Search Results for author: Aggelos K. Katsaggelos

Found 38 papers, 12 papers with code

Sparse Bayesian Methods for Low-Rank Matrix Estimation

no code implementations25 Feb 2011 S. Derin Babacan, Martin Luessi, Rafael Molina, Aggelos K. Katsaggelos

Recovery of low-rank matrices has recently seen significant activity in many areas of science and engineering, motivated by recent theoretical results for exact reconstruction guarantees and interesting practical applications.

Matrix Completion

Robust and Low-Rank Representation for Fast Face Identification with Occlusions

1 code implementation8 May 2016 Michael Iliadis, Haohong Wang, Rafael Molina, Aggelos K. Katsaggelos

In this paper we propose an iterative method to address the face identification problem with block occlusions.

Face Identification

DeepBinaryMask: Learning a Binary Mask for Video Compressive Sensing

1 code implementation12 Jul 2016 Michael Iliadis, Leonidas Spinoulas, Aggelos K. Katsaggelos

In this paper, we propose a novel encoder-decoder neural network model referred to as DeepBinaryMask for video compressive sensing.

Compressive Sensing Video Compressive Sensing +1

Compressive Holographic Video

no code implementations27 Oct 2016 Zihao Wang, Leonidas Spinoulas, Kuan He, Huaijin Chen, Lei Tian, Aggelos K. Katsaggelos, Oliver Cossairt

Compressive holography has been introduced as a method that allows 3D tomographic reconstruction at different depths from a single 2D image.

4D reconstruction Super-Resolution

Deep Multi-view Models for Glitch Classification

no code implementations28 Apr 2017 Sara Bahaadini, Neda Rohani, Scott Coughlin, Michael Zevin, Vicky Kalogera, Aggelos K. Katsaggelos

Non-cosmic, non-Gaussian disturbances known as "glitches", show up in gravitational-wave data of the Advanced Laser Interferometer Gravitational-wave Observatory, or aLIGO.

Classification General Classification +1

Efficient Video Object Segmentation via Network Modulation

1 code implementation CVPR 2018 Linjie Yang, Yanran Wang, Xuehan Xiong, Jianchao Yang, Aggelos K. Katsaggelos

Video object segmentation targets at segmenting a specific object throughout a video sequence, given only an annotated first frame.

Object Segmentation +5

DIRECT: Deep Discriminative Embedding for Clustering of LIGO Data

no code implementations7 May 2018 Sara Bahaadini, Vahid Noroozi, Neda Rohani, Scott Coughlin, Michael Zevin, Aggelos K. Katsaggelos

In this paper, benefiting from the strong ability of deep neural network in estimating non-linear functions, we propose a discriminative embedding function to be used as a feature extractor for clustering tasks.

Clustering

Generative Adversarial Networks and Perceptual Losses for Video Super-Resolution

no code implementations14 Jun 2018 Alice Lucas, Santiago Lopez Tapia, Rafael Molina, Aggelos K. Katsaggelos

Finally, we show that our proposed model, the VSRResFeatGAN model, outperforms current state-of-the-art SR models, both quantitatively and qualitatively.

Generative Adversarial Network Image Restoration +2

Adaptive Image Sampling using Deep Learning and its Application on X-Ray Fluorescence Image Reconstruction

3 code implementations27 Dec 2018 Qiqin Dai, Henry Chopp, Emeline Pouyet, Oliver Cossairt, Marc Walton, Aggelos K. Katsaggelos

We propose an XRF image inpainting approach to address the issue of long scanning time, thus speeding up the scanning process while still maintaining the possibility to reconstruct a high quality XRF image.

Binarization Image Inpainting +1

A Single Video Super-Resolution GAN for Multiple Downsampling Operators based on Pseudo-Inverse Image Formation Models

no code implementations2 Jul 2019 Santiago López-Tapia, Alice Lucas, Rafael Molina, Aggelos K. Katsaggelos

The popularity of high and ultra-high definition displays has led to the need for methods to improve the quality of videos already obtained at much lower resolutions.

Video Super-Resolution

Self-supervised Fine-tuning for Correcting Super-Resolution Convolutional Neural Networks

no code implementations30 Dec 2019 Alice Lucas, Santiago Lopez-Tapia, Rafael Molina, Aggelos K. Katsaggelos

We apply our method on the problem of fine-tuning for unseen image formation models and on removal of artifacts introduced by GANs.

Image Enhancement Video Super-Resolution

Examining the Benefits of Capsule Neural Networks

no code implementations29 Jan 2020 Arjun Punjabi, Jonas Schmid, Aggelos K. Katsaggelos

Capsule networks are a recently developed class of neural networks that potentially address some of the deficiencies with traditional convolutional neural networks.

E3D: Event-Based 3D Shape Reconstruction

1 code implementation9 Dec 2020 Alexis Baudron, Zihao W. Wang, Oliver Cossairt, Aggelos K. Katsaggelos

We first introduce an event-to-silhouette (E2S) neural network module to transform a stack of event frames to the corresponding silhouettes, with additional neural branches for camera pose regression.

3D Reconstruction 3D Shape Reconstruction

Snapshot Compressive Imaging: Principle, Implementation, Theory, Algorithms and Applications

no code implementations7 Mar 2021 Xin Yuan, David J. Brady, Aggelos K. Katsaggelos

Via novel optical designs, the 2D detector samples the HD data in a {\em compressive} manner; following this, algorithms are employed to reconstruct the desired HD data-cube.

