Search Results for author: Nikos Deligiannis

Found 36 papers, 8 papers with code

Traffic Event Detection as a Slot Filling Problem

no code implementations13 Sep 2021 Xiangyu Yang, Giannis Bekoulis, Nikos Deligiannis

In particular, we experiment with several models to identify (i) whether a tweet is traffic-related or not, and (ii) in the case that the tweet is traffic-related to identify more fine-grained information regarding the event (e. g., the type of the event, where the event happened).

Event Detection Slot Filling +2

Bias Loss for Mobile Neural Networks

2 code implementations ICCV 2021 Lusine Abrahamyan, Valentin Ziatchin, Yiming Chen, Nikos Deligiannis

In compact CNNs, due to the limited number of parameters, abundant features are unlikely to be obtained, and feature diversity becomes an essential characteristic.

Learned Gradient Compression for Distributed Deep Learning

no code implementations16 Mar 2021 Lusine Abrahamyan, Yiming Chen, Giannis Bekoulis, Nikos Deligiannis

In contrast, we advocate that the gradients across the nodes are correlated and propose methods to leverage this inter-node redundancy to improve compression efficiency.

Image Classification Quantization +1

Temporal Collaborative Filtering with Graph Convolutional Neural Networks

no code implementations13 Oct 2020 Esther Rodrigo Bonet, Duc Minh Nguyen, Nikos Deligiannis

Motivated by this, we propose a novel TCF method that leverages GNNs to learn user and item representations, and RNNs to model their temporal dynamics.

Collaborative Filtering Recommendation Systems

A Deep-Unfolded Reference-Based RPCA Network For Video Foreground-Background Separation

no code implementations2 Oct 2020 Huynh Van Luong, Boris Joukovsky, Yonina C. Eldar, Nikos Deligiannis

This paper proposes a new deep-unfolding-based network design for the problem of Robust Principal Component Analysis (RPCA) with application to video foreground-background separation.

Interpretable Deep Multimodal Image Super-Resolution

no code implementations7 Sep 2020 Iman Marivani, Evaggelia Tsiligianni, Bruno Cornelis, Nikos Deligiannis

Multimodal image super-resolution (SR) is the reconstruction of a high resolution image given a low-resolution observation with the aid of another image modality.

Image Super-Resolution

Graph Convolutional Neural Networks with Node Transition Probability-based Message Passing and DropNode Regularization

no code implementations28 Aug 2020 Tien Huu Do, Duc Minh Nguyen, Giannis Bekoulis, Adrian Munteanu, Nikos Deligiannis

Among the existing GCNNs, many methods can be viewed as instances of a neural message passing motif; features of nodes are passed around their neighbors, aggregated and transformed to produce better nodes' representations.

Data Augmentation Graph Classification

Interpretable Deep Recurrent Neural Networks via Unfolding Reweighted $\ell_1$-$\ell_1$ Minimization: Architecture Design and Generalization Analysis

no code implementations18 Mar 2020 Huynh Van Luong, Boris Joukovsky, Nikos Deligiannis

In this line of research, this paper develops a novel deep recurrent neural network (coined reweighted-RNN) by the unfolding of a reweighted $\ell_1$-$\ell_1$ minimization algorithm and applies it to the task of sequential signal reconstruction.

Multimodal Deep Unfolding for Guided Image Super-Resolution

no code implementations21 Jan 2020 Iman Marivani, Evaggelia Tsiligianni, Bruno Cornelis, Nikos Deligiannis

The deep unfolding architecture is used as a core component of a multimodal framework for guided image super-resolution.

Image Super-Resolution Multimodal Deep Learning

DeepFPC: Deep Unfolding of a Fixed-Point Continuation Algorithm for Sparse Signal Recovery from Quantized Measurements

no code implementations2 Dec 2019 Peng Xiao, Bin Liao, Nikos Deligiannis

We present DeepFPC, a novel deep neural network designed by unfolding the iterations of the fixed-point continuation algorithm with one-sided l1-norm (FPC-l1), which has been proposed for solving the 1-bit compressed sensing problem.

