Federated Learning (FL) has emerged as a promising approach to enable
co...
Task-conditional architecture offers advantage in parameter efficiency b...
Most existing ultra-high resolution (UHR) segmentation methods always
st...
To overcome the domain gap between synthetic and real-world datasets,
un...
With the increasing interest and rapid development of methods for Ultra-...
Existing knowledge distillation works for semantic segmentation mainly f...
Detection of human body and its parts (e.g., head or hands) has been
int...
Existing head pose estimation (HPE) mainly focuses on single person with...
In this work, we investigate a simple and must-known conditional generat...
The detection of human body and its related parts (e.g., face, head or h...
Most recent head pose estimation (HPE) methods are dominated by the Eule...
The message-passing scheme is the core of graph representation learning....
Each student matters, but it is hardly for instructors to observe all th...
Domain adaptive object detection (DAOD) aims to alleviate transfer
perfo...
Data-efficient learning on graphs (GEL) is essential in real-world
appli...
Federated learning (FL) faces three major difficulties: cross-domain,
he...
Human body orientation estimation (HBOE) is widely applied into various
...
The normalizing layer has become one of the basic configurations of deep...
In this work we address multi-target domain adaptation (MTDA) in semanti...
Learning scene flow from a monocular camera still remains a challenging ...
Fully-supervised crowd counting is a laborious task due to the large amo...
Video surveillance systems have been installed to ensure the student saf...
Utilizing trimap guidance and fusing multi-level features are two import...
Single image super-resolution(SISR) is an ill-posed problem that aims to...
Crowd counting aims to learn the crowd density distributions and estimat...
Sequential recommendation as an emerging topic has attracted increasing
...
Person re-identification (re-id) aims to match the same person from imag...
We study on image super-resolution (SR), which aims to recover realistic...
The recent development of light-weighted neural networks has promoted th...
Natural image matting is a fundamental problem in computational photogra...
Generating natural and accurate descriptions in image cap-tioning has al...
Over the last few years, deep learning based approaches have achieved
ou...
Recently, significant progress has been achieved in deep image matting. ...
There are many factors affecting visual face recognition, such as low
re...
Nowadays, skeleton information in videos plays an important role in
huma...
Like many computer vision problems, human pose estimation is a challengi...
Existing pose estimation approaches can be categorized into single-stage...
Most attention-based image captioning models attend to the image once pe...
Recently, supervised hashing methods have attracted much attention since...
Sparse coding (SC) is an automatic feature extraction and selection tech...
Sparse coding (SC) is an unsupervised learning scheme that has received ...
Recent advance of large scale similarity search involves using deeply le...
In many applications, the pairwise constraint is a kind of weaker superv...
Click through rate (CTR) prediction of image ads is the core task of onl...
Spectral clustering is one of the most popular clustering approaches wit...
We introduce a novel dictionary optimization method for high-dimensional...