Detailed technical program
Program for 27th European Signal Processing Conference
Monday, September 2 8:30 - 9:00
Check-in
Monday, September 2 9:00 - 10:30
T01.A: Deep learning for music separation
Tutorial #1:
Antoine Liutkus (Inria, LIRMM, University of Montpellier, France), Fabian-Robert Stöter (Inria, LIRMM, University of Montpellier, France)
Room 1T02.A: Portfolio Optimization in Financial Markets
Tutorial #2
Daniel P. Palomar (Hong Kong University of Science and Technology)
Room 2T03.A: Communication Networks Design: Model-Based, Data-Driven, or Both?
Tutorial #3
Alessio Zappone (University of Cassino and Southern Lazio, Italy), Marco Di Renzo (Paris-Saclay University, France), Merouane Debbah (Paris-Saclay University, France)
Room 3T04.A: Connecting the Dots: Identifying Network Structure of Complex Data via Graph Signal Processing
Tutorial #4
Gonzalo Mateo (University of Rochester, USA), Santiago Segarra (Rice University, USA)
Room 4T05.A: Point cloud coding: The status quo
Tutorial #5
Joao Ascenso (Instituto Superior Técnico, Portugal), Fernando Pereira (Instituto Superior Técnico, Portugal)
Room 5Monday, September 2 10:30 - 11:00
Coffee break
Monday, September 2 11:00 - 12:30
T01.B: Deep learning for music separation
Tutorial #1:
Antoine Liutkus (Inria, LIRMM, University of Montpellier, France), Fabian-Robert Stöter (Inria, LIRMM, University of Montpellier, France)
Room 1T02.B: Portfolio Optimization in Financial Markets
Tutorial #2
Daniel P. Palomar (Hong Kong University of Science and Technology)
Room 2T03.B: Communication Networks Design: Model-Based, Data-Driven, or Both?
Tutorial #3
Alessio Zappone (University of Cassino and Southern Lazio, Italy), Marco Di Renzo (Paris-Saclay University, France), Merouane Debbah (Paris-Saclay University, France)
Room 3T04.B: Connecting the Dots: Identifying Network Structure of Complex Data via Graph Signal Processing
Tutorial #4
Gonzalo Mateo (University of Rochester, USA), Santiago Segarra (Rice University, USA)
Room 4T05.B: Point cloud coding: The status quo
Tutorial #5
Joao Ascenso (Instituto Superior Técnico, Portugal), Fernando Pereira (Instituto Superior Técnico, Portugal)
Room 5Monday, September 2 12:30 - 14:00
Lunch break
Monday, September 2 14:00 - 15:30
T06.A: Determinantal Point Processes in Signal Processing and Machine Learning
Tutorial #6
Simon Barthelme (CNRS, University of Grenoble, France), Nicolas Tremblay (CNRS, University of Grenoble, France)
Room 1T07.A: Misspecified and Semiparametric lower bounds and their application to inference problems with Complex Elliptically Symmetric distributed data
Tutorial #7
Stefano Fortunati (University of Pisa, Italy), Fulvio Gini (University of Pisa, Italy)
Room 5T08.A: Multi-Microphone Source Localization on Manifolds
Tutorial #8
Sharon Gannot (Bar-Ilan University, Israel), Bracha Laufer-Goldshtein (Bar-Ilan University, Israel), Ronen Talmon (Technion, Israel)
Room 3T09.A: Proximal Gradient Algorithms Applications in Signal Processing
Tutorial #9
Niccolò Antonello (Idiap Research Institute, Switzerland), Panagiotis Patrinos (KU Leuven, Belgium), Toon van Waterschoot (KU Leuven, Belgium), Lorenzo Stella (Amazon Development Center, Berlin, Germany)
Room 4T10.A: Random Matrix Advances in Large Dimensional Statistics, Machine Learning and Neural Nets
Tutorial #10
Romain Couillet (Paris-Saclay University, France), Mohamed Seddik (Paris-Saclay University, France), Malik Tiomoko (Paris-Saclay University, France)
Room 2Monday, September 2 15:30 - 16:00
Coffee break
Monday, September 2 16:00 - 17:30
T06.B: Determinantal Point Processes in Signal Processing and Machine Learning
Tutorial #6
Simon Barthelme (CNRS, University of Grenoble, France), Nicolas Tremblay (CNRS, University of Grenoble, France)
Room 1T07.B: Misspecified and Semiparametric lower bounds and their application to inference problems with Complex Elliptically Symmetric distributed data
Tutorial #7
Stefano Fortunati (University of Pisa, Italy), Fulvio Gini (University of Pisa, Italy)
Room 5T08.B: Multi-Microphone Source Localization on Manifolds
Tutorial #8
Sharon Gannot (Bar-Ilan University, Israel), Bracha Laufer-Goldshtein (Bar-Ilan University, Israel), Ronen Talmon (Technion, Israel)
Room 3T09.B: Proximal Gradient Algorithms Applications in Signal Processing
Tutorial #9
Niccolò Antonello (Idiap Research Institute, Switzerland), Panagiotis Patrinos (KU Leuven, Belgium), Toon van Waterschoot (KU Leuven, Belgium), Lorenzo Stella (Amazon Development Center, Berlin, Germany)
Room 4T10.B: Random Matrix Advances in Large Dimensional Statistics, Machine Learning and Neural Nets
Tutorial #10
Romain Couillet (Paris-Saclay University, France), Mohamed Seddik (Paris-Saclay University, France), Malik Tiomoko (Paris-Saclay University, France)
Room 2Monday, September 2 17:45 - 19:30
Student Paper Competition
Poster
Rooms: Poster Area 1, Poster Area 2, Poster Area 3- On the Relation Between DOA-Vector Eigenbeam ESPRIT and Subspace Pseudointensity-Vector
- Fast Alignment of Limited Angle Tomograms by Projected Cross Correlation
- Comparing Optimization Methods of Neural Networks for Real-time Inference
- Deep Log-Likelihood Ratio Quantization
- Optimized Reference Picture Selection for Light Field Image Coding
- Gated Graph Convolutional Recurrent Neural Networks
- Waveform Optimization for FDA Radar
- A Parallel Optimization Approach on Infinity Norm Minimization Problem
- Asymptotic Karlin-Rubin's Theorem with Application to Signal Detection in a Subspace Cone
- On the Recursions of Robust COMET Algorithm for Convexly Structured Shape Matrix
- Random Matrix-Improved Estimation of the Wasserstein Distance Between Two Centered Gaussian Distributions
- A Biologically Constrained Encoding Solution for Long-Term Storage of Images onto Synthetic DNA
- Reversible Privacy Preservation Using Multi-level Encryption and Compressive Sensing
Monday, September 2 20:00 - 22:30
Welcome reception
Tuesday, September 3 8:30 - 9:30
Opening and Awards Ceremony
Room: Auditorium Gaviota
Tuesday, September 3 9:30 - 10:30
PLEN-1: Josiane Zerubia, "Marked point process models in image processing. Application to Remote Sensing"
EURASIP Fellow Inaugural Lecture
Josiane Zerubia (INRIA Sophia Antipolis Méditerranée, France)
Room: Auditorium GaviotaChair: Maria S. Greco (University of Pisa, Italy)
Tuesday, September 3 10:30 - 11:00
Coffee break
Tuesday, September 3 11:00 - 12:40
TuML1: SS3-System-Level Analysis and Optimization in Large-Scale Wireless Networks
Organizers: Marco Di Renzo, Martin Klaus Müller, Stefan Schwarz
Room 1Chairs: Marco Di Renzo (CentraleSupelec-University, France), Martin Klaus Müller (TU Wien, Austria)
- 11:00 Coverage Analysis of Relay Assisted V2I Communication in Microcellular Urban Networks
- 11:20 A Continuum Model for Route Optimization in Large-Scale Inhomogeneous Multi-Hop Wireless Networks
- 11:40 Coverage Analysis for Backscatter Communication Empowered Cellular Internet-of-Things
- 12:00 Reduced-complexity Downlink Cell-Free mmWave Massive MIMO Systems with Fronthaul Constraints
- 12:20 On Interference Pikes in Poisson Networks
TuML2: ASMSP LI - Audio and Speech Source Separation
Room 2
Chair: Emanuël Habets (International Audio Laboratories Erlangen, Germany)
- 11:00 Robust and Responsive Acoustic Pairing of Devices Using Decorrelating Time-Frequency Modelling
- 11:20 Analytical Method to Convert Circular Harmonic Expansion Coefficients for Sound Field Synthesis by Using Multipole Loudspeaker Array
- 11:40 On Room Impulse Response Measurement Using Orthogonal Periodic Sequences
- 12:00 Automatic Chord Estimation Based on a Frame-wise Convolutional Recurrent Neural Network with Non-Aligned Annotations
- 12:20 A Least Squares Narrowband DOA Estimator with Robustness Against Phase Wrapping
TuML3: BISA LI - ECG Processing
Room 3
Chair: Aydin Akan (Izmir Katip Celebi University, Turkey)
- 11:00 Deep Learning Models for Denoising of ECG Signals
- 11:20 A Single ECG Lead-Based Oscillation Index for the Quantification of Periodic Breathing in Severe Heart Failure Patients
- 11:40 Löwner-Based Tensor Decomposition for Blind Source Separation in Atrial Fibrillation ECGs
- 12:00 Compressed Sensing for the Extraction of Atrial Fibrillation Patterns from Surface Electrocardiograms
- 12:20 Validation of Baseline Wander Removal and Isoelectric Correction in Electrocardiograms Using Clustering
TuML4: SPCN LI - Massive MIMO Systems
Room 4
Chair: Xavier Mestre (Centre Tecnològic de Telecomunicacions de Catalunya (CTTC), Spain)
- 11:00 Weighted Sum Rate Maximization for Hybrid Beamforming Design in Multi-Cell Massive MIMO OFDM Systems
