no code implementations • 21 Apr 2022 • Kaushik Balakrishnan, Devesh Upadhyay
In this paper, we consider the recently proposed Bottleneck Transformers [2], which combine CNN and multi-head self attention (MHSA) layers effectively, and we integrate it with a Transformer encoder and apply it to the task of 2D human pose estimation.
no code implementations • 10 Sep 2021 • Kaushik Balakrishnan, Devesh Upadhyay
Specifically, the latent encoding of the system is modeled as a Gaussian, and is advanced in time by using an auxiliary neural network that outputs two Koopman matrices $K_{\mu}$ and $K_{\sigma}$.
no code implementations • 5 Jan 2021 • Kaushik Balakrishnan, Punarjay Chakravarty, Shubham Shrivastava
Training robots to navigate diverse environments is a challenging problem as it involves the confluence of several different perception tasks such as mapping and localization, followed by optimal path-planning and control.
no code implementations • 9 Jun 2020 • Kaushik Balakrishnan, Devesh Upadhyay
Reaction-diffusion systems are ubiquitous in nature and in engineering applications, and are often modeled using a non-linear system of governing equations.