research
my main research interests, along with relevant publications
You can find below a selected list of research topics I have worked on, along with indicative relevant publications. Note that a few of them might fall within multiple categories.
Information-theoretic Representation Learning
- N. Passalis, M. Tzelepi, and Anastasios Tefas, “Heterogeneous Knowledge Distillation using Information Flow Modeling,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020
- N. Passalis and A. Tefas, “Learning Deep Representations with Probabilistic Knowledge Transfer,” European Conference on Computer Vision (ECCV), 2018
- N. Passalis, M. Tzelepi and A. Tefas, “Probabilistic Knowledge Transfer for Lightweight Deep Representation Learning”, Transactions on Neural Networks and Learning Systems, 2020
- N. Passalis, and A. Tefas, “Deep supervised hashing using quadratic spherical mutual information for efficient image retrieval”, Signal Processing: Image Communication, 2021
- N. Passalis, A. Iosifidis, M. Gabbouj and A. Tefas, “Variance-preserving deep metric learning for content-based image retrieval”, Pattern Recognition Letters, 2019
- N. Passalis and A. Tefas, “Entropy Optimized Feature-Based Bag-of-Words Representation for Information Retrieval,” IEEE Transactions on Knowledge and Data Engineering
Model-based and Data-driven Learning
- P. Nousi, S.-C. Fragkouli, N. Passalis, P. Iosif, T. Apostolatos, G. Pappas, N. Stergioulas, and A. Tefas, “Autoencoder-driven spiral representation learning for gravitational wave surrogate modelling”, Neurocomputing, 2022
- G. Mourgias-Alexandris, M. Moralis-Pegios, A. Tsakyridis, N. Passalis, M. Kirtas, A. Tefas, T. Rutirawut, FY. Gardes, and N. Pleros, “Channel response-aware photonic neural network accelerators for high-speed inference through bandwidth-limited optics”, Optics Express, 2022
- N. Passalis and A. Tefas, “Pseudo-Active Vision For Improving Deep Visual Perception Through Neural Sensory Refinement”, IEEE International Conference on Image Processing (ICIP), 2021
- N. Passalis, and A. Tefas, “Global Adaptive Input Normalization for Short-Term Electric Load Forecasting,” IEEE Symposium Series on Computational Intelligence, 2020
- N. Passalis, J. Kanniainen, M. Gabbouj, A. Iosifidis, and A. Tefas, “Forecasting Financial Time Series using Robust Deep Adaptive Input Normalization”, Journal of Signal Processing Systems, 2020
- N. Passalis, A. Tefas, J. Kanniainen, M. Gabbouj and A. Iosifidis, “Deep Adaptive Input Normalization for Time Series Forecasting”, IEEE Transactions on Neural Networks and Learning Systems, 2019
- N. Passalis, A. Tefas, J. Kanniainen, M. Gabbouj and A. Iosifidis, “Adaptive Normalization for Forecasting Limit Order Book Data using Convolutional Neural Networks”, IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2020
DL Architectures for Feature Aggregation
- N. Passalis and A. Tefas, “Learning Bag-of-Features Pooling for Deep Convolutional Neural Networks,” International Conference on Computer Vision (ICCV), 2017
- F. Laakom, N. Passalis, J. Raitoharju, J. Nikkanen, A. Tefas, A. Iosifidis, and M. Gabbouj, “Bag of Color Features For Color Constancy”, IEEE Transactions on Image Processing, 2020
- N. Passalis, A. Tefas, J. Kanniainen, M. Gabbouj, and A. Iosifidis, “Temporal Logistic Neural Bag-of-Features for Financial Time series Forecasting leveraging Limit Order Book Data,” Pattern Recognition Letters, 2020
- M. Krestenitis, N. Passalis, A. Iosifidis, M. Gabbouj and A. Tefas, “Recurrent Bag-of-Features for Visual Information Analysis”, Pattern Recognition, 2020
- N. Passalis, A. Tefas, J. Kanniainen, M. Gabbouj and A. Iosifidis, “Temporal bag-of-features learning for predicting mid price movements using high frequency limit order book data,” IEEE Transactions on Emerging Topics in Computational Intelligence, 2018
- N. Passalis and A. Tefas, “Information Clustering using Manifold-based Optimization of the Bag-of-Features Representation,” Transactions on Cybernetics, 2018
- N. Passalis and A. Tefas, “Neural Bag-of-Features Learning,” Pattern Recognition, 2017
