Skip to main content

One-for-All: Grouped Variation Network-Based Fractional Interpolation in Video Coding

Fractional interpolation is used to provide sub-pixel level references for motion compensation in the interprediction of video coding, which attempts to remove temporal redundancy in video sequences. Traditional handcrafted fractional interpolation filters face the challenge of modeling discontinuous regions in videos, while existing deep learning-based methods are either designed for a single quantization parameter (QP), only generating half-pixel samples, or need to train a model for each sub-pixel position.

CNN Fixations: An Unraveling Approach to Visualize the Discriminative Image Regions

Deep convolutional neural networks (CNNs) have revolutionized the computer vision research and have seen unprecedented adoption for multiple tasks, such as classification, detection, and caption generation. However, they offer little transparency into their inner workings and are often treated as black boxes that deliver excellent performance.

Special Issue on Contactless Monitoring of Critical Infrastructure

Industrial control systems (ICSs) manage and monitor critical civil or military infrastructure, such as water treatment facilities, power plants, electricity grids, transportation systems, oil and gas refineries, and health care. Because they are so important, ICSs are becoming attractive targets for malicious attacks that could lead to catastrophic failures with substantive impacts.

Reconfigurable High Speed Optical Signal Processing Using Optical Frequency Comb for High-Capacity, Spectrally Efficient Fiber Optic Systems and Networks

Optical fiber communication systems provide the infrastructure for high-capacity data transfer. The field has shown dramatic increases in transmission capacity, and yet the demand for capacity also grows significantly. We are in a situation in which systems must continually grow in capacity to keep pace with the demand, thereby necessitating continual innovation and technical advances.