Investigator: Gim Hee Lee. Most existing animal pose and shape estimation approaches reconstruct animal meshes with a parametric SMAL model. However, the SMAL model is learned from scans of toy animals …
Investigator: Wei Tsang Ooi. As we race forward into the digital age, and with the increasing capacity of computers to process vast amounts of data for a variety of complex tasks, …
Investigator: Angela Yao. We aim to bridge data-driven discriminative hand pose estimation with optimization-based model-fitting. Using a differentiable hand renderer that aligns estimates by comparing the rendered and input depth maps, …
Investigator: Bryan Low. How can multiple data owners collectively learn and fuse their ML models? We present two approaches. In the first work, we presents a novel Collective Online Learning of …
Investigator: Harold Soh. The principal aim of this project is to develop core techniques for learning models of other (human) agents: Artificial Theories of Mind and Body (AToM/B). We intend to …
Investigator: Harold Soh The ability of humans to navigate our environment is heavily dependent on the quality and speed of sensing. Tactile sensing, or the sensation of touch and pressure, is …