Search Results for author:
Found 5 papers, 1 papers with code
Neural Network Assisted Lifting Steps For Improved Fully Scalable Lossy Image Compression in JPEG 2000
The proposed approach involves two steps, a high-to-low step followed by a low-to-high step.
Exploration of Learned Lifting-Based Transform Structures for Fully Scalable and Accessible Wavelet-Like Image Compression
Moreover, we demonstrate that employing more learned lifting steps and more layers in each learned lifting operator do not contribute strongly to the compression performance.
Efficient Motion Modelling with Variable-sized blocks from Hierarchical Cuboidal Partitioning
Specifically, we have constructed motion-compensated current frame using the cuboidal partitioning information of the anchor frame in a group-of-picture (GOP).
Human-Machine Collaborative Video Coding Through Cuboidal Partitioning
This is because video coding targets human perception, while feature coding aims for machine vision tasks.
Transform Quantization for CNN (Convolutional Neural Network) Compression
In this paper, we compress convolutional neural network (CNN) weights post-training via transform quantization.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
