Computer vision
Teaching machines to interpret and reason about the visual world, from object recognition to medical imaging.
Project
Project FDNN: FPGA-based Deep Neural Networks
This project aims to accelerate the inference and training of Deep Neural Networks (DNN) using FPGAs for high energy efficiency and low latency in data centers. We have been developing a CNN (Convolutional Neural Network) accelerator…
Publication
Image2Text: A Multimodal Caption Generator
Video
Magic Brush
Click to download video We develop the MagicBrush system, a novel painting-based image search engine. This system enables users to draw a color sketch as a query to find images. Different from existing works on…
Video
MindFinder: Finding Images by Sketching
Click to download video Sketch-based image search is a well-known and difficult problem, in which little progress has been made in the past decade in developing a large-scale and practical sketch-based search engine. We have…
Publication
Mining 3D Key-Pose-Motifs for Action Recognition
Publication
Network Morphism
Project
Deep Neural Networks
We study how to morph a well-trained neural network to a new one, and how to design advanced deep neural networks.