Justin Uang
Papers
1
Total Citations
56
H-Index
1
About
Justin Uang is a researcher whose work sits at the intersection of computer vision and robotics, with a particular focus on advancing object instance recognition. His most influential contribution, the 2013 paper "Multimodal blending for high-accuracy instance recognition" (56 citations), tackles a persistent challenge in robotic perception: reliably detecting specific objects in cluttered, real-world environments. Uang’s key insight was to leverage multimodal sensor data—such as the depth and color information from Microsoft Kinect—and blend them in a novel way to dramatically improve recognition accuracy, especially in the common tabletop setting. This work directly addressed the limitations of systems that relied solely on texture or shape, offering a more robust solution for robots interacting with their surroundings. By demonstrating how to fuse different sensory streams for high-accuracy detection, Uang helped lay the groundwork for more capable and adaptable robotic systems, making his research a valuable reference for students and engineers working on perception for autonomous manipulation.
Research Focus
Key Achievements
Top Papers
- 1Multimodal blending for high-accuracy instance recognition56 citations · 2013