Demonstration venue · read-only. Every page can be browsed; the buttons that would change it are switched off. Create an account to run TaxoReview on your own data. A simulation from public publication records: the people listed were not invited and did not agree to review.
? Tutorial for this page

George Cheng

dblp:207/6854 · DBLP profile ↗
← Back
5ranked-venue papers
0as first author
3since 2021 · last 2022
0000-0002-5262-4857ORCID · reported

Domains — the database's venue-derived domains; a paper can count in several

Systems, architecture and hardware · 2 · 1 since 2021Artificial intelligence and machine learning · 1 · 1 since 2021Graphics, computer vision, multimedia, augmented reality and games · 1Applied, interdisciplinary, general and emerging computing · 1 · 1 since 2021

Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.

Computer graphics and multimedia
1 paper
Computer animation and physical simulation · 100%
Artificial intelligence
2 papers
Reinforcement learning · 100%

Topics — the 3 heaviest of 4, each with the papers that count most for it

TopicWeightPapersLastEvidence papers
Computer animation and physical simulation
character animation
0.412020
Character controllers using motion VAEs · ACM Trans. Graph. 2020
Computer animation and physical simulation
motion synthesis
0.412020
Character controllers using motion VAEs · ACM Trans. Graph. 2020
Machine learning › Reinforcement learning
goal-conditioned control
0.112020
Character controllers using motion VAEs · ACM Trans. Graph. 2020

Methods — techniques the papers use, named apart from their topics

variational autoencoder · 0.9motion capture · 0.9deep reinforcement learning · 0.9multi-critic actor learning · 0.6
YearPublicationVenuePosition
2022 Multi-Critic Actor Learning: Teaching RL Policies to Act with Style
Siddharth Mysore, George Cheng, Yunqi Zhao, Kate Saenko
ICLR2
2021 Comprehensive Analysis of High-Speed Cascaded H-Bridge (CHB) Medium-Voltage Adjustable Speed Drives
abstract
High-speed medium-voltage (MV) adjustable speed drives (ASDs) are essential for gearless direct drive systems, offering reduced size and maintenance. High-speed applications include off-shore compressors in oil and gas industry, wind energy generation, and fly-wheel energy storage systems. This paper will cover the implications to cover a higher speed range (120-500Hz), arising from retrofitting existing MV 50/60 Hz cascaded H-bridge (CHB) ASDs. An essential requirement for the ASD is to remain within the Total Harmonic Distortion (THD) and Harmonic Voltage Factor (HVF) constraints set by standards. Key-aspects affecting CHB performance at high speeds are switching frequency and number of voltage levels. Another key-aspect is the CHB power cell DC-Link operational stress, power loss, and size. A unique comprehensive analysis covering all mentioned aspects is performed to provide a view of the MV high-speed application demands and needed High-Speed CHB design considerations.
Omar Zayed, Ahmed Elezab, Mehdi Narimani, George Cheng, Navid Reza Zargari
IECON4
2021 Predictive models of aging of the human eye based on ocular anterior segment morphology
Jiaonan Ma, Xueli Xu, Yulin Lei, Xiaojin Huangfu, Xianglong Yi, George Cheng, Ji Bai, Xingwu Zhong, Ximing Xu 0002
J. Biomed. Informatics13
2020 Character controllers using motion VAEs
abstract
A fundamental problem in computer animation is that of realizing purposeful and realistic human movement given a sufficiently-rich set of motion capture clips. We learn data-driven generative models of human movement using autoregressive conditional variational autoencoders, or Motion VAEs. The latent variables of the learned autoencoder define the action space for the movement and thereby govern its evolution over time. Planning or control algorithms can then use this action space to generate desired motions. In particular, we use deep reinforcement learning to learn controllers that achieve goal-directed movements. We demonstrate the effectiveness of the approach on multiple tasks. We further evaluate system-design choices and describe the current limitations of Motion VAEs.
Hung Yu Ling, Fabio Zinno, George Cheng, Michiel van de Panne
ACM Trans. Graph.3
2013 A simple method for capacitor voltages balancing of diode-clamped multilevel converters using space vector modulation
abstract
This paper presents a new and simple method for capacitor voltages balancing of an n-level diode-clamped multilevel converters using space vector modulation (SVM). The proposed method introduces a generalized approach to calculate dc-link capacitor currents without the use of look-up tables for an n-level diode-clamped converter. This approach balances dc-link capacitor voltages based on minimum energy property. The performance of the proposed method has been studied for a three-level, four-level and five-level diode-clamped converter in MATLAB/Simulink environment.
Mehdi Narimani, Venkata Yaramasu, Navid Reza Zargari, George Cheng, Gerry Moschopoulos
IECON5