- 11:20 Channel Hardening, Favorable Equalization and Propagation in Wideband Massive MIMO
- 11:40 Fractional Programming for Energy Efficient Power Control in Uplink Massive MIMO Systems
- 12:00 Switch-Based Hybrid Precoding in mmWave Massive MIMO Systems
- 12:20 Efficient Distributed Processing for Large Scale MIMO Detection
TuML5: TMTSP LI - Bayesian Techniques
Room: Auditorium Gaviota
Chair: Yoann Altmann (Heriot-Watt University, School of Engineering and Physical Sciences, United Kingdom (Great Britain))
- 11:00 Diffusion Maps Particle Filter
- 11:20 Bayesian Sequential Joint Signal Detection and Signal-to-Noise Ratio Estimation
- 11:40 Efficient Adaptive Multiple Importance Sampling
- 12:00 Bayesian Robust Signal Subspace Estimation in Non-Gaussian Environment
- 12:20 Sparse Bayesian Learning for a Bilinear Calibration Model and Mismatched CRB
TuMP1: VIP PI - Multimedia and 3D Processing
Room: Poster Area 1
Chair: Rozenn Dahyot (Trinity College Dublin, Ireland)
- A Localized No-Reference Blurriness Measure for Omnidirectional Images and Video
- Visual Quality Analysis of Judder Effect on Head Mounted Displays
- Hybrid Octree-Plane Point Cloud Geometry Coding
- A Robust Roll Angle Estimation Algorithm Based on Gradient Descent
- A Composite Discriminator for GAN Based Video Super-Resolution
- Semantic Prior Based Generative Adversarial Network for Video Super-Resolution
- Deep Convolutional and LSTM Neural Network Architectures on Leap Motion Hand Tracking Data Sequences
- HMM-based Convolutional LSTM for Visual Scanpath Prediction
- TensMIL2: Improved Multiple Instance Classification Through Tensor Decomposition and Instance Selection
- Linear Approximation of Deep Neural Networks for Efficient Inference on Video Data
- A Fast Local Mode Decision for the HEVC Intra Prediction Based on Direction Detection
TuMP2: VIP PII - Computational and Spectral Imaging
Room: Poster Area 2
Chair: Patrick Le Callet (Université de Nantes, France)
- Electromagnetic Imaging of a Dielectric Micro-Structure via Convolutional Neural Networks
- Hyperspectral Complex Domain Denoising
- A Non-iterative Reconstruction Algorithm for Single Pixel Spectral Imaging with Side Information
- Multi-resolution Reconstruction Algorithm for Phase Retrieval in X-ray Crystallography
- Non-local Restoration of Sparse 3D Single-Photon Data
- Coded Aperture Design for Super-Resolution Phase Retrieval
- An Adaptive Video Acquisition Scheme for Object Tracking
- Subjective Evaluation of Light Field Image Compression Methods Based on View Synthesis
TuMP3: SiG-DML PI - Pattern Recognition
Room: Poster Area 3
Chair: Yuval Bistritz (Tel Aviv University, Israel)
- Discriminative Joint Vector and Component Reduction for Gaussian Mixture Models
- Applications of Projected Belief Networks (PBN)
- Weighted Subset Selection for Fast SVM Training
- Black-Box Decision Based Adversarial Attack with Symmetric Αlpha-Stable Distribution
- Open-Set Recognition Using Intra-Class Splitting
- Virtual Adversarial Training for Semi-supervised Verification Tasks
- Understanding Support Vector Machines with Polynomial Kernels
Tuesday, September 3 12:40 - 13:40
Lunch break
Tuesday, September 3 13:40 - 15:40
TuAL1: SS4-Advances on tensor and multi-dimensional data representation
Organizers: Laurent Albera, Marc Castella
Room 1Chairs: Laurent Albera (Université de Rennes1 & Inserm, France), Marc Castella (Institut Mines-Télécom, Télécom SudParis & UMR-CNRS 5157 SAMOVAR, France)
- 13:40 Tensor-Train Modeling for MIMO-OFDM Tensor Coding-And-Forwarding Relay Systems
- 14:00 Rank Estimation and Tensor Decomposition Using Physics-Driven Constraints for Brain Source Localization
- 14:20 Path-connectedness of Tensor Ranks
- 14:40 Identifying Stable Components of Matrix/Tensor Factorizations via Low-Rank Approximation of Inter-Factorization Similarity
- 15:00 Probabilistic Tensor Train Decomposition
- 15:20 Detecting the Rank of a Symmetric Tensor
TuAL2: SS2-Music Information Processing
Organizers: Emmanouil Benetos, Bob L. Sturm, Mark B. Sandler
Room 2Chairs: Emmanouil Benetos (Queen Mary University of London, United Kingdom (Great Britain)), Mark Sandler (Queen Mary University of London, United Kingdom (Great Britain))
- 13:40 Joint Singing Voice Separation and F0 Estimation with Deep U-Net Architectures
- 14:00 The Art of Teaching Computers: The SIMSSA Optical Music Recognition Workflow System
- 14:20 Spectral Visibility Graphs: Application to Similarity of Harmonic Signals
- 14:40 Improving Singing Voice Separation Using Deep U-Net and Wave-U-Net with Data Augmentation
- 15:00 Data Augmentation for Drum Transcription with Convolutional Neural Networks
- 15:20 Temporal Convolutional Networks for Musical Audio Beat Tracking
TuAL3: BISA LII - Signal Processing for MRI Signaling
Room 3
Chair: Joerg Keller (FernUniversitaet in Hagen, Germany)
- 13:40 fMRI BOLD Signal Decomposition Using a Multivariate Low-Rank Model
- 14:00 Online Dictionary Learning for Single-Subject fMRI Data Unmixing
- 14:20 Improved Regularized Reconstruction for Simultaneous Multi-Slice Cardiac MRI T1 Mapping
- 14:40 A Quality of Recognition Case Study: Texture-based Segmentation and MRI Quality Assessment
- 15:00 Rethinking Sampling in Parallel MRI: A Data-Driven Approach
- 15:20 Investigating Time-Varying Brain Connectivity with Functional Magnetic Resonance Imaging Using Sequential Monte Carlo
TuAL4: SiG-DML LI - Deep Learning Applications
Room 4
Chairs: Nikos Deligiannis (Vrije Universiteit Brussel, Belgium), Valery Naranjo (Polytechnic University of Valencia, Spain)
- 13:40 Power Distribution Insulators Classification Using Image Hybrid Deep Learning
- 14:00 Monaural Speech Separation with Deep Learning Using Phase Modelling and Capsule Networks
- 14:20 Multimodal Image Super-resolution via Deep Unfolding with Side Information
- 14:40 Large-scale Pollen Recognition with Deep Learning
- 15:00 Real-Time Hand Gesture Recognition Model Using Deep Learning Techniques and EMG Signals
- 15:20 Deep Learning Based Localization of Near-Field Sources with Exact Spherical Wavefront Model
TuAL5: VIP LI - Image Enhancement
Room: Auditorium Gaviota
Chair: Frederic Dufaux (CNRS, France)
- 13:40 Tone Mapped HDR Images Contrast Enhancement Using Piecewise Linear Perceptual Transformation
- 14:00 Loss Functions for Denoising Compressed Images: a Comparative Study
- 14:20 iTM-Net: Deep Inverse Tone Mapping Using Novel Loss Function Based on Tone Mapping Operator
- 14:40 IEST: Interpolation-Enhanced Shearlet Transform for Light Field Reconstruction Using Adaptive Separable Convolution
- 15:00 Audio-Visual Speech Enhancement Using Hierarchical Extreme Learning Machine
- 15:20 Optimized Reference Picture Selection for Light Field Image Coding
TuAP1: TMTSP PI - Compressed Sensing and Sparse Modeling
Room: Poster Area 1
Chair: André Ferrari (Université de Nice Sophia-Antipolis, France)
- A New Algorithm for Dictionary Learning Based on Convex Approximation
- A Novel Compressive Sensing Scheme Under the Variational Bayesian Framework
- State Space Models with Dynamical and Sparse Variances, and Inference by EM Message Passing
- Robust Compressive Spectral Image Recovery Algorithm Using Dictionary Learning and Transform Tensor SVD
- Random Gabor Multipliers for Compressive Sensing: A Simulation Study
- Impact Sounds Classification for Interactive Applications via Discriminative Dictionary Learning
- Secure Dictionary Learning for Sparse Representation
- Convex Optimization Based Sparse Learning over Networks
- Compressive Chirp Transform for Estimation of Chirp Parameters
- Malware Identification with Dictionary Learning
TuAP2: TMTSP PII - Optimization methods
Room: Poster Area 2
Chair: Patrick L. Combettes (North Carolina State University, USA)
- Improving FISTA's Speed of Convergence via a Novel Inertial Sequence
- Adaptive Localized Cayley Parametrization Technique for Smooth Optimization over the Stiefel Manifold
- A Parallel Optimization Approach on Infinity Norm Minimization Problem
- Discrete-Valued Vector Reconstruction by Optimization with Sum of Sparse Regularizers
- FISTA: Achieving a Rate of Convergence Proportional to K^-3 for Small / Medium Values of k
- Exact Multiplicative Factor Updates for Convolutional Beta-NMF in 2D
- Region-based Relaxations to Accelerate Greedy Approaches
- Fully Proximal Splitting Algorithms in Image Recovery
TuAP3: SPMuS PI - Radar
Room: Poster Area 3
Chair: Angelo Coluccia (University of Salento, Italy)
- Low-Complexity Optimization for Direction-of-Arrival Estimation via Approximate Message Passing
