Knowledge graphs (KGs) are commonly used as side information to enhance
...
Recent works have explored the fundamental role of depth estimation in
m...
Although previous co-speech gesture generation methods are able to synth...
Structured text extraction is one of the most valuable and challenging
a...
To make indoor industrial cell-free massive multiple-input multiple-outp...
3D representation disentanglement aims to identify, decompose, and manip...
Prompt-based learning reformulates downstream tasks as cloze problems by...
Cross-domain text classification aims to adapt models to a target domain...
3D semantic scene completion (SSC) is an ill-posed task that requires
in...
Satisfiability Modulo Theories (SMT) has significant application in vari...
Image augmentation is a common mechanism to alleviate data scarcity in
c...
A well-designed recommender system can accurately capture the attributes...
Satisfiability Modulo Theories (SMT) refers to the problem of deciding t...
Prompting method is regarded as one of the crucial progress for few-shot...
A multicarrier-division duplex (MDD)-based cell-free (CF) scheme, namely...
The separation of training and data transmission as well as the frequent...
Prompting methods recently achieve impressive success in few-shot learni...
Adaptive text to speech (TTS) can synthesize new voices in zero-shot
sce...
Semantic information has been proved effective in scene text recognition...
As an effective strategy, data augmentation (DA) alleviates data scarcit...
Deep neural networks often have a huge number of parameters, which posts...
While recent text to speech (TTS) models perform very well in synthesizi...
Text to speech (TTS) is widely used to synthesize personal voice for a t...
Custom voice, a specific text to speech (TTS) service in commercial spee...
Pre-trained contextual representations like BERT have achieved great suc...
When trained effectively, the Variational Autoencoder (VAE) is both a
po...
In this work, we propose a method for neural dialogue response generatio...
Commonsense Reading Comprehension (CRC) is a significantly challenging t...
How to model distribution of sequential data, including but not limited ...