Mohan Zhou
Papers
1
Total Citations
48
H-Index
1
About
Mohan Zhou is a leading researcher in computer vision and generative AI, with a primary focus on human-centric content synthesis. His work centers on the challenging task of generating realistic, responsive virtual avatars, particularly through the creation of lifelike talking heads and listening agents. Zhou’s most impactful contribution is the introduction of a benchmark dataset and baseline for responsive listening head generation, a paper that has garnered 48 citations since 2022. This work addresses a critical gap in human-computer interaction by enabling avatars to exhibit natural, context-aware listening behaviors, moving beyond simple speech generation to capture the nuances of non-verbal communication. By providing a standardized evaluation framework, Zhou has catalyzed further research in this nascent field. His achievements are notable for bridging the gap between generative models and real-time interactive systems, with potential applications in virtual reality, telepresence, and digital assistants. Zhou’s research is essential reading for anyone interested in the frontier of believable digital humans.
Research Focus
Key Achievements
Top Papers
- 1Responsive Listening Head Generation: A Benchmark Dataset and Baseline48 citations · 2022