activity
20192025
most citedPosition Dependent Prediction Combination For Intra-Frame Video Coding

37 citations · 53 across the 5 of their papers we have counts for

collaborators
Showing eess.IVShow all

6 papers · 1 filter

eess.IV202537 cited

Position Dependent Prediction Combination For Intra-Frame Video Coding

Amir Said, Xin Zhao, Marta Karczewicz +2

Intra-frame prediction in the High Efficiency Video Coding (HEVC) standard can be empirically improved by applying sets of recursive two-dimensional filters to the predicted values…

eess.IV20253 cited

Low-Complexity Transform Adjustments For Video Coding

Amir Said, Hilmi E. Egilmez, Yung-Hsuan Chao

Recent video codecs with multiple separable transforms can achieve significant coding gains using asymmetric trigonometric transforms (DCTs and DSTs), because they can exploit dive…

eess.IV202510 cited

Highly Efficient Non-Separable Transforms for Next Generation Video Coding

Amir Said, Xin Zhao, Marta Karczewicz +3

For the last few decades, the application of signal-adaptive transform coding to video compression has been stymied by the large computational complexity of matrix-based solutions.…

eess.IV2023

New Filters for Image Interpolation and Resizing

Amir Said

We propose a new class of kernels to simplify the design of filters for image interpolation and resizing. Their properties are defined according to two parameters, specifying the w…

eess.IV20221 cited

Boosting neural video codecs by exploiting hierarchical redundancy

Reza Pourreza, Hoang Le, Amir Said +2

In video compression, coding efficiency is improved by reusing pixels from previously decoded frames via motion and residual compensation. We define two levels of hierarchical redu…

eess.IV2021

Transform Network Architectures for Deep Learning based End-to-End Image/Video Coding in Subsampled Color Spaces

Hilmi E. Egilmez, Ankitesh K. Singh, Muhammed Coban +5

Most of the existing deep learning based end-to-end image/video coding (DLEC) architectures are designed for non-subsampled RGB color format. However, in order to achieve a superio…