Browsing University of Waterloo by Supervisor "Yang, En-hui"
Now showing items 1-7 of 7
-
Coding for Data Analytics: New Information Distances
(University of Waterloo, 2020-09-03)Distance plays a vital role in many applications of data analytics. For instance, in image retrieval, organization, and management, one needs a proper similarity distance to measure the perceptual similarity between any ... -
Context Adaptive Space Quantization for Image Coding
(University of Waterloo, 2016-01-18)One of the most widely used lossy image compression formats in the world is JPEG. It operates by splitting an image into blocks, applying a frequency transform to each block, quantizing each transformed block, and entropy ... -
Deep SELECTOR-JPEG: ADAPTIVE JPEG IMAGE COMPRESSION FOR COMPUTER VISION IN IMAGE CLASSIFICATION AND HUMAN VISION
(University of Waterloo, 2021-01-18)Deep Neural Networks (DNNs) demonstrate excellent performance in many Computer Vision (CV) applications such as image classification. To meet storage/bandwidth requirements, the input images to these CV applications are ... -
Fast Intra-frame Coding Algorithm for HEVC Based on TCM and Machine Learning
(University of Waterloo, 2016-09-27)High Efficiency Video Coding (HEVC) is the latest video coding standard. Compared with the previous standard H.264/AVC, it can reduce the bit-rate by around 50% while maintaining the same perceptual quality. This performance ... -
Grammar-Based Representations of Large Sparse Binary Matrices
(University of Waterloo, 2016-10-26)Large sparse matrices representation is a fundamental problem in big data processing and analysis. In some applications dealing with large sparse matrices, the I/O of these sparse matrices is the bottleneck of the whole ... -
Image/Video Compression: Human and Computer Vision Perspectives
(University of Waterloo, 2020-05-15)As we start a new decade, image and video compression should further improve to satisfy each of the human and computer visions. Human and computer visions have different perspectives on the perceived images and videos, ... -
A Watermarking-Based Framework for Protecting Deep Image Classifiers Against Adversarial Attacks
(University of Waterloo, 2021-09-27)Although deep learning-based models have achieved tremendous success in image-related tasks, they are known to be vulnerable to adversarial examples---inputs with imperceptible, but subtly crafted perturbation which fool ...