- Semidefinite Programming for MIMO Radar Target Localization Using Bistatic Range Measurements
- Waveform Optimization for FDA Radar
- Spatio-Temporal Waveform Design in Active Sensing Systems with Multilayer Targets
- An Adversarial Super-Resolution Remedy for Radar Design Trade-offs
- Vector-Valued KLMS Based Multiple Target Range and Velocity Estimation Using IEEE 802.11P Waveform for Autonomous Vehicle
- Fast Direct Detection of Accelerating Radar Targets
Tuesday, September 3 15:40 - 16:10
Coffee break
Tuesday, September 3 16:10 - 17:50
TuEL1: SS10-Signal processing for secure and reliable localization using terrestrial networks
Organizers: José A. del Peral-Rosado, Giuseppe Destino, Felix Antreich, Gonzalo Seco-Granados
Room 1Chair: José A. López-Salcedo (Universitat Autònoma de Barcelona, Spain)
- 16:10 LTE Ranging Measurement Using Uplink Opportunistic Signals and the SAGE Algorithm
- 16:30 Radio Positioning and Tracking of High-Speed Devices in 5G NR Networks: System Concept and Performance
- 16:50 Non-Centralized Navigation for Source Localization by Cooperative UAVs
- 17:10 Heterogeneous Network Localization with a Distributed Phased Array Composed of Cooperative Vehicles
- 17:30 Learning Methods for RSSI-based Geolocation: A Comparative Study
TuEL2: ASMSP LII - Speaker and Speech Recognition
Room 2
Chair: Jesper Rindom Jensen (Aalborg University, Denmark)
- 16:10 CNN-based Multichannel End-to-End Speech Recognition for Everyday Home Environments
- 16:30 Lip-Reading with Limited-Data Network
- 16:50 Context-Aware Neural Voice Activity Detection Using Auxiliary Networks for Phoneme Recognition, Speech Enhancement and Acoustic Scene Classification
- 17:10 DNN Speaker Embeddings Using Autoencoder Pre-Training
- 17:30 Energy Separation Algorithm Based Spectrum Estimation for Very Short Duration of Speech
TuEL3: DIS LI - Design and Implementation of Signal Processing Methods
Room 3
Chair: Gabriel Falcao (Instituto de Telecomunicações, University of Coimbra, Portugal)
- 16:10 Extending Architecture Modeling for Signal Processing Towards GPUs
- 16:30 A Low-Computation-Cycle Design of Input-Decimation Technique for RIDFT Algorithm
- 16:50 Real-Time Prototyping of Matlab-Java Code Integration for Water Sensor Networks Applications
- 17:10 Compressive Digital Receiver: First Results on Sensitivity, Dynamic Range and Instantaneous Bandwidth Measurements
- 17:30 Comparing Optimization Methods of Neural Networks for Real-time Inference
TuEL4: VIP LII - Multimedia Content Analysis
Room 4
Chair: Fernando Pérez-González (University of Vigo, Spain)
- 16:10 Compression Efficiency and Computational Cost Comparison Between AV1 and HEVC Encoders
- 16:30 Improving the Performance of Lightweight CNN Models Using Minimum Enclosing Ball Regularization
- 16:50 Collecting, Analyzing and Predicting Socially-Driven Image Interestingness
- 17:10 Face-aware Saliency Estimation Model for 360 Images
- 17:30 A Novel Resynchronization Procedure for Hand-Lips Fusion Applied to Continuous French Cued Speech Recognition
TuEL5: TMTSP LII - Detection Methods
Room: Auditorium Gaviota
Chair: Abdelhak M Zoubir (Darmstadt University of Technology, Germany)
- 16:10 Two-Channel Passive Detection Exploiting Cyclostationarity
- 16:30 Source Enumeration in Non-White Noise and Small Sample Size via Subspace Averaging
- 16:50 Kernel Based Online Change Point Detection
- 17:10 ExPACO: Detection of an Extended Pattern Under Nonstationary Correlated Noise by Patch Covariance Modeling
- 17:30 Fast Surface Detection in Single-Photon Lidar Waveforms
TuEP1: OSPA PI - Other Signal Processing Areas
Room: Poster Area 1
Chair: Carlos J Escudero (University of A Coruña, Spain)
- Estimation of Measurement-Noise Variance for Variable-Step-Size NLMS Filters
- NLOS Classification Based on RSS and Ranging Statistics Obtained from Low-Cost UWB Devices
- Multiscale Permutation Entropy: Statistical Characterization on Autoregressive and Moving Average Processes
- Compensating for Object Variability in DNN-HMM Object-Centered Human Activity Recognition
- Non-Destructive Prediction of Pork Meat Degradation Using a Stacked Autoencoder Classifier on Hyperspectral Images
- Graphical Schemes Designed to Display and Study the Long-Term Variations of Schumann Resonance
- An Environment for Gestural Interaction with 3D Virtual Musical Instruments as an Educational Tool
- GPR Antenna Localization Based on A-Scans
- Scheduling Moldable Parallel Streaming Tasks on Heterogeneous Platforms with Frequency Scaling
TuEP2: BISA PI -Biomedical signal and image processing
Room: Poster Area 2
Chair: Saeid Sanei (Nottingham Trent University & Imperial College London, United Kingdom (Great Britain))
- Imaging Experiment of Multi-Pinhole Based X-Ray Fluorescence Computed Tomography Using Rat Head Phantoms
- Derivation of Respiratory Effort from Photoplethysmography
- Advancing Speech Recognition with No Speech or with Noisy Speech
- Sequential Peak Detection for Flow Cytometry
- Multi-Exponential Relaxation Times Maps Reconstruction and Unsupervised Classification in Magnitude Magnetic Resonance Imaging
- Combining Evidences from Variable Teager Energy Source and Mel Cepstral Features for Classification of Normal vs. Pathological Voices
- Fast Alignment of Limited Angle Tomograms by Projected Cross Correlation
- Identification of Alzheimer's Disease Using Non-linguistic Audio Descriptors
TuEP3: BISA PII -Bio-inspired signal and image processing
Room: Poster Area 3
Chair: Ercan Engin Kuruoglu (CNR, Italy)
- A Novel Design Method for Digital FIR/IIR Filters Based on the Shuffle Frog-Leaping Algorithm
- Efficiency of the Bio-Inspired Leaky Integrate-and-Fire Neuron for Signal Coding
- Efficiency of the Memory Polynomial Model in Realizing Digital Twins for Gait Assessment
- Neuro-inspired Compression of RGB Images
- A Probabilistic Method to Find and Visualize Distinct Regions in Protein Sequences
- Detecting Higher Order Genomic Variant Interactions with Spectral Analysis
- Variational Bayes Color Deconvolution with a Total Variation Prior
- A Robust and Sequential Approach for Detecting Gait Asymmetry Based on Radar Micro-Doppler Signatures
Tuesday, September 3 18:00 - 19:00
3MT: Three Minutes Thesis (3MT) contest
Room: Auditorium Gaviota
Tuesday, September 3 20:00 - 22:30
Visit to the Aquarium Finisterrae
Wednesday, September 4 9:00 - 10:00
PLEN-2: Yurii Nesterov, "Relative smoothness: new paradigm in Convex Optimization"
Yurii Nesterov (Center for Operations Research and Econometrics (CORE), Université Catholique de Louvain (UCL), Belgium)
Room: Auditorium AraoChair: Marius Pesavento (Technische Universität Darmstadt & Merckstr. 25, Germany)
Wednesday, September 4 10:00 - 10:30
Coffee break
Wednesday, September 4 10:30 - 12:10
WeML1: SPCN LII - Low-Complexity Tranceiver Techniques
Room 1
Chair: Carlos Mosquera (University of Vigo, Spain)
- 10:30 Reduced Complexity Maximum Likelihood Detector for DFT-s-SEFDM Systems
- 10:50 Low-Complexity Switching Network Design for Hybrid Precoding in mmWave MIMO Systems
- 11:10 Low Complexity Robust Adaptive Beamformer Based on Parallel RLMS and Kalman RLMS
- 11:30 Low-Complexity 2-Coordinates Descent for Near-Optimal MMSE Soft-Output Massive MIMO Uplink Data Detection
- 11:50 Low-Complexity Hybrid Transceivers for Uplink Multiuser mmWave MIMO by User Clustering
WeML2: ASMSP LIII - Artificial Neural Networks in Audio Signal Processing
Room 2
Chair: Sharon Gannot (Bar-Ilan University, Israel)
- 10:30 Automatic Playlist Generation Using Convolutional Neural Networks and Recurrent Neural Networks
- 10:50 The Receptive Field as a Regularizer in Deep Convolutional Neural Networks for Acoustic Scene Classification
- 11:10 Multi-scale Aggregation of Phase Information for Complexity Reduction of CNN Based DOA Estimation
- 11:30 Deep Neural Network Based Poetic Meter Classification Using Musical Texture Feature Fusion
- 11:50 Cauchy Multichannel Speech Enhancement with a Deep Speech Prior
WeML3: BISA LIII - Deep Learning for Biomedical Applications
Room 3
Chair: Maarten De Vos (University of Oxford, United Kingdom (Great Britain))
- 10:30 Surrogate Rehabilitative Time Series Data for Image-based Deep Learning
- 10:50 On the Segmentation of Plantar Foot Thermal Images with Deep Learning
- 11:10 Deep Transfer Learning for Single-Channel Automatic Sleep Staging with Channel Mismatch
- 11:30 Computer Aid-System to Identify the First Stage of Prostate Cancer Through Deep-Learning Techniques
- 11:50 Reproducibility of Deep CNN for Biomedical Image Processing Across Frameworks and Architectures
WeML4: SiG-DML LII - Signal processing for big data.
