Accurately predicting the destination of taxi trajectories can have vari...
The criticality of prompt and precise traffic forecasting in optimizing
...
Backdoor attacks pose serious security threats to deep neural networks
(...
Arbitrary-oriented object detection is a relatively emerging but challen...
Clinical trials often involve the assessment of multiple endpoints to
co...
A bioequivalence study is a type of clinical trial designed to compare t...
Traffic data serves as a fundamental component in both research and
appl...
Reconfigurable intelligent surface (RIS) has emerged as a promising
tech...
With the rapid advancement of 5G networks, billions of smart Internet of...
Strategy card game is a well-known genre that is demanding on the intell...
Deep Reinforcement Learning combined with Fictitious Play shows impressi...
Training Graph Neural Networks (GNNs) on large graphs is challenging due...
With the rapid development of intelligent transportation system applicat...
Neural Architecture Search (NAS) has shown great potentials in automatic...
The performance of video frame interpolation is inherently correlated wi...
To reduce multiuser interference and maximize the spectrum efficiency in...
With the rapid development of face forgery technology, deepfake videos h...
Deep learning (DL) shows its prosperity in a wide variety of fields. The...
The surging demand for fresh information from various Internet of Things...
Realistic and diverse simulation scenarios with reactive and feasible ag...
Multi-tenant machine learning services have become emerging data-intensi...
Reconfigurable intelligent surface (RIS) is very promising for wireless
...
Pre-trained language models have achieved state-of-the-art results in va...
Traditional frame-based cameras inevitably suffer from motion blur due t...
Modern GPU datacenters are critical for delivering Deep Learning (DL) mo...
In this paper, we propose a frequency-time division network (FreqTimeNet...
Pre-trained models have achieved state-of-the-art results in various Nat...
In active visual tracking, it is notoriously difficult when distracting
...
MLOps is about taking experimental ML models to production, i.e., servin...
It is of paramount importance to achieve efficient data collection in th...
Federated learning (FL) is a promising privacy-preserving distributed ma...
RGB-D salient object detection (SOD) is usually formulated as a problem ...
Recent research on joint source channel coding (JSCC) for wireless
commu...
StarCraft, one of the most difficult esport games with long-standing his...
Competitive Self-Play (CSP) based Multi-Agent Reinforcement Learning (MA...
Coronavirus has been spreading around the world since the end of 2019. T...
The micromobility is shaping first- and last-mile travels in urban areas...
Imaging is a sophisticated process combining a plenty of photovoltaic
co...
To satisfy the stringent requirements on computational resources in the ...
Physical activities and social interactions are essential activities tha...
Designing a lightweight semantic segmentation network often requires
res...
Learning knowledge graph embedding from an existing knowledge graph is v...
We introduce Arena, a toolkit for multi-agent reinforcement learning (MA...
Video object segmentation aims at accurately segmenting the target objec...
It is important to scale out deep neural network (DNN) training for redu...
Object detection in remote sensing, especially in aerial images, remains...
Most existing deep reinforcement learning (DRL) frameworks consider eith...
Recent studies showed that single-machine graph processing systems can b...
Starcraft II (SCII) is widely considered as the most challenging Real Ti...
We study active object tracking, where a tracker takes visual observatio...