Due to the mutual occlusion, severe scale variation, and complex spatial...
Incorporating physics in human motion capture to avoid artifacts like
fl...
Point cloud registration is a task to estimate the rigid transformation
...
Pulmonary nodules and masses are crucial imaging features in lung cancer...
As a promising field, Multi-Query Image Retrieval (MQIR) aims at searchi...
Soft object manipulation tasks in domestic scenes pose a significant
cha...
The recent multi-modality models have achieved great performance in many...
Conventional cameras capture image irradiance on a sensor and convert it...
Multi-instance point cloud registration is the problem of estimating mul...
Top-down methods dominate the field of 3D human pose and shape estimatio...
Considering the prevalence of the power-law distribution in user-item
ne...
Image signal processing (ISP) is crucial for camera imaging, and neural
...
The event camera is a bio-vision inspired camera with high dynamic range...
Graph neural networks generalize conventional neural networks to
graph-s...
Instance segmentation in 3D scenes is fundamental in many applications o...
In recent years, the robotics community has made substantial progress in...
Category-level 6D object pose and size estimation is to predict 9
degree...
How to estimate the quality of the network output is an important issue,...
Illumination estimation is the essential step of computational color
con...
This paper reviews the NTIRE 2020 challenge on real image denoising with...
Current end-to-end deep learning driving models have two problems: (1) P...
In this paper, we propose a geometry-contrastive generative adversarial
...
We develop a model of perceptual similarity judgment based on re-trainin...
In this paper, we address the problem of searching action proposals in
u...