- N. Passalis and A. Tefas, “Learning Neural Bag-of-Features for Large Scale Information Retrieval,” IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2017
- N. Passalis and A. Tefas, “Entropy Optimized Feature-Based Bag-of-Words Representation for Information Retrieval,” IEEE Transactions on Knowledge and Data Engineering, 2016
Lightweight Machine/Deep Learning
Knowledge Distillation
- N. Passalis, M. Tzelepi, and Anastasios Tefas, “Heterogeneous Knowledge Distillation using Information Flow Modeling,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020
- N. Passalis and A. Tefas, “Learning Deep Representations with Probabilistic Knowledge Transfer,” European Conference on Computer Vision (ECCV), 2018
- M. Tzelepi, N. Passalis, and A. Tefas, “Online Subclass Knowledge Distillation”, Expert Systems With Applications, 2021
- A. Tsantekidis, N. Passalis, and A. Tefas, “Diversity-driven Knowledge Distillation for Financial Trading using Deep Reinforcement Learning”, Neural Networks, 2021
- A. Zaras, N. Passalis, and A. Tefas, “Improving Knowledge Distillation using Unified Ensembles of Specialized Teachers”, Pattern Recognition Letters, 2021
- N. Passalis, M. Tzelepi and A. Tefas, “Probabilistic Knowledge Transfer for Lightweight Deep Representation Learning”, Transactions on Neural Networks and Learning Systems, 2020
- N. Passalis and A. Tefas, “Unsupervised knowledge transfer using similarity embeddings,” IEEE Transactions on Neural Networks and Learning Systems, 2018
- G. Panagiotatos, N. Passalis, A. Iosifidis, M. Gabbouj, A. Tefas, “Curriculum-based Teacher Ensemble for Robust Neural Network Distillation,” European Signal Processing Conference (EUSIPCO)
Adaptive Computational Graphs for DL
- N. Passalis, and A. Tefas, “Adaptive Inference for Face Recognition leveraging Deep Metric Learning-enabled Early Exits,” European Signal Processing Conference (EUSIPCO), 2021
- N. Passalis, J. Raitoharju, A. Tefas, M. Gabbouj, “Efficient Adaptive Inference for Deep Convolutional Neural Networks using Hierarchical Early Exits,” Pattern Recognition, 2020
- N. Passalis, J. Raitoharju, A. Tefas, M. Gabbouj, “Adaptive Inference using Hierarchical Convolutional Bag-of-Features for Low-power Embedded Platforms,” IEEE International Conference on Image Processing (ICIP), 2019
- N. Passalis, J. Raitoharju, M. Gabbouj, and A. Tefas, “Efficient Adaptive Inference leveraging Bag-of-Features-based Early Exits,” IEEE International Workshop on Multimedia Signal Processing, 2020
Dimensionality Reduction
- N. Passalis and A. Tefas, “Dimensionality Reduction using Similarity-induced Embeddings,” IEEE Transactions on Neural Networks and Learning Systems, 2017
- N. Passalis and A. Tefas, “PySEF: A python library for similarity-based dimensionality reduction,” Knowledge-Based Systems, 2018
Lighweight Architectures
Hashing
Timeseries Analysis
Energy Data Analytics
- N. Maragkos, M. Tzelepi, N. Passalis, A. Adamakos, and A. Tefas, “Electric load demand forecasting on greek energy market using lightweight neural networks”, IEEE 14th Image, Video, and Multidimensional Signal Processing Workshop (IVMSP), 2022
- N. Passalis, and A. Tefas, “Global Adaptive Input Normalization for Short-Term Electric Load Forecasting,” IEEE Symposium Series on Computational Intelligence, 2020
Timeseries analysis
- N. Passalis, J. Kanniainen, M. Gabbouj, A. Iosifidis, and A. Tefas, “Forecasting Financial Time Series using Robust Deep Adaptive Input Normalization”, Journal of Signal Processing Systems , 2020
- A. Tsantekidis, N. Passalis, A. Tefas, J. Kanniainen, M. Gabbouj and A. Iosifidis, “Using Deep Learning for price prediction by exploiting stationary limit order book features”, Applied Soft Computing, 2020
- P. Nousi, A. Tsantekidis, N. Passalis, A. Tefas, J. Kanniainen, M. Gabbouj and A. Iosifidis, “Machine learning for forecasting mid price movement using limit order book data”, IEEE Access, 2019