Room 4
Chair: Emilie Chouzenoux (Université Paris-Est Marne-la-Vallée, France)
- 10:30 Quantifying Uncertainty in High Dimensional Inverse Problems by Convex Optimisation
- 10:50 Deep L1-PCA of Time-Variant Data with Application to Brain Connectivity Measurements
- 11:10 On Realizing Distributed Deep Neural Networks: An Astrophysics Case Study
- 11:30 How to Apply Random Projections to Nonnegative Matrix Factorization with Missing Entries?
- 11:50 ON-IN: An On-Node and In-Node Based Mechanism for Big Data Collection in Large-Scale Sensor Networks
WeML5: TMTSP LIII - Parameter Estimation
Room: Auditorium Arao
Chair: Daniel P Palomar (Hong Kong University of Science and Technology, Hong Kong)
- 10:30 On Multivariate non-Gaussian Scale Invariance: Fractional Lévy Processes and Wavelet Estimation
- 10:50 On the Recursions of Robust COMET Algorithm for Convexly Structured Shape Matrix
- 11:10 Semiparametric Stochastic CRB for DOA Estimation in Elliptical Data Model
- 11:30 Random Matrix-Improved Estimation of the Wasserstein Distance Between Two Centered Gaussian Distributions
- 11:50 Parameter Estimation of Heavy-Tailed AR(p) Model from Incomplete Data
WeMP1: VIP PIII - Signal processing for computer vision
Room: Poster Area 1
Chair: Athanasios Psaltis (Centre for Research and Technology Hellas, Greece)
- Deep Spatio-Temporal Modeling for Object-Level Gaze-Based Relevance Assessment
- Dual-threshold Based Local Patch Construction Method for Manifold Approximation and Its Application to Facial Expression Analysis
- Patch-Based Colour Transfer with Optimal Transport
- Super-Resolution on Degraded Low-Resolution Images Using Convolutional Neural Networks
- Harmonic Networks with Limited Training Samples
- Reversible Privacy Preservation Using Multi-level Encryption and Compressive Sensing
- BEV Object Tracking for LIDAR-based Ground Truth Generation
- Fingerspelled Alphabet Sign Recognition in Upper-Body Videos
WeMP2: SPMuS PII - Signal Processing for Sensor Arrays and Networks
Room: Poster Area 2
Chair: Florian Roemer (Fraunhofer Institute for Nondestructive Testing IZFP & Ilmenau University of Technology, Germany)
- Reducing the Bias in DRSS-Based Localization: An Instrumental Variable Approach
- Shuffled Bits in the Low-Detectability Regime
- On Acoustic Modeling for Broadband Beamforming
- Frequency Diverse Array Beampattern Synthesis with Constrained Nonlinear Programming Frequency Offsets
- Calibration of Antenna Array with Dual Channel Switched Receiver System
- Blind Calibration of Sensor Arrays for Narrowband Signals with Asymptotically Optimal Weighting
- Dual Function FH MIMO Radar System with DPSK Signal Embedding
- Scheduling Data Embedding in Dual Function Radar Networks
WeMP3: SPMuS PIII - Multichannel and Graph Signal Processing
Room: Poster Area 3
Chair: Elvin Isufi (Delft University of Technology, The Netherlands)
- A Graph Signal Processing Approach to Direction of Arrival Estimation
- An NMF-Based Approach for Hyperspectral Unmixing Using a New Multiplicative-tuning Linear Mixing Model to Address Spectral Variability
- An Unmixing-Based Change Detection Approach for Multiresolution Remote Sensing Images
- A Parallel Sparse Regularization Method for Structured Multilinear Low-Rank Tensor Decomposition
- A Privacy-Preserving Asynchronous Averaging Algorithm Based on Shamir's Secret Sharing
- Generalizing Graph Convolutional Neural Networks with Edge-Variant Recursions on Graphs
Wednesday, September 4 12:10 - 13:10
Lunch break
Wednesday, September 4 13:10 - 15:10
WeAL1: SS5-Machine Audition: recent advances and applications
Organizers: Michele Scarpiniti, Jen-Tzung Chien, Stefano Squartini
Room 1Chairs: Jen-Tzung Chien (National Chiao Tung University, Taiwan), Michele Scarpiniti (Sapienza University of Rome, Italy)
- 13:10 Sounding Industry: Challenges and Datasets for Industrial Sound Analysis
- 13:30 End-to-end Audio Classification with Small Datasets - Making It Work
- 13:50 Efficient Phase-Based Acoustic Tracking of Drones Using a Microphone Array
- 14:10 Providing Spatial Control in Personal Sound Zones Using Graph Signal Processing
- 14:30 CNN-based Virtual Microphone Signal Estimation for MPDR Beamforming in Underdetermined Situations
- 14:50 Audio-Based Epileptic Seizure Detection
WeAL2: SPMuS LI - DoA Estimation
Room 2
Chair: Dominic K. C. Ho (University of Missouri, USA)
- 13:10 ESPRIT Angles-of-Arrival Estimation with Missing Sensor Data
- 13:30 Maximum-likelihood DOA Estimation at Low SNR in Laplace-like Noise
- 13:50 Full Covariance Fitting DoA Estimation Using Partial Relaxation Framework
- 14:10 Subspace-Based Method for Direction Estimation of Coherent Signals with Arbitrary Linear Array
- 14:30 Realtime 2-D DOA Estimation Using Phase-Difference Projection (PDP)
- 14:50 Direct Localization by Partly Calibrated Arrays: A Relaxed Maximum Likelihood Solution
WeAL3: BForSec -Passive forensic analysis
Room 3
Chair: Giulia Boato (University of Trento, Italy)
- 13:10 Automated Forensic Ink Determination in Handwritten Documents by Clustering
- 13:30 Dempster-Shafer Theory for Fusing Face Morphing Detectors
- 13:50 Hue Modification Localization by Pair Matching
- 14:10 DEFACTO: Image and Face Manipulation Dataset
- 14:30 Prediction Residue Analysis in MPEG-2 Double Compressed Video Sequences
- 14:50 Reliable Demosaicing Detection for Image Forensics
WeAL4: SiG-DML LIII - Classification
Room 4
Chair: Davide Dardari (University of Bologna, Italy)
- 13:10 Data Augmentation Using Generative Adversarial Network for Environmental Sound Classification
- 13:30 Random Forest on an Embedded Device for Real-time Machine State Classification
- 13:50 Self-supervised Attention Model for Weakly Labeled Audio Event Classification
- 14:10 Online Multiscale-Data Classification Based on Multikernel Adaptive Filtering with Application to Sentiment Analysis
- 14:30 Spectral-Spatial Classification of Hyperspectral Images Using CNNs and Approximate Sparse Multinomial Logistic Regression
- 14:50 A Complete Framework of Radar Pulse Detection and Modulation Classification for Cognitive EW
WeAL5: VIP LIII - Image/Video Filtering
Room: Auditorium Arao
Chair: Fernando Pereira (Instituto Superior Técnico - Instituto de Telecomunicações & Universidade de Lisboa, Portugal)
- 13:10 SOS Boosting for Image Deblurring Algorithms
- 13:30 Statistical Modeling of the Patches DC Component for Low-Frequency Noise Reduction
- 13:50 Iterative Wiener Filtering for Deconvolution with Ringing Artifact Suppression
- 14:10 Single Image Haze Removal Using Conditional Wasserstein Generative Adversarial Networks
- 14:30 Multiple-Degradation Video Super-Resolution with Direct Inversion of the Low-Resolution Formation Model
- 14:50 Hyperspectral X-ray Denoising: Model-Based and Data-Driven Solutions
WeAP1: ASMSP PI - Speech and Voice
Room: Poster Area 1
Chair: Axel Roebel (IRCAM, France)
- ExcitNet Vocoder: A Neural Excitation Model for Parametric Speech Synthesis Systems
- Concatenated Identical DNN (CI-DNN) to Reduce Noise-Type Dependence in DNN-Based Speech Enhancement
- WGANSing: A Multi-Voice Singing Voice Synthesizer Based on the Wasserstein-GAN
- Refined WaveNet Vocoder for Variational Autoencoder Based Voice Conversion
- TV-CAR Speech Analysis Based on Regularized LP
- A Speech Reconstruction Algorithm via Iteratively Reweighted ℓ2 Minimization for MFCC Codec
