Classical machine learning methods may lead to poor prediction performan...
Graph Neural Network (GNN)-based models have become the mainstream appro...
A fundamental problem of every intermittently-powered sensing system is ...
Training a dialogue policy using deep reinforcement learning requires a ...
In this paper, we formally address universal object detection, which aim...
The progress of LiDAR-based 3D object detection has significantly enhanc...
We present Antler, which exploits the affinity between all pairs of task...
As a new realm of AI security, backdoor attack has drew growing attentio...
Adapting speaker recognition systems to new environments is a widely-use...
Automatic speaker verification systems are vulnerable to a variety of ac...
6-DoF grasp pose detection of multi-grasp and multi-object is a challeng...
Decomposition-based evolutionary algorithms have become fairly popular f...
Current instance segmentation methods rely heavily on pixel-level annota...
Audio analysis for forensic speaker verification offers unique challenge...
Disability is an important factor affecting todays society. At the same ...
Depth estimation is solved as a regression or classification problem in
...
Semi-supervised learning aims to leverage a large amount of unlabeled da...
In this paper, we delve into semi-supervised object detection where unla...
Dialogue policy learning based on reinforcement learning is difficult to...
Traditionally, the performance of non-native mispronunciation verificati...
Forensic audio analysis for speaker verification offers unique challenge...
Environmental air quality affects people's life, obtaining real-time and...
Recently it has shown that the policy-gradient methods for reinforcement...
We present EMPHASIS, an emotional phoneme-based acoustic model for speec...