M
Michael Iliadis
Researcher at Northwestern University
Publications - 18
Citations - 919
Michael Iliadis is an academic researcher from Northwestern University. The author has contributed to research in topics: Facial recognition system & Deep learning. The author has an hindex of 8, co-authored 18 publications receiving 623 citations. Previous affiliations of Michael Iliadis include TCL Corporation & University of Piraeus.
Papers
More filters
Journal ArticleDOI
Using Deep Neural Networks for Inverse Problems in Imaging: Beyond Analytical Methods
TL;DR: The popular neural network architectures used for imaging tasks are reviewed, offering some insight as to how these deep-learning tools can solve the inverse problem.
Journal ArticleDOI
Deep Fully-Connected Networks for Video Compressive Sensing
TL;DR: In this article, a deep learning framework for video compressive sensing is presented, which enables recovery of video frames in a few seconds at significantly improved reconstruction quality compared to previous approaches.
Journal ArticleDOI
Robust and Low-Rank Representation for Fast Face Identification With Occlusions
TL;DR: In this paper, the authors proposed an iterative method to address the face identification problem with block occlusions, which utilizes a robust representation based on two characteristics in order to model contiguous errors effectively.
Journal ArticleDOI
DeepBinaryMask: Learning a binary mask for video compressive sensing
TL;DR: The reconstruction performance is found to improve when using the trained sensing mask from the network as compared to other mask designs such as random, across a wide variety of compressive sensing reconstruction algorithms.
Posted Content
Deep Fully-Connected Networks for Video Compressive Sensing
TL;DR: A deep learning framework for video compressive sensing that enables recovery of video frames in a few seconds at significantly improved reconstruction quality compared to previous approaches and offers insights into understanding how dataset sizes and number of layers affect reconstruction performance.