- Effectiveness of Cross-Domain Architectures for Whisper-to-Normal Speech Conversion
- Front-End Feature Compensation for Noise Robust Speech Emotion Recognition
- Speech-Based Stress Classification Based on Modulation Spectral Features and Convolutional Neural Networks
- Analysing Deep Learning-Spectral Envelope Prediction Methods for Singing Synthesis
- Investigation of Reverse Mode Loudspeaker Performance in Urban Sound Classification
WeAP2: ASMSP PII - Reverberation Reduction and Signal Enhancement
Room: Poster Area 2
Chair: Mads Græsbøll Christensen (Aalborg University, Denmark)
- Performance Analysis of Diffusion Filtered-X Algorithms in Multitask ANC Systems
- Estimating & Mitigating the Impact of Acoustic Environments on Machine-to-Machine Signalling
- Clean Speech AE-DNN PSD Constraint for MCLP Based Reverberant Speech Enhancement
- Laplace Nonnegative Matrix Factorization with Application to Semi-supervised Audio Denoising
- Introducing SPAIN (SParse Audio INpainter)
- A New Weighted NMF Algorithm for Missing Data Interpolation and Its Application to Speech Enhancement
- Adaptive Pre-whitening Based on Parametric NMF
- A Comparison of Machine Learning Methods for Detecting Right Whales from Autonomous Surface Vehicles
WeAP3: SS6-Evaluation of Vehicular Wireless Communications and their Applications based on Experimental Data
Organizers: Martin Klaus Müller, José A. García-Naya, José Rogríguez-Piñeiro
Room: Poster Area 3Chairs: Martin Klaus Müller (TU Wien, Austria), José Rodríguez-Piñeiro (Tongji University, P.R. China)
- Integration of High Speed Train Channel Measurements in System Level Simulations
- Feasibility of LTE for Train Control in Subway Environments Based on Experimental Data
- LTE-based Wireless Channel Modeling on High-Speed Railway at 465MHz
- Measurement-based Wideband Radio Channel Characterization in an Underground Parking Lot
- Experimental Evaluation of the Reconfigurable Photodetector for Blind Interference Alignment in Visible Light Communications
- Path Loss at 5 GHz and 31 GHz for Two Distinct Indoor Airport Settings
- Optimization of the Radio Access to Provide Vehicular Communications Based on Drive Tests
- Decentralized Multi-Agent Deep Reinforcement Learning in Swarms of Drones for Flood Monitoring
Wednesday, September 4 15:10 - 15:40
Coffee break
Wednesday, September 4 15:40 - 17:20
WeEL1: SS9-Tensor-Based Signal Processing I
Organzers: Lieven De Lathauwer, Sabine Van Huffel
Room 1Chair: Sabine Van Huffel (Katholieke Universiteit Leuven, Belgium)
- 15:40 Tensor Network Kalman Filter for LTI Systems
- 16:00 Rank-one Tensor Approximation with Beta-divergence Cost Functions
- 16:20 Joint Low-Rank Factorizations with Shared and Unshared Components Identifiability and Algorithms
- 16:40 Two-Way MIMO Decode-and-Forward Relaying Systems with Tensor Space-Time Coding
- 17:00 Large-scale Canonical Polyadic Decomposition via Regular Tensor Sampling
WeEL2: ASMSP LIV - Noise and Echo Reduction
Room 2
Chair: Alberto Gonzalez (Universidad Politecnica de Valencia, Spain)
- 15:40 Offline Noise Reduction Using Optimal Mass Transport Induced Covariance Interpolation
- 16:00 Infinite Impulse Response Echo Canceller in STFT Domain for Reverberant Environments
- 16:20 Change Prediction for Low Complexity Combined Beamforming and Acoustic Echo Cancellation
- 16:40 An EM Algorithm for Joint Dual-Speaker Separation and Dereverberation
- 17:00 Maximum Likelihood Convolutional Beamformer for Simultaneous Denoising and Dereverberation
WeEL3: SPMuS LII - Sampling and Filtering over Graphs
Room 3
Chair: Cédric Richard (Université de Nice Sophia-Antipolis, France)
- 15:40 An Adaptive Sampling Technique for Graph Diffusion LMS Algorithm
- 16:00 Subsampling of Multivariate Time-Vertex Graph Signals
- 16:20 Graph Filter Design Using Sum-of-squares Representation
- 16:40 Distributed Consensus-Based Extended Kalman Filtering: A Bayesian Perspective
- 17:00 Defining Graph Signal Distances Using an Optimal Mass Transport Framework
WeEL4: SPCN LIII - Multi-user Communication Systems
Room 4
Chair: Ignacio Santamaria (University of Cantabria, Spain)
- 15:40 Wireless Multi-group Multicast Precoding with Selective RF Energy Harvesting
- 16:00 Multi-point Connectivity for Reliable mmWave
- 16:20 Globally Optimal TIN Strategies with Time-Sharing in the MISO Interference Channel
- 16:40 Rate Balancing for Multiuser Multicell Downlink MIMO Systems
- 17:00 Energy-Efficient Improper Signaling for $K$-User Interference Channels
WeEL5: TMTSP LIV - Signal Modeling and Estimation
Room: Auditorium Arao
Chair: Stefano Marano (University of Salerno, Italy)
- 15:40 Algorithms for Piecewise Constant Signal Approximations
- 16:00 Regression to a Linear Lower Bound with Outliers: An Exponentially Modified Gaussian Noise Model
- 16:20 Modelling Mismatch and Noise Statistics Uncertainty in Linear MMSE Estimation
- 16:40 Identification of Vector Autoregressive Models with Granger and Stability Constraints
- 17:00 A Modelling Approach to Generate Representative UAV Trajectories Using PSO
WeEP1: SiG-DML PII - Learning theory
Room: Poster Area 1
Chair: Víctor Elvira (IMT Lille Douai, France)
- Training Variational Autoencoders with Discrete Latent Variables Using Importance Sampling
- Partially Adversarial Learning and Adaptation
- Reparameterization Gradient Message Passing
- Variational Bayesian GAN
- Convolutional LSTM-based Long-Term Spectrum Prediction for Dynamic Spectrum Access
- Training Generative Adversarial Networks with Weights
- Finding Common Image Semantics for Urban Perceived Safety Based on Pairwise Comparisons
- Compressive Independent Component Analysis
WeEP2: DIS PI - DSP implementation and Optimisation
Room: Poster Area 2
Chair: Alberto Carini (Università di Trieste, Italy)
- Memory-Optimized Voronoi Cell-Based Parallel Kernels for the Shortest Vector Problem on Lattices
- Sensor Fusion for Learning-based Tracking of Controller Movement in Virtual Reality
- Bayesian Time-Domain Multiple Sound Source Localization for a Stochastic Machine
- 2-D Non-Separable Integer Implementation of Paraunitary Filter Bank Based on the Quaternionic Multiplier Block-Lifting Structure
- Hardware Acceleration of Approximate Transform Module for the Versatile Video Coding
- Optimization of Signal Processing Chains: Application to Cascaded Filters
- Heart Disease Detection Architecture for Lead I Off-the-Person ECG Monitoring Devices
- FPGA Implementation of a TVWS Up- And Downconverter Using Non-Power-of-Two FFT Modulated Filter Banks
WeEP3: SS1-Advanced Signal Processing for Resource-Efficient 5G Satellite-Terrestrial Networks
Organizers: Eva Lagunas, Charly Poulliat, Paul de Kerret
Room: Poster Area 3Chair: Eva Lagunas (University of Luxembourg, Luxembourg)
- Power-Efficient Secure Beamforming in Cognitive Satellite-Terrestrial Networks
- Validation Framework for Building a Spectrum Sharing Testbed for Integrated Satellite-Terrestrial Systems
- Resource Optimization for Cognitive Satellite Systems with Incumbent Terrestrial Receivers
- Satellite Links Integrated in 5G SDN-enabled Backhaul Networks: An Iterative Joint Power and Flow Assignment
- Neural Network Aided Computation of Generalized Spatial Modulation Capacity
- On the Physical Layer Security of IoT Devices over Satellite
- Spectral Coexistence of 5G Networks and Satellite Communication Systems Enabled by Coordinated Caching and QoS-Aware Resource Allocation
