While videoconferencing is prevalent, concurrent participation channels ...
Personalized text-to-image generation has emerged as a powerful and
soug...
We propose a hybrid joint source-channel coding (JSCC) scheme, in which ...
Creating expressive, diverse and high-quality 3D avatars from highly
cus...
Non alcoholic fatty liver disease (NAFLD) is the most common cause of ch...
As a distributed learning, Federated Learning (FL) faces two challenges:...
Anomaly detection based on system logs plays an important role in intell...
Large language models (LLMs) are gaining increasing popularity in both
a...
To address the issue of poor generalization ability in end-to-end speech...
To enhance the generalization ability of the model and improve the
effec...
Molecular property prediction is an important problem in drug discovery ...
In the constant updates of the product dialogue systems, we need to retr...
The demand for intelligent industries and smart services based on big da...
Location privacy is critical in vehicular networks, where drivers'
traje...
Coronary CT angiography (CCTA) scans are widely used for diagnosis of
co...
Cross-domain image retrieval aims at retrieving images across different
...
Spatiotemporal learning, which aims at extracting spatiotemporal correla...
Harvesting question-answer (QA) pairs from customer service chatlog in t...
We present DualNER, a simple and effective framework to make full use of...
With the demand for standardized large-scale livestock farming and the
d...
Multi-target multi-camera tracking (MTMCT) plays an important role in
in...
Most of the existing semantic segmentation approaches with image-level c...
Generating precise class-aware pseudo ground-truths, a.k.a, class activa...
Few-shot text classification aims to classify the text under the few-sho...
In certain Blockchain systems, multiple Blockchains are required to oper...
Gaze estimation, which is a method to determine where a person is lookin...
Obfuscating a dataset by adding random noises to protect the privacy of
...
Aiming at two molecular graph datasets and one protein association subgr...
Versatile Video Coding (VVC) has set a new milestone in high-efficiency ...
NLP-powered automatic question generation (QG) techniques carry great
pe...
Self-supervised learning (SSL) recently has achieved outstanding success...
Image semantic segmentation aims at the pixel-level classification of im...
In this paper, we propose a distortion-aware loop filtering model to imp...
Compared with traditional task-irrelevant downsampling methods, task-ori...
Artificial neural networks have advanced the frontiers of reversible
ste...
The strong convergence rate of the Euler scheme for SDEs driven by addit...
Semantic Web (SW) technology has been widely applied to many domains suc...
Double-strand DNA breaks (DSBs) are a form of DNA damage that can cause
...
Current fully-supervised facial landmark detection methods have progress...
In this paper we present an invariance proof of three properties on Simp...
There has been many studies on improving the efficiency of shared learni...
Large-scale fine-grained image retrieval has two main problems. First, l...
In recent years, facial makeup transfer has attracted growing attention ...
Modern high-dimensional point process data, especially those from
neuros...
We present a novel lightweight convolutional neural network for point cl...
Feature encoding is essential for point cloud analysis. In this paper, w...
Thanks to technological advances leading to near-continuous time
observa...
Despite the success of neural dialogue systems in achieving high perform...
Object detection on drone-captured scenarios is a recent popular task. A...
Few-shot semantic segmentation is a challenging task of predicting objec...