-lingual speech representation learning (XLSR) has rec...
Recent years have witnessed tremendous interest in deep learning on
grap...
Data scarcity is a tremendous challenge in causal effect estimation. In ...
Intent detection and slot filling are two fundamental tasks for building...
Domain adaptation is an important but challenging task. Most of the exis...
Feature-based transfer is one of the most effective methodologies for
tr...
Numerous deep reinforcement learning agents have been proposed, and each...
Imbalanced learning (IL), i.e., learning unbiased models from
class-imba...
This work is inspired by recent advances in hierarchical reinforcement
l...
Reducing domain divergence is a key step in transfer learning problems.
...
This work aims to extend the current causal inference framework to
incor...
Recent studies have revealed that neural network-based policies can be e...