activity
20192024
most citedReal-time Diverse Motion In-betweening with Space-time Control

2 citations · 4 across the 5 of their papers we have counts for

collaborators

6 papers

cs.LG2021

Discovering Diverse Athletic Jumping Strategies

Zhiqi Yin, Zeshi Yang, Michiel van de Panne +1

We present a framework that enables the discovery of diverse and natural-looking motion strategies for athletic skills such as the high jump. The strategies are realized as control…

cs.GR2021

Efficient Hyperparameter Optimization for Physics-based Character Animation

Zeshi Yang, Zhiqi Yin

Physics-based character animation has seen significant advances in recent years with the adoption of Deep Reinforcement Learning (DRL). However, DRL-based learning methods are usua…

cs.GR2021

Learning and Exploring Motor Skills with Spacetime Bounds

Li-Ke Ma, Zeshi Yang, Xin Tong +2

Equipping characters with diverse motor skills is the current bottleneck of physics-based character animation. We propose a Deep Reinforcement Learning (DRL) framework that enables…

cs.RO20201 cited

Neural fidelity warping for efficient robot morphology design

Sha Hu, Zeshi Yang, Greg Mori

We consider the problem of optimizing a robot morphology to achieve the best performance for a target task, under computational resource limitations. The evaluation process for eac…

cs.CV20201 cited

Improving Skeleton-based Action Recognitionwith Robust Spatial and Temporal Features

Zeshi Yang, Kangkang Yin

Recently skeleton-based action recognition has made signif-icant progresses in the computer vision community. Most state-of-the-art algorithms are based on Graph Convolutional Netw…

cs.GR2019

Towards Robust Direction Invariance in Character Animation

Li-Ke Ma, Zeshi Yang, Baining Guo +1

In character animation, direction invariance is a desirable property. That is, a pose facing north and the same pose facing south are considered the same; a character that can walk…