Deep Coupled-Representation Learning for Sparse Linear Inverse Problems with Side Information

no code implementations4 Jul 2019 Evaggelia Tsiligianni, Nikos Deligiannis

In linear inverse problems, the goal is to recover a target signal from undersampled, incomplete or noisy linear measurements.

Multimodal Deep Learning Representation Learning

Fake News Detection using Deep Markov Random Fields

no code implementations NAACL 2019 Duc Minh Nguyen, Tien Huu Do, Robert Calderbank, Nikos Deligiannis

While the correlations among news articles have been shown to be effective cues for online news analysis, existing deep-learning-based methods often ignore this information and only consider each news article individually.

Fake News Detection

Designing recurrent neural networks by unfolding an l1-l1 minimization algorithm

1 code implementation18 Feb 2019 Hung Duy Le, Huynh Van Luong, Nikos Deligiannis

We propose a new deep recurrent neural network (RNN) architecture for sequential signal reconstruction.

Geometric Matrix Completion with Deep Conditional Random Fields

no code implementations29 Jan 2019 Duc Minh Nguyen, Robert Calderbank, Nikos Deligiannis

We consider matrix completion as a structured prediction problem in a conditional random field (CRF), which is characterized by a maximum a posterior (MAP) inference, and we propose a deep model that predicts the missing entries by solving the MAP inference problem.

Matrix Completion Recommendation Systems +1

Matrix Factorization via Deep Learning

no code implementations4 Dec 2018 Duc Minh Nguyen, Evaggelia Tsiligianni, Nikos Deligiannis

Matrix completion is one of the key problems in signal processing and machine learning.

Matrix Completion

Matrix Completion With Variational Graph Autoencoders: Application in Hyperlocal Air Quality Inference

no code implementations5 Nov 2018 Tien Huu Do, Duc Minh Nguyen, Evaggelia Tsiligianni, Angel Lopez Aguirre, Valerio Panzica La Manna, Frank Pasveer, Wilfried Philips, Nikos Deligiannis

Existing inference methods typically use low spatial resolution data collected by fixed monitoring stations and infer the concentration of air pollutants using additional types of data, e. g., meteorological and traffic information.

Air Quality Inference Matrix Completion

Regularizing Autoencoder-Based Matrix Completion Models via Manifold Learning

no code implementations4 Jul 2018 Duc Minh Nguyen, Evaggelia Tsiligianni, Robert Calderbank, Nikos Deligiannis

Specifically, we propose an autoencoder-based matrix completion model that performs prediction of the unknown matrix values as a main task, and manifold learning as an auxiliary task.

Matrix Completion Multi-Task Learning

Extendable Neural Matrix Completion

no code implementations13 May 2018 Duc Minh Nguyen, Evaggelia Tsiligianni, Nikos Deligiannis

Matrix completion is one of the key problems in signal processing and machine learning, with applications ranging from image pro- cessing and data gathering to classification and recommender sys- tems.

Matrix Completion

Twitter User Geolocation using Deep Multiview Learning

no code implementations11 May 2018 Tien Huu Do, Duc Minh Nguyen, Evaggelia Tsiligianni, Bruno Cornelis, Nikos Deligiannis

Predicting the geographical location of users on social networks like Twitter is an active research topic with plenty of methods proposed so far.

Multiview Learning

Online Decomposition of Compressive Streaming Data Using $n$-$\ell_1$ Cluster-Weighted Minimization

no code implementations8 Feb 2018 Huynh Van Luong, Nikos Deligiannis, Søren Forchhammer, André Kaup

The proposed decomposition solves an $n$-$\ell_1$ cluster-weighted minimization to decompose a sequence of frames (or vectors), into sparse and low-rank components, from compressive measurements.