Wednesday, September 4 19:30 - 23:30
Conference Banquet
Thursday, September 5 9:30 - 10:30
PLEN-3: Raymond Knopp, "Academic research, Standardization and Open-Prototyping"
Raymond Knopp (EURECOM, Sophia Antipolis, France)
Room: Auditorium AraoChair: Markus Rupp (TU Wien, Austria)
Thursday, September 5 10:30 - 11:00
Coffee break
Thursday, September 5 11:00 - 12:40
ThML1: SS9-Tensor-Based Signal Processing II
Organzers: Lieven De Lathauwer, Sabine Van Huffel
Room 1Chair: Lieven De Lathauwer (KU Leuven Kulak, Belgium)
- 11:00 NLS Algorithm for Kronecker-Structured Linear Systems with a CPD Constrained Solution
- 11:20 Estimation of Sensor Array Signal Model Parameters Using Factor Analysis
- 11:40 Estimation of a Low-Rank Probability-Tensor from Sample Sub-Tensors via Joint Factorization Minimizing the Kullback-Leibler Divergence
- 12:00 Tensor Factorisation and Transfer Learning for Sleep Pose Detection
- 12:20 New Algorithms on Complex Joint Eigenvalue Decomposition Based on Generalized Givens Rotations
ThML2: SPMuS LIII - Radar and Sonar Detection
Room 2
Chair: Fulvio Gini (University of Pisa, Italy)
- 11:00 Sampling Rate and Bits per Sample Tradeoff for Cloud MIMO Radar Target Detection Cloud MIMO Radar Target Detection
- 11:20 Forward Looking GPR-Based Landmine Detection Using a Robust Likelihood Ratio Test
- 11:40 Generalized Gamma Distribution SAR Sea Clutter Modelling for Oil Spill Candidates Detection
- 12:00 Detection Enumeration and Localization of Underwater Acoustic Sources
- 12:20 Improved Waveforms for Time-Efficient Radar Range Measurement Disambiguation
ThML3: BISA LIV - Biomedical Image Processing
Room 3
Chair: Francoise Peyrin (Universite de Lyon INSA Lyon & Inserm U1206 UMR CNRS 5220, France)
- 11:00 A Sparse and Prior Based Method for 3D Image Denoising
- 11:20 Image and Ontological Information Fusion for Cataract Surgery Recommendation
- 11:40 Cardiac Motion Estimation Using Convolutional Sparse Coding
- 12:00 Unsupervised Medical Image Translation Using Cycle-MedGAN
- 12:20 Prediction of FDG Uptake in Lung Tumors from CT Images Using Generative Adversarial Networks
ThML4: SiG-DML LIV - Neural Networks
Room 4
Chair: Saikat Chatterjee (KTH - Royal Institute of Technology & Communication Theory Lab, Sweden)
- 11:00 Ship Classification from Multi-Spectral Satellite Imaging by Convolutional Neural Networks
- 11:20 Segmentation of Surface Cracks Based on a Fully Convolutional Neural Network and Gated Scale Pooling
- 11:40 Gearbox Fault Diagnosis Using Convolutional Neural Networks and Support Vector Machines
- 12:00 Curriculum-based Teacher Ensemble for Robust Neural Network Distillation
- 12:20 End-to-End Language Identification Using a Residual Convolutional Neural Network with Attentive Temporal Pooling
ThML5: VIP LIV - Video Segmentation and Feature Extraction
Room: Auditorium Arao
Chair: João Ascenso (Instituto Superior Técnico & Instituto de Telecomunicações, Portugal)
- 11:00 On Detecting and Handling Target Occlusions in Correlation-filter-based 2D Tracking
- 11:20 Efficient Feature Extraction for Person Re-Identification via Distillation
- 11:40 Cross-domain Knowledge Transfer Schemes for 3D Human Action Recognition
- 12:00 Complexity Scalable HEVC-to-AV1 Transcoding Based on Coding Tree Depth Inheritance
- 12:20 NAViDAd: A No-Reference Audio-Visual Quality Metric Based on a Deep Autoencoder
ThMP1: TMTSP PIII-Signal processing theory and methods
Room: Poster Area 1
Chair: Stefano Fortunati (University of Pisa, Italy)
- Asymptotic Karlin-Rubin's Theorem with Application to Signal Detection in a Subspace Cone
- Scale-discretised Ridgelet Transform on the Sphere
- Two-Band Signal Reconstruction from Periodic Nonuniform Samples
- Separation of Independent / Dependent Sources Using Copulas
- Demodulation Algorithm Based on Higher Order Synchrosqueezing
- A New Signal-Selective Wide-Band Ambiguity Function
- Joint Unmixing-Deconvolution Algorithms for Hyperspectral Images
- A Blind Reconstruction Algorithm for Level-Crossing Analog-to-Digital Conversion
- Segmentation of Piecewise ARX Processes by Exploiting Sparsity in Tight-Dimensional Spaces
- Signal Recovery from Phaseless Measurements of Spherical Harmonics Expansion
- Connections Between Reassigned Spectrum and Least Squares Estimation for Sinusoidal Models
ThMP2: TMTSP PIV - Signal Processing and Theory Methods
Room: Poster Area 2
Chair: Florian Roemer (Fraunhofer Institute for Nondestructive Testing IZFP & Ilmenau University of Technology, Germany)
- Defect Detection from Compressed 3-D Ultrasonic Frequency Measurements
- Edge and Cloud-aided Secure Sparse Representation for Face Recognition
- Multiple K-Means Clustering Based Locally Low-Rank Approach to Nonlinear Matrix Completion
- Convex Combination of Spline Adaptive Filters
- L0-Norm Adaptive Volterra Filters
- Fast Basis Function Estimators for Identification of Nonstationary Stochastic Processes
- Parameter-free Small Variance Asymptotics for Dictionary Learning
- Measure-Transformed Gaussian Quasi Score Test in the Presence of Nuisance Parameters
ThMP3: SPCN PI - Signal Processing for Communications
Room: Poster Area 3
Chair: Ana Pérez-Neira (CTTC, Spain)
- All-Powerful Learning Algorithm for the Priority Access in Cognitive Network
- OFDM Spectral Precoding with Per-Subcarrier Distortion Constraints
- An Algebraic Framework for Digital Envelope Modulation
- Evaluation of Analog Encoding for Multi-User Wireless Transmission of Still Images
- Deep Log-Likelihood Ratio Quantization
- Node Activity Monitoring in Heterogeneous Networks Using Energy Sensors
- Jammer Detection in M-QAM-OFDM by Learning a Dynamic Bayesian Model for the Cognitive Radio
Thursday, September 5 12:40 - 13:40
Lunch break
Thursday, September 5 13:40 - 15:40
ThAL1: SS8-Acoustic Scene Analysis and Signal Enhancement Based on Advanced Signal Processing and Machine Learning
Organizers: Shoji Makino, Nobutaka Ono
Room 1Chairs: Shoji Makino (University of Tsukuba, Japan), Nobutaka Ono (Tokyo Metropolitan University, Japan)
- 13:40 Acoustic Source Position Estimation Based on Multi-Feature Gaussian Processes
- 14:00 Comparison of Parameter Estimation Methods for Single-Microphone Multi-Frame Wiener Filtering
- 14:20 Efficient Full-Rank Spatial Covariance Estimation Using Independent Low-Rank Matrix Analysis for Blind Source Separation
- 14:40 Wavelength Proportional Arrangement of Virtual Microphones Based on Interpolation/Extrapolation for Underdetermined Speech Enhancement
- 15:00 Fast Multichannel Source Separation Based on Jointly Diagonalizable Spatial Covariance Matrices
- 15:20 Multi-Microphone Speaker Separation Based on Deep DOA Estimation
ThAL2: SPMuS LIV - Robust Array Processing
Room 2
Chair: Geert Leus (Delft University of Technology, The Netherlands)
- 13:40 Robust ToA-Based Localization in a Mixed LOS/NLOS Environment Using Hybrid Mapping Technique
- 14:00 Outlier Detection from Non-Smooth Sensor Data
- 14:20 Robust Subspace Tracking with Missing Data and Outliers via ADMM
- 14:40 Block Sparsity-Based DOA Estimation with Sensor Gain and Phase Uncertainties
- 15:00 Robust Self-Localization of Microphone Arrays Using a Minimum Number of Acoustic Sources
- 15:20 Auto-calibration of Uniform Linear Array Antennas
ThAL3: BISA LV - Neural Networks in Biomedicine
Room 3
Chair: Ahmed Tewfik (University of Texas, Austin, USA)
