Skip to search formSkip to main contentSkip to account menu
A Wavenet for Speech Denoising
TLDR
The proposed model adaptation retains Wavenet's powerful acoustic modeling capabilities, while significantly reducing its time-complexity by eliminating its autoregressive nature.
View on IEEE
Fully-Convolutional Point Networks for Large-Scale Point Clouds
TLDR
This work proposes a general-purpose, fully-convolutional network architecture for efficiently processing large-scale 3D data and demonstrates its ability to effectively learn both low-level features as well as complex compositional relationships by evaluating it on benchmark datasets for semantic voxel segmentation, semantic part segmentation and 3D scene captioning.
View PDF on arXiv
Deep Learned Full-3D Object Completion from Single View
TLDR
A new approach to 3D reconstruction and scene understanding is proposed, which implicitly learns 3D geometry from depth maps pairing a deep convolutional neural network architecture with an auto-encoder.
View PDF on arXiv
Freeform Gesture Authentication
TLDR
By careful formulation of a free-form gesture model, this project can protect against over-theshoulder attacks and offer a much greater level of security than traditional pin, text-based, and Android’s default pattern authentication.
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy, Terms of Service, and Dataset License