no code implementations • 14 Dec 2023 • Kawisorn Kamtue, Jose M. F. Moura, Orathai Sangpetch, Paulo Garcia
Results suggest that our PhyOT can track objects in extreme conditions that the state-of-the-art deep neural networks fail while its performance in general cases does not degrade significantly from that of existing deep learning approaches.
no code implementations • 4 Mar 2023 • John Shi, Jose M. F. Moura
The paper presents the graph signal processing (GSP) companion model that naturally replicates the basic tenets of classical signal processing (DSP) for GSP.
no code implementations • 25 Mar 2022 • John Shi, Jose M. F. Moura
This paper introduces a $\textit{canonical}$ graph signal model defined by a $\textit{canonical}$ graph and a $\textit{canonical}$ shift, the $\textit{companion}$ graph and the $\textit{companion}$ shift.
1 code implementation • 11 Apr 2021 • Evgeny Toropov, Paola A. Buitrago, Jose M. F. Moura
Shuffler defines over 40 data handling operations with annotations that are commonly useful in supervised learning applied to computer vision and supports some of the most well-known computer vision datasets.
no code implementations • 19 Mar 2021 • John Shi, Jose M. F. Moura
This paper shows that in fact one can develop a unified graph signal sampling theory with analogous interpretations in both domains just like sampling in traditional DSP.