- 13:40 A Novel Recurrent Neural Network Architecture for Classification of Atrial Fibrillation Using Single-lead ECG
- 14:00 Classification of Brainwaves Using Convolutional Neural Network
- 14:20 Predicting the Success of Blastocyst Implantation from Morphokinetic Parameters Estimated Through CNNs and Sum of Absolute Differences
- 14:40 Towards Automatic Glaucoma Assessment: An Encoder-decoder CNN for Retinal Layer Segmentation in Rodent OCT Images
- 15:00 Segmentation of Head and Neck Tumour Using Modified U-net
- 15:20 Inhomogeneously Stacked RNN for Recognizing Hand Gestures from Magnetometer Data
ThAL4: SiG-DML LV - Machine Learning for Robotics
Room 4
Chair: Walter Kellermann (University Erlangen-Nuremberg, Germany)
- 13:40 Acoustic Simulation in Dynamic Environments for Robot Audition
- 14:00 Active Acoustic Source Tracking Exploiting Particle Filtering and Monte Carlo Tree Search
- 14:20 Extracting Proprioceptive Information by Analyzing Rotating Range Sensors Induced Distortion
- 14:40 Deep Reinforcement Learning for Autonomous Model-Free Navigation with Partial Observability
- 15:00 Antenna Controller for Low-Latency and High Reliability Robotic Communications over Time-Varying Fading Channels
- 15:20 Sound-based Distance Estimation for Indoor Navigation in the Presence of Ego Noise
ThAL5: TMTSP LV - Sparse Dictionary Learning
Room: Auditorium Arao
Chair: Herwig Wendt (University of Toulouse, CNRS, France)
- 13:40 L0Soft: L0 Minimization via Soft Thresholding
- 14:00 Spectrum Insensitive Sparse Recovery with Iterative Affine Projections
- 14:20 Atomic Norms in Group Sliding Sparse Recovery
- 14:40 Learning Tensor-structured Dictionaries with Application to Hyperspectral Image Denoising
- 15:00 Hyperspectral and Multispectral Image Fusion Based on a Non-locally Centralized Sparse Model and Adaptive Spatial-Spectral Dictionaries
- 15:20 Hyper-parameter Selection on Convolutional Dictionary Learning Through Local \ell_{0,\infty} Norm
ThAP1: ASMSP PIII - Acoustic Signal Processing;
Room: Poster Area 1
Chair: Richard Hendriks (Delft University of Technology, The Netherlands)
- Sensor Selection and Rate Distribution Based Beamforming in Wireless Acoustic Sensor Networks
- Permutation Alignment Based on MUSIC Spectrum Discrepancy for Blind Source Separation
- MWF-based Speech Dereverberation with a Local Microphone Array and an External Microphone
- Replay Attack Detection Using Generalized Cross-Correlation of Stereo Signal
- Generalized Multichannel Variational Autoencoder for Underdetermined Source Separation
- Distributed Adaptive Node-Specific Signal Estimation in a Wireless Sensor Network with Partial Prior Knowledge of the Desired Source Steering Vector
- Non-Intrusive POLQA Estimation of Speech Quality Using Recurrent Neural Networks
- Computational Acceleration and Smart Initialization of Full-rank Spatial Covariance Analysis
- Referenceless Performance Evaluation of Audio Source Separation Using Deep Neural Networks
- A Unifying Framework for Blind Source Separation Based on A Joint Diagonalizability Constraint
- Automatic Measurement of Speech Breathing Rate
- A New Metric to Evaluate Auditory Attention Detection Performance Based on a Markov Chain
ThAP2: VIP PIV - Image Processing
Room: Poster Area 2
Chair: Marc Antonini (Université de Nice Sophia Antipolis, France)
- Lossless Image Coding Exploiting Local and Non-local Information via Probability Model Optimization
- Gaze Tracking by Joint Head and Eye Pose Estimation Under Free Head Movement
- Graph Spectral Domain Features for Static Hand Gesture Recognition
- Target Identification from Coded Diffraction Patterns via Template Matching
- A Biologically Constrained Encoding Solution for Long-Term Storage of Images onto Synthetic DNA
- Free Registration Based Shape Prior for Active Contours
- Low-Rank Approximation via the Generalized Reweighted Iterative Nuclear Norm
ThAP3: SPCN PII - Channel State Estimation
Room: Poster Area 3
Chair: Christoph F Mecklenbräuker (Vienna University of Technology, Austria)
- A Robust Group-Sparse Proportionate Affine Projection Algorithm with Maximum Correntropy Criterion for Channel Estimation
- Maximum-likelihood Detection of Impulsive Noise Support for Channel Parameter Estimation
- Underwater Acoustic Channel Estimation and Equalization via Adaptive Filtering and Sparse Approximation
- Spectrum Sensing by Higher-Order SVM-based Detection
- Novel Sensing Mechanism for Full-Duplex Secondary Users in Cognitive Radio
- Intersymbol and Intercarrier Interference in OFDM Transmissions Through Highly Dispersive Channels
- Hybrid FSO/RF-FSO Systems over Generalized Malaga Distributed Channels with Pointing Errors
Thursday, September 5 15:40 - 16:10
Coffee break
Thursday, September 5 16:10 - 17:50
ThEL1: VIP LV - Image Feature Extraction
Room 1
Chair: Anastasios Tefas (Aristotle University of Thessaloniki, Greece)
- 16:10 Improved Lossless Image Compression Using Adaptive Image Rotation
- 16:30 An Improved Feature Extraction Method for Texture Classification with Increased Noise Robustness
- 16:50 An Ensemble Learning Approach for the Classification of Remote Sensing Scenes Based on Covariance Pooling of CNN Features
- 17:10 Texture Superpixel Clustering from Patch-based Nearest Neighbor Matching
- 17:30 One-Class Feature Learning Using Intra-Class Splitting
ThEL2: ASMSP LV - Model Based Audio Signal Processing
Room 2
Chair: Rainer Martin (Ruhr-University Bochum, Germany)
- 16:10 Bayesian Model Selection for Nonlinear Acoustic Echo Cancellation
- 16:30 Spectral Complexity Reduction of Music Signals for Cochlear Implant Users Based on Subspace Tracking
- 16:50 Ad-hoc Mobile Array Based Audio Segmentation Using Latent Variable Stochastic Model
- 17:10 Monaural Source Separation Based on Sequentially Trained LSTMs in Real Room Environments
- 17:30 Model-based Optimization of a Low-dimensional Modulation Filter Bank for DRR and T60 Estimation
ThEL3: SPMuS LV - Signal and Image Processing Applications
Room 3
Chair: Arie Yeredor (Tel-Aviv University, Israel)
- 16:10 Matrix Cofactorization for Joint Unmixing and Classification of Hyperspectral Images
- 16:30 Bayesian Estimation of Recurrent Changepoints for Signal Segmentation and Anomaly Detection
- 16:50 Single Image Ear Recognition Using Wavelet-Based Multi-Band PCA
- 17:10 Analysis of Nematodes in Coffee Crops at Different Altitudes Using Aerial Images
- 17:30 Compression of High-Dimensional Multispectral Image Time Series Using Tensor Decomposition Learning
ThEL4: SPCN LIV - Internet of Things
Room 4
Chair: Mounir Ghogho (UIR, Morocco)
- 16:10 Spatial Inference in Sensor Networks Using Multiple Hypothesis Testing and Bayesian Clustering
- 16:30 A Low Complexity Image Compression Algorithm for IoT Multimedia Applications
- 16:50 GestureKeeper: Gesture Recognition for Controlling Devices in IoT Environments
- 17:10 Cost-Aware Dual Prediction Scheme for Reducing Transmissions at IoT Sensor Nodes
- 17:30 Optimum Trajectory Planning for Robotic Data Ferries in Delay Tolerant Wireless Sensor Networks
ThEL5: TMTSP LVI - Time-Frequency Methods
Room: Auditorium Arao
Chair: Richard Heusdens (Delft University of Technology, The Netherlands)
- 16:10 Tracking Recurring Patterns in Time Series Using Dynamic Time Warping
- 16:30 Shuffling for Understanding Multifractality - Application to Asset Price Time Series
