The reconstruction of textureless areas has long been a challenging prob...
Channel prediction is critical to address the channel aging issue in mob...
Energy-Based Models (EBMs) have been widely used for generative modeling...
Most video platforms provide video streaming services with different
qua...
We present a simple but effective technique to smooth out textures while...
Product Retrieval (PR) and Grounding (PG), aiming to seek image and
obje...
In a noisy conversation environment such as a dinner party, people often...
Cell instance segmentation in cytology images has significant importance...
The popularity of on-demand ride pooling is owing to the benefits offere...
Constrained Reinforcement Learning has been employed to enforce safety
c...
Can conversational videos captured from multiple egocentric viewpoints r...
AI creation, such as poem or lyrics generation, has attracted increasing...
Heterogeneous information fusion is one of the most critical issues for
...
Beyond topical relevance, passage ranking for open-domain factoid questi...
Most obstacle avoidance algorithms are only effective in specific
enviro...
Few-Shot Learning (FSL) is a challenging task, which aims to recognize n...
Previous works show the great potential of pre-trained language models (...
The mercury constitutive model predicting the strain and stress in the t...
Computational cytology is a critical, rapid-developing, yet challenging ...
The reliability of the mercury spallation target is mission-critical for...
Augmented reality devices have the potential to enhance human perception...
Cooperative Intelligent Transport System (C-ITS) is a promising network ...
The sparsely-activated models have achieved great success in natural lan...
Supersized pre-trained language models have pushed the accuracy of vario...
Pre-trained model such as BERT has been proved to be an effective tool f...
It is challenging to control a soft robot, where reinforcement learning
...
Enhanced mobile broadband (eMBB) and ultrareliable and low-latency
commu...
Context information in search sessions has proven to be useful for captu...
Designing pre-training objectives that more closely resemble the downstr...
A proactive dialogue system has the ability to proactively lead the
conv...
Augmented Reality (AR) as a platform has the potential to facilitate the...
As a simple technique to accelerate inference of large-scale pre-trained...
Recent years have witnessed great progress on building emotional chatbot...
A common shortfall of supervised learning for medical imaging is the gre...
Estimating camera wearer's body pose from an egocentric view (egopose) i...
The mobile robotic testbed is an essential and critical support to verif...
Leveraging powerful deep learning techniques, the end-to-end (E2E) learn...
With the rising incidence of some diseases, such as obesity and diabetes...
Deep Q-learning algorithms often suffer from poor gradient estimations w...
Skin conditions are reported the 4th leading cause of nonfatal disease b...
This paper presents the design, control, and applications of a multi-seg...
Tracking a crowd in 3D using multiple RGB cameras is a challenging task....
The widespread popularity of unmanned aerial vehicles enables an immense...
This paper presents a robust computationally efficient real-time collisi...
Enabling a neural network to sequentially learn multiple tasks is of gre...
In image processing, Total Variation (TV) regularization models are comm...
Nonconvex optimization algorithms with random initialization have attrac...
Urban logistics is becoming more complicated and costlier due to new
cha...
Grant-free random access (RA) with massive MIMO is a promising RA techni...
We propose novel real-time algorithm to localize hands and find their
as...