New lesion segmentation is essential to estimate the disease progression...
Current methods for few-shot segmentation (FSSeg) have mainly focused on...
The task of 3D single object tracking (SOT) with LiDAR point clouds is
c...
Weakly-supervised point cloud segmentation with extremely limited labels...
Weakly supervised point cloud segmentation, i.e. semantically segmenting...
Semi-supervised segmentation remains challenging in medical imaging sinc...
With the development of Generative Adversarial Network, image-based virt...
In this work, we address the challenging task of few-shot segmentation.
...
Currently, the state-of-the-art methods treat few-shot semantic segmenta...
Image manipulation with natural language, which aims to manipulate image...
Fully supervised object detection has achieved great success in recent y...
Most existing virtual try-on applications require clean clothes images.
...
Fully convolutional networks (FCN) have achieved great success in human
...