The current speech anti-spoofing countermeasures (CMs) show excellent
pe...
Visible and near-infrared(NIR) band sensors provide images that capture
...
Quantum computing has emerged as a promising domain for the machine lear...
Bug localization, which is used to help programmers identify the locatio...
Utilizing the large-scale unlabeled data from the target domain via
pseu...
This report describes our submission to track1 and track3 for VoxCeleb
S...
Large language models (LLMs) have demonstrated an impressive ability to
...
Automatically generating source code from natural language descriptions ...
Static analysis is the process of analyzing software code without execut...
Source code representation with deep learning techniques is an important...
ECAPA-TDNN is currently the most popular TDNN-series model for speaker
v...
Existing Deep Reinforcement Learning (DRL) algorithms suffer from sample...
A proper code evaluation metric (CEM) profoundly impacts the evolution o...
Attention-based neural networks, such as Transformers, have become ubiqu...
Developers often perform repetitive code editing activities for various
...
In the software engineering community, deep learning (DL) has recently b...
This paper describes the deepfake audio detection system submitted to th...
Imbalanced data pose challenges for deep learning based classification
m...
This paper describes the systems developed by the HCCL team for the NIST...
Recent progress on 3D scene understanding has explored visual grounding
...
Probabilistic Linear Discriminant Analysis (PLDA) was the dominant and
n...
The impression section of a radiology report summarizes the most promine...
Capturing long-range dependency and modeling long temporal contexts is p...
This paper describes the systems submitted by team HCCL to the Far-Field...
Name lookup is a key technology for the forwarding plane of content rout...
Aiming at the local overload of multi-controller deployment in
software-...
Optimising the approximation of Average Precision (AP) has been widely
s...
Over the past few years, deep neural networks (DNNs) have been continuou...
Despite the advent of deep learning in computer vision, the general
hand...
Enabling a neural network to sequentially learn multiple tasks is of gre...
With the advent of a new round of the Industrial Revolution, the Industr...
Ultra-reliable and low-latency communications (URLLC) are considered as ...
Catastrophic forgetting is a challenge issue in continual learning when ...
Understanding the internal representations of deep neural networks (DNNs...
Polar codes under successive cancellation decoding proposed by Arıkan
pr...
Buffer insertion is a popular technique to reduce the interconnect delay...