Multiview Deep Learning for Predicting Twitter Users' Location

no code implementations21 Dec 2017 Tien Huu Do, Duc Minh Nguyen, Evaggelia Tsiligianni, Bruno Cornelis, Nikos Deligiannis

In the context of Twitter user geolocation, we realize MENET with textual, network, and metadata features.

Multiview Learning

Multimodal Image Super-resolution via Joint Sparse Representations induced by Coupled Dictionaries

1 code implementation25 Sep 2017 Pingfan Song, Xin Deng, João F. C. Mota, Nikos Deligiannis, Pier Luigi Dragotti, Miguel R. D. Rodrigues

This paper proposes a new approach to construct a high-resolution (HR) version of a low-resolution (LR) image given another HR image modality as reference, based on joint sparse representations induced by coupled dictionaries.

Dictionary Learning Image Super-Resolution

Deep Learning Sparse Ternary Projections for Compressed Sensing of Images

1 code implementation28 Aug 2017 Duc Minh Nguyen, Evaggelia Tsiligianni, Nikos Deligiannis

Compressed sensing (CS) is a sampling theory that allows reconstruction of sparse (or compressible) signals from an incomplete number of measurements, using of a sensing mechanism implemented by an appropriate projection matrix.

Incorporating Prior Information in Compressive Online Robust Principal Component Analysis

1 code implementation24 Jan 2017 Huynh Van Luong, Nikos Deligiannis, Jurgen Seiler, Soren Forchhammer, Andre Kaup

In addition, we apply the proposed algorithm to online video foreground and background separation from compressive measurements.

Distributed Coding of Multiview Sparse Sources with Joint Recovery

no code implementations18 Jul 2016 Huynh Van Luong, Nikos Deligiannis, Søren Forchhammer, André Kaup

In support of applications involving multiview sources in distributed object recognition using lightweight cameras, we propose a new method for the distributed coding of sparse sources as visual descriptor histograms extracted from multiview images.

Object Recognition

Multi-modal dictionary learning for image separation with application in art investigation

no code implementations14 Jul 2016 Nikos Deligiannis, Joao F. C. Mota, Bruno Cornelis, Miguel R. D. Rodrigues, Ingrid Daubechies

Our dictionary learning framework can be tailored both to a single- and a multi-scale framework, with the latter leading to a significant performance improvement.

Dictionary Learning

X-ray image separation via coupled dictionary learning

no code implementations20 May 2016 Nikos Deligiannis, João F. C. Mota, Bruno Cornelis, Miguel R. D. Rodrigues, Ingrid Daubechies

In support of art investigation, we propose a new source sepa- ration method that unmixes a single X-ray scan acquired from double-sided paintings.

Dictionary Learning

Measurement Bounds for Sparse Signal Reconstruction with Multiple Side Information

no code implementations10 May 2016 Huynh Van Luong, Jurgen Seiler, Andre Kaup, Soren Forchhammer, Nikos Deligiannis

To address this problem, we theoretically study a generic \textcolor{black}{weighted $n$-$\ell_{1}$ minimization} framework and propose a reconstruction algorithm that leverages multiple side information signals (RAMSI).

Object Recognition

Vectors of Locally Aggregated Centers for Compact Video Representation

no code implementations13 Sep 2015 Alhabib Abbas, Nikos Deligiannis, Yiannis Andreopoulos

We create vectors of locally aggregated centers (VLAC) by first clustering SIFT features to obtain local feature centers (LFCs) and then encoding the latter with respect to given centers of local feature centers (CLFCs), extracted from a training set.

Video Description

Compressed Sensing with Prior Information: Optimal Strategies, Geometry, and Bounds

2 code implementations22 Aug 2014 Joao F. C. Mota, Nikos Deligiannis, Miguel R. D. Rodrigues

Our bounds and geometrical interpretations reveal that if the prior information has good enough quality, L1-L1 minimization improves the performance of CS dramatically.

Information Theory Information Theory

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