Jiebo Luo

University of Rochester, Carestream (United States)

Papers

Total Citations

H-Index

About

Jiebo Luo is a leading figure in computer vision and multimedia, with a particular focus on predictive scene parsing and generative adversarial networks (GANs). His most impactful work, "STC-GAN: Spatio-Temporally Coupled Generative Adversarial Networks for Predictive Scene Parsing" (2020, 52 citations), introduces a novel framework that assigns pixel-level semantic labels to future video frames—a critical capability for autonomous driving and robot navigation. By coupling spatial and temporal dynamics, Luo’s approach advances the ability of AI systems to anticipate and interpret visual scenes in real time, bridging gaps in video understanding. Earlier in his career, he contributed to the foundational challenges of mobile multimedia, co-editing a special issue on "Multimedia over Mobile IP" (2002, 8 citations) that explored wireless communication and Internet convergence. His work on "Real-time one-dimensional motion estimation and its application in computer vision" (2015, 3 citations) further demonstrates his versatility in motion analysis. With a career spanning over two decades, Luo’s research has consistently pushed boundaries in AI-driven visual intelligence, earning him recognition as a pioneer in predictive scene parsing and a key influencer in the evolution of multimedia systems.