Jia-Xing Zhong
Papers
2
Total Citations
5
H-Index
2
About
Jia-Xing Zhong is a leading researcher at the intersection of computer vision and robotics, with a focus on enabling intelligent, real-time interaction between machines and dynamic environments. His work centers on two key areas: **personalized on-device vision systems** and **reactive object manipulation**. In his highly cited 2024 paper, "Swiss DINO," Zhong introduces an efficient vision framework that allows robotic home appliances to perform **personal object search**—localizing and identifying user-specific items directly on the device, bypassing cloud dependency. This breakthrough has garnered **3 citations** in under a year, signaling its immediate impact on edge AI and consumer robotics. Complementing this, Zhong’s "Learning to Catch Reactive Objects with a Behavior Predictor" (2024, **2 citations**) tackles the challenge of **catching moving objects that respond to a robot’s actions**, such as a dodging toy or an evasive ball. By integrating a behavior predictor, his method advances beyond passive tracking, enabling robots to anticipate and adapt to reactive targets. Zhong’s contributions are notable for bridging theoretical models with practical, deployable systems, earning recognition for pushing the boundaries of **real-time, personalized robotics**. His work inspires students and researchers to explore how vision and prediction can make robots truly responsive to the unpredictable human world.
Research Focus
Key Achievements
Top Papers
- 1
- 2Learning to Catch Reactive Objects with a Behavior Predictor2 citations · 2024