Wen Jiang

Zhejiang University, University of Pennsylvania

Papers

Total Citations

H-Index

About

Wen Jiang is a leading researcher at the intersection of computer vision and robotics, with a primary focus on 3D human pose estimation and active perception for robotic manipulation. Their seminal survey on monocular 3D human pose estimation (2020, 52 citations) has become a foundational resource, systematically analyzing methods for recovering human pose from single RGB images and videos—a critical capability for applications in human-computer interaction, robotics, and augmented reality. This work established key taxonomies and benchmarks that continue to guide the field. More recently, Jiang has pioneered novel approaches to active sensing, introducing the "Next Best Sense" framework (2025) that combines vision and touch using FisherRF for 3D Gaussian Splatting. This work represents a significant advance in enabling robots to intelligently select optimal viewpoints and tactile interactions for scene understanding, leveraging the emerging 3DGS representation for both photorealistic and geometrically accurate modeling. Their research bridges the gap between passive perception and active exploration, with direct implications for autonomous manipulation and embodied AI.