Jun Cen

Hong Kong University of Science and Technology, Zhejiang University

Papers

Total Citations

H-Index

About

Jun Cen is a rising researcher at the intersection of 3D computer vision and robotic perception, with a focus on pushing beyond conventional closed-set paradigms. His most influential work, "Open-set 3D Object Detection" (2021, 30 citations), addresses a critical limitation in existing 3D detection systems: their inability to recognize objects outside of pre-trained categories. This contribution is foundational for robust robot perception in dynamic, unstructured environments. Cen further advances scene understanding with "BORM: Bayesian Object Relation Model for Indoor Scene Recognition" (2021, 17 citations), which innovatively transfers human-like object knowledge—such as spatial and functional relationships—into machine scene recognition, bridging a key gap between human cognition and AI. His work "Precision forward design for 3D printing using kinematic sensitivity via Jacobian matrix considering uncertainty" (2020, 18 citations) demonstrates versatility, applying probabilistic modeling to manufacturing. Collectively, Cen’s research is shaping safer, more adaptive autonomous systems, with his open-set detection work already influencing subsequent studies in safety-critical robotics. His trajectory signals a commitment to making AI perception as flexible and context-aware as human vision.