English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

In the past few years, neural character animation has emerged and offered anautomatic method for animating virtual characters. Their motion is synthesizedby a neural network. Controlling this movement in real time with a user-definedcontrol signal is also an important task in video games for example. Solutionsbased on fully-connected layers (MLPs) and Mixture-of-Experts (MoE) have givenimpressive results in generating and controlling various movements withclose-range interactions between the environment and the virtual character.However, a major shortcoming of fully-connected layers is their computationaland memory cost which may lead to sub-optimized solution. In this work, weapply pruning algorithms to compress an MLP- MoE neural network in the contextof interactive character animation, which reduces its number of parameters andaccelerates its computation time with a trade-off between this acceleration andthe synthesized motion quality. This work demonstrates that, with the samenumber of experts and parameters, the pruned model produces less motionartifacts than the dense model and the learned high-level motion features aresimilar for both

Towards Lightweight Neural Animation : Exploration of Neural Network Pruning in Mixture of Experts-based Animation Models