Removing Blocking Artifacts in Video Streams Using Event Cameras

no code implementations12 May 2021 Henry H. Chopp, Srutarshi Banerjee, Oliver Cossairt, Aggelos K. Katsaggelos

In this paper, we propose EveRestNet, a convolutional neural network designed to remove blocking artifacts in videostreams using events from neuromorphic sensors.

Blocking

Visual Explanations for Convolutional Neural Networks via Latent Traversal of Generative Adversarial Networks

1 code implementation29 Oct 2021 Amil Dravid, Aggelos K. Katsaggelos

Lack of explainability in artificial intelligence, specifically deep neural networks, remains a bottleneck for implementing models in practice.

Investigating the Potential of Auxiliary-Classifier GANs for Image Classification in Low Data Regimes

no code implementations22 Jan 2022 Amil Dravid, Florian Schiffers, Yunan Wu, Oliver Cossairt, Aggelos K. Katsaggelos

Generative Adversarial Networks (GANs) have shown promise in augmenting datasets and boosting convolutional neural networks' (CNN) performance on image classification tasks.

Classification Image Classification +1

medXGAN: Visual Explanations for Medical Classifiers through a Generative Latent Space

1 code implementation11 Apr 2022 Amil Dravid, Florian Schiffers, Boqing Gong, Aggelos K. Katsaggelos

Despite the surge of deep learning in the past decade, some users are skeptical to deploy these models in practice due to their black-box nature.

Compressive Ptychography using Deep Image and Generative Priors

no code implementations5 May 2022 Semih Barutcu, Doğa Gürsoy, Aggelos K. Katsaggelos

However, reconstructions with less number of scan points lead to imaging artifacts and significant distortions, hindering a quantitative evaluation of the results.

A Deep Generative Approach to Oversampling in Ptychography

no code implementations28 Jul 2022 Semih Barutcu, Aggelos K. Katsaggelos, Doğa Gürsoy

Traditional approaches with reduced overlap between scanning areas result in reconstructions with artifacts.

DeepCOVID-Fuse: A Multi-modality Deep Learning Model Fusing Chest X-Radiographs and Clinical Variables to Predict COVID-19 Risk Levels

no code implementations20 Jan 2023 Yunan Wu, Amil Dravid, Ramsey Michael Wehbe, Aggelos K. Katsaggelos

The pre-trained fusion model with only CXRs as input increases accuracy to 0. 632 and AUC to 0. 813 and with only clinical variables as input increases accuracy to 0. 539 and AUC to 0. 733.

The secret of immersion: actor driven camera movement generation for auto-cinematography

no code implementations29 Mar 2023 Xinyi Wu, Haohong Wang, Aggelos K. Katsaggelos

The experimental results indicate that our proposed camera control system can efficiently offer immersive cinematic videos, both quantitatively and qualitatively, based on a fine-grained immersive shooting.

Video-Specific Query-Key Attention Modeling for Weakly-Supervised Temporal Action Localization

no code implementations7 May 2023 Xijun Wang, Aggelos K. Katsaggelos

To better learn these action category queries, we exploit not only the features of the current input video but also the correlation between different videos through a novel video-specific action category query learner worked with a query similarity loss.

Weakly-supervised Temporal Action Localization Weakly Supervised Temporal Action Localization

Smooth Attention for Deep Multiple Instance Learning: Application to CT Intracranial Hemorrhage Detection

1 code implementation18 Jul 2023 Yunan Wu, Francisco M. Castro-Macías, Pablo Morales-Álvarez, Rafael Molina, Aggelos K. Katsaggelos

Multiple Instance Learning (MIL) has been widely applied to medical imaging diagnosis, where bag labels are known and instance labels inside bags are unknown.

Multiple Instance Learning

YOLO-Angio: An Algorithm for Coronary Anatomy Segmentation

no code implementations24 Oct 2023 Tom Liu, Hui Lin, Aggelos K. Katsaggelos, Adrienne Kline

Coronary angiography remains the gold standard for diagnosis of coronary artery disease, the most common cause of death worldwide.

Anatomy Coronary Artery Segmentation +2

Real-World Atmospheric Turbulence Correction via Domain Adaptation

no code implementations12 Feb 2024 Xijun Wang, Santiago López-Tapia, Aggelos K. Katsaggelos

Atmospheric turbulence, a common phenomenon in daily life, is primarily caused by the uneven heating of the Earth's surface.

Domain Adaptation

Explainable Transformer Prototypes for Medical Diagnoses

1 code implementation11 Mar 2024 Ugur Demir, Debesh Jha, Zheyuan Zhang, Elif Keles, Bradley Allen, Aggelos K. Katsaggelos, Ulas Bagci

Deployments of artificial intelligence in medical diagnostics mandate not just accuracy and efficacy but also trust, emphasizing the need for explainability in machine decisions.

A General Method to Incorporate Spatial Information into Loss Functions for GAN-based Super-resolution Models

no code implementations15 Mar 2024 Xijun Wang, Santiago López-Tapia, Alice Lucas, Xinyi Wu, Rafael Molina, Aggelos K. Katsaggelos

To reduce these artifacts and enhance the perceptual quality of the results, in this paper, we propose a general method that can be effectively used in most GAN-based super-resolution (SR) models by introducing essential spatial information into the training process.

Super-Resolution

Cannot find the paper you are looking for? You can Submit a new open access paper.