43 citations · 162 across the 29 of their papers we have counts for
34 papers
Graph Fourier Transform Enhancement through Envelope Extensions
Ali Bagheri Bardi, Taher Yazdanpanah, Milos Dakovic +1
Many real-world networks are characterized by directionality; however, the absence of an appropriate Fourier basis hinders the effective implementation of graph signal processing t…
Fourier Analysis of Signals on Directed Acyclic Graphs (DAG) Using Graph Zero-Padding
Ljubisa Stankovic, Milos Dakovic, Ali Bagheri Bardi +2
Directed acyclic graphs (DAGs) are used for modeling causal relationships, dependencies, and flows in various systems. However, spectral analysis becomes impractical in this settin…
Eigenvalues of Symmetric Non-normalized Discrete Trigonometric Transforms
Ali Bagheri Bardi, Milos Dakovic, Taher Yazdanpanah +1
A comprehensive approach to the spectrum characterization (derivation of eigenvalues and the corresponding multiplicities) for non-normalized, symmetric discrete trigonometric tran…
Cluster-CAM: Cluster-Weighted Visual Interpretation of CNNs' Decision in Image Classification
Zhenpeng Feng, Hongbing Ji, Milos Dakovic +3
Despite the tremendous success of convolutional neural networks (CNNs) in computer vision, the mechanism of CNNs still lacks clear interpretation. Currently, class activation mappi…
Fair and skill-diverse student group formation via constrained k-way graph partitioning
Alexander Jenkins, Imad Jaimoukha, Ljubisa Stankovic +1
Forming the right combination of students in a group promises to enable a powerful and effective environment for learning and collaboration. However, defining a group of students i…
Demystifying CNNs for Images by Matched Filters
Shengxi Li, Xinyi Zhao, Ljubisa Stankovic +1
The success of convolution neural networks (CNN) has been revolutionising the way we approach and use intelligent machines in the Big Data era. Despite success, CNNs have been cons…