The in-loop filter, which constitutes an important part in modern video coding, improves both
subjective and objective quality of reconstructed frames. Lately, Convolutional Neural …

Recently, learning-based in-loop filtering has attracted lots of attention. State-of-the-art
works generally deploy computationally expensive, large-scale neural networks, which is …

We present a convolutional neural network design with additional branches after certain
convolutions so that we can extract features with differing effective receptive fields and levels …

Recently, the underlying mechanism for successful deep learning (DL) was presented
based on a quantitative method that measures the quality of a single filter in each layer of a …

The integral comb (CIC) filter is an efficient filter which is widely used in the digital down-
conversion and up-conversion of wireless communication technology. However, the level …

Convolutional Neural Network (CNN) has an amount of parameter redundancy, filter pruning
aims to remove the redundant filters and provides the possibility for the application of CNN …

Dynamic convolution has achieved significant gain in performance and computational
complexity, thanks to its powerful representation capability given limited filter number/layers …

Increasing the number of parameters seems to have improved convolutional neural
networks, eg. increasing the depth or width of the networks. In this paper, we propose a …

Improving sparsity of deep neural networks (DNNs) is essential for network compression
and has drawn much attention. In this work, we disclose a harmful sparsifying process called …