- 16:50 Second-Order Time-Reassigned Synchrosqueezing Transform: Application to Draupner Wave Analysis
- 17:10 Filtering-based Analysis Comparing the DFA with the CDFA for Wide Sense Stationary Processes
- 17:30 2D Fourier Transform Based Analysis Comparing the DFA with the DMA
ThEP1: SiG-DML PIII -Applications of Machine Learning;
Room: Poster Area 1
Chair: Franz Hlawatsch (Vienna University of Technology, Austria)
- Spectrogram Feature Losses for Music Source Separation
- Data Preprocessing for ANN-based Industrial Time-Series Forecasting with Imbalanced Data
- Spatial and Hierarchical Riemannian Dimensionality Reduction and Dictionary Learning for Segmenting Multichannel Images
- A Machine Learning Approach to the Identification of Dynamical Nonlinear Systems
- Improving Energy Disaggregation Performance Using Appliance-Driven Sampling Rates
- Learning of Image Dehazing Models for Segmentation Tasks
- A Highly Reliable Wrist-Worn Acceleration-Based Fall Detector
- Joint User Grouping and Power Allocation for MISO Systems: Learning to Schedule
- Deep Complex Neural Network Learning for High-Voltage Insulation Fault Classification from Complex Bispectrum Representation
ThEP2: BISA PIV - EEG Analysis
Room: Poster Area 2
Chair: Vicente Zarzoso (IUT Nice - Côte d'Azur, France)
- Identify Spatial Similarity of Electroencephalography (EEG) During Working-Memory Maintenance
- Perception of Non-Native Phoneme Contrasts in 8-13 Months Infants Tensor-Based Analysis of EEG Signals
- Labeler-hot Detection of EEG Epileptic Transients
- Alcoholic EEG Analysis Using Riemann Geometry Based Framework
- Modified U-Net for Automatic Brain Tumor Regions Segmentation
- Perfusion-based Brain Connectivity: PASL Vs pCASL
- Detecting Early Parkinson's Disease from Keystroke Dynamics Using the Tensor-Train Decomposition
- Analysis of Parkinson's Disease Dysgraphia Based on Optimized Fractional Order Derivative Features
ThEP3: BISA PIII - ECG & Cardio
Room: Poster Area 3
Chair: Riccardo Bernardini (University of Udine, Italy)
- Volumetric Surface-guided Graph-based Segmentation of Cardiac Adipose Tissues on Fat-Water MR Images
- Stress Detection Through Electrodermal Activity (EDA) and Electrocardiogram (ECG) Analysis in Car Drivers
- A Graph Signal Processing Framework for Atrial Activity Extraction
- A Multitarget Tracking Method for Estimating Carotid Artery Wall Motion from Ultrasound Sequences
- Breathing Rate Complexity Features for "In-the-Wild'' Stress and Anxiety Measurement
- A Self-Tuned Architecture for Human Activity Recognition Based on a Dynamical Recurrence Analysis of Wearable Sensor Data
- Semi-Supervised Adaptive Learning for Decoding Movement Intent from Electromyograms
Friday, September 6 9:00 - 10:00
PLEN-4: Alejandro Ribeiro, "Graph Neural Networks"
Alejandro Ribeiro (Department of Electrical and Systems Engineering, University of Pennsylvania, Philadelphia, USA)
Room: Auditorium AraoChair: Luis Castedo (University of A Coruña, Spain)
Friday, September 6 10:00 - 10:30
Coffee break
Friday, September 6 10:30 - 12:10
FrML1: ASMSP LVI - Acoustic Source Localization
Room 1
Chair: Augusto Sarti (Politecnico di Milano, Italy)
- 10:30 Variational Inference for DOA Estimation in Reverberant Conditions
- 10:50 Indoor Sound Source Localization Based on Sparse Bayesian Learning and Compressed Data
- 11:10 On the Relation Between DOA-Vector Eigenbeam ESPRIT and Subspace Pseudointensity-Vector
- 11:30 On Spectral Embeddings for Supervised Binaural Source Localization
- 11:50 Self-Localization of Distributed Microphone Arrays Using Directional Statistics with DoA Estimation Reliability
FrML2: SPMuS LVI - Signal Processing Over Graphs
Room 2
Chair: Remy Boyer (University of Lille & CRIStAL, France)
- 10:30 Learning Causal Networks Topology from Streaming Graph Signals
- 10:50 Enhanced Diffusion Learning over Networks
- 11:10 Topology Inference and Signal Representation Using Dictionary Learning
- 11:30 Gated Graph Convolutional Recurrent Neural Networks
- 11:50 Privacy-Preserving Distributed Average Consensus Based on Additive Secret Sharing
FrML3: VIP LVI - Video Coding
Room 3
Chair: Giuseppe Valenzise (CNRS, France)
- 10:30 Early SKIP Mode Decision Method in HEVC Based on Perceptual Distortion Measure
- 10:50 Evaluation of Modifications to CPPPSNR in 360ᵒ Video Quality Assessment
- 11:10 Fast CU Size Decisions for HEVC Inter-Prediction Using Support Vector Machines
- 11:30 HVS Based Perceptual Pre-Processing for Video Coding
- 11:50 A Temporal Dependency Model for Rate-Distortion Optimization in Video Coding
FrML4: TMTSP LVII - Adaptive Algorithms
Room: Auditorium Arao
Chair: Mohammed Nabil El Korso (Paris 10 University & LEME-EA 4416, France)
- 10:30 Tracking Theory of Adaptive Filters with Input-Output Sampling Rate Offset
- 10:50 A Simple Sparsity-aware Feature LMS Algorithm
- 11:10 Transient Analysis of Partitioned-Block Frequency-Domain Adaptive Filters
- 11:30 Signal Subspace Change Detection in Structured Covariance Matrices
- 11:50 Feature LMS Algorithm for Bandpass System Models
FrMP1: TMTSP PV-Statistical signal processing
Room: Poster Area 1
Chair: Jordi Vilà-Valls (ISAE-SUPAERO, University of Toulouse, France)
- A Novel Particle Filter for High-Dimensional Systems Using Penalized Perturbations
- Gauss-Hermite Quadrature for non-Gaussian Inference via an Importance Sampling Interpretation
- A Dyadic Particle Filter for Price Prediction
- Complexity-Reduced Suboptimal Equalization with Monte Carlo Based MIMO Detectors
- A Data Augmentation Approach for Sampling Gaussian Models in High Dimension
- Structure Learning via Hadamard Product of Correlation and Partial Correlation Matrices
- Low-rank Data Matrix Recovery with Missing Values and Faulty Sensors
- Fully Adaptive Savitzky-Golay Type Smoothers
- Recursive LCMVEs with Non-Stationary Constraints and Partially Coherent Signal Sources
- On Adaptive Spectrum Estimation of Multivariate Autoregressive Locally Stationary Processes
FrMP2: SS7-Signal processing methods for 4D arrays
Organizers: Paolo Rocca, Roberto Maneiro-Catoria
Room: Poster Area 2Chairs: Roberto Maneiro-Catoira (University of A Coruña, Spain), Lorenzo Poli (ELEDIA Research Center, University of Trento, Italy)
- 10:30 MIMO Receiver with Reduced Number of RF Chains Based on 4D Array and Software Defined Radio
- 10:44 Adaptive Beamforming Based on Time Modulated Array with Harmonic Characteristic Analysis
- 10:58 Precise Response Control of Transmit-receive Two-dimensional Beampattern in FDA-MIMO Radar
- 11:12 Beam-Steering in Switched 4D Arrays Based on the Discrete Walsh Transform
- 11:27 FDA-MIMO Signal Processing for Mainlobe Jammer Suppression
- 11:41 Optimization-based Synthesis of Time-Modulated Arrays with Accurate Time-Frequency Analysis
- 11:55 Time Modulated Array - a Database Approach
Friday, September 6 10:30 - 13:00
SW1L: II XoveTIC Conference. Scientific talent at Galicia (Lectures)
EUSIPCO 2019 Satellite Workshop
Room 4Friday, September 6 13:30 - 19:00
SW2: Satellite Workshop on Signal Processing Computer vision and Deep Learning for Autonomous Systems
EUSIPCO 2019 Satellite Workshop
Workshop organizers: Nikos Nikolaidis and Anastasios Tefas (Aristotle University of Thessaloniki, Greece)
Room 4Friday, September 6 14:00 - 15:30
SW1P: II XoveTIC Conference. Scientific talent at Galicia (Posters)
Rooms: Poster Area 1, Poster Area 2, Poster Area 3