Qingming Huang

University of Chinese Academy of Sciences, Chinese Academy of Sciences

Papers

Total Citations

H-Index

About

Qingming Huang is a leading researcher in 3D computer vision and embodied AI, with key contributions spanning autonomous driving, robotic perception, and human-robot interaction. His most cited work, "PIPC-3Ddet" (2023, 40+ citations), introduces a pioneering framework that harnesses perspective information and proposal correlation for 3D point cloud object detection—a foundational technology for self-driving vehicles and robotic sensing systems. This method significantly advances the accuracy of detecting objects in complex 3D environments. Huang also tackles the challenge of predictive vision through "Uncertainty-Boosted Robust Video Activity Anticipation" (2024), which addresses data uncertainty in forecasting future events for applications in robot vision and autonomous navigation. His research extends to inferential reasoning with "Inferential Visual Question Generation" (2022), which generates challenging questions from images to push the boundaries of both human and machine intelligence. By integrating uncertainty modeling, multi-modal reasoning, and 3D spatial understanding, Huang’s work drives the next generation of intelligent systems capable of perceiving, predicting, and interacting with dynamic environments.