no code implementations • 29 May 2021 • Aditya Jonnalagadda, William Yang Wang, B. S. Manjunath, Miguel P. Eckstein
We propose Foveated Transformer (FoveaTer) model, which uses pooling regions and eye movements to perform object classification tasks using a Vision Transformer architecture.
no code implementations • 18 Mar 2021 • Aditya Jonnalagadda, Iuri Frosio, Seth Schneider, Morgan McGuire, Joohwan Kim
Game publishers and anti-cheat companies have been unsuccessful in blocking cheating in online gaming.
1 code implementation • ICLR 2019 • Arturo Deza, Aditya Jonnalagadda, Miguel Eckstein
The problem of $\textit{visual metamerism}$ is defined as finding a family of perceptually indistinguishable, yet physically different images.