We study how choices of input point cloud coordinate frames impact learn...
RGB-D semantic segmentation has attracted increasing attention over the ...
Convolutional layers are the core building blocks of Convolutional Neura...
Existing CNN-based methods for pixel labeling heavily depend on multi-sc...
Learning disentangled representations of data is a fundamental problem i...
To efficiently extract spatiotemporal features of video for action
recog...
Unsupervised domain adaptation aims at learning a shared model for two
r...
We present a simple and general framework for feature learning from poin...
We present a simple and general framework for feature learning from poin...
We introduce a large-scale 3D shape understanding benchmark using data a...
Understanding semantic similarity among images is the core of a wide ran...
Object cutout is a fundamental operation for image editing and manipulat...
Building discriminative representations for 3D data has been an importan...
Human 3D pose estimation from a single image is a challenging task with
...