Human Body Model based ID using Shape and Pose Parameters

no code implementations • 6 Dec 2023 • Aravind Sundaresan, Brian Burns, Indranil Sur, Yi Yao, Xiao Lin, Sujeong Kim

We show that when our HMID network is trained using additional shape and pose losses, it shows a significant improvement in biometric identification performance when compared to an identical model that does not use such losses.

Human Mesh Recovery

Sensor Control for Information Gain in Dynamic, Sparse and Partially Observed Environments

no code implementations • 3 Nov 2022 • J. Brian Burns, Aravind Sundaresan, Pedro Sequeira, Vidyasagar Sadhu

We present an approach for autonomous sensor control for information gathering under partially observable, dynamic and sparsely sampled environments that maximizes information about entities present in that space.

Reinforcement Learning (RL)