- N. Passalis, A. Tefas, J. Kanniainen, M. Gabbouj and A. Iosifidis, “Temporal bag-of-features learning for predicting mid price movements using high frequency limit order book data,” IEEE Transactions on Emerging Topics in Computational Intelligence, 2018
- A. Tsantekidis, N. Passalis, A. Tefas, J. Kanniainen, M. Gabbouj and A. Iosifidis, “Forecasting stock prices from the limit order book using convolutional neural networks,” IEEE Conference on Business Informatics (CBI), 2017
- N. Passalis, A. Tsantekidis, A. Tefas, J. Kanniainen, M. Gabbouj and A. Iosifidis, “Time-series Classification Using Neural Bag-of-Features,” European Signal Processing Conference (EUSIPCO), 2017
- N. Passalis, A. Tefas, J. Kanniainen, M. Gabbouj, and A. Iosifidis, “Deep Temporal Logistic Bag-of-Features for Forecasting High Frequency Limit Order Book Time Series,” IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2019
Trading using Deep Reinforcement Learning
- A. Tsantekidis, N. Passalis, and A. Tefas, “Diversity-driven Knowledge Distillation for Financial Trading using Deep Reinforcement Learning”, Neural Networks, 2021
- A. Tsantekidis, N. Passalis, A. Toufa, K. Saitas-Zarkias, and A. Tefas, “Price Trailing for Financial Trading using Deep Reinforcement Learning”, Transactions on Neural Networks and Learning Systems, 2020
Robotics Perception
Deep Reinforcement Learning for Robotics Control
- N. Passalis and A. Tefas, “Continuous Drone Control using Deep Reinforcement Learning for Frontal View Person Shooting”, Neural Computing and Applications, 2019
- N. Passalis and A. Tefas, “Deep Reinforcement Learning for Controlling Frontal Person Close-up Shooting,” Neurocomputing, 2019
- M. Kirtas, K. Tsampazis, N. Passalis, and Anastasios Tefas, “A Webots-based Deep Reinforcement Learning Framework for Robotics,” International Conference on Artificial Intelligence Applications and Innovations, 2020
Perception and Control
- N. Passalis and A. Tefas, “Concept Detection and Face Pose Estimation Using Lightweight Convolutional Neural Networks for Steering Drone Video Shooting,” European Signal Processing Conference (EUSIPCO), 2017
- N. Passalis, A. Tefas and I. Pitas, “Efficient camera control using 2d visual information for unmanned aerial vehicle-based cinematography,” International Symposium on Circuits and Systems (ISCAS), 2018
- J. Taipalmaa, N. Passalis, H. Zhang, M. Gabbouj and J. Raitoharju, “High-Resolution Water Segmentation for Autonomous Unmanned Surface Vehicles: A novel dataset and evaluation,” IEEE International Workshop on Machine Learning for Signal Processing (MLSP), 2019
- J. Taipalmaa, N. Passalis, and J. Raitoharju, “Different Color Spaces in Deep Learning-based Water Segmentation for Autonomous Marine Operations,” IEEE International Conference on Image Processing (ICIP), 2020
- C. Symeonidis, P. Nousi, P. Tosidis, K. Tsampazis, N. Passalis, A. Tefas, N. Nikolaidis, “Efficient Realistic Data Generation Framework leveraging Deep Learning-based Human Digitization,” International Conference on Engineering Applications of Neural Networks , 2021
- Villa Escusol, Jose, Taipalmaa, Jussi, Gerasimenko, Mikhail, Pyattaev, Alexander, Ukonaho, Mikko, Zhang, Honglei, Raitoharju, Jenni, Passalis, Nikolaos, Perttula, Antti, Aaltonen, Jussi, and others, “aColor: Mechatronics, Machine Learning, and Communications in an Unmanned Surface Vehicle”, Transport Research Arena Conference (TRA2020)
Active Perception
- N. Passalis and A. Tefas, “Pseudo-Active Vision For Improving Deep Visual Perception Through Neural Sensory Refinement”, IEEE International Conference on Image Processing (ICIP), 2021
- T. Bozinis, N. Passalis, and A. Tefas, “Improving Visual Question Answering using Active Perception on Static Images,” International Conference on Pattern Recognition (ICPR), 2020
- A. Tzimas, N. Passalis, and Anastasios Tefas, “Leveraging Deep Reinforcement Learning for Active Shooting under Open-World Setting,” IEEE International Conference on Multimedia and Expo, 2020
Photonic Neuromorphic Deep Learning
Ex-situ training for photonic neuromorphic architectures
- N. Passalis, G. Mourgias-Alexandris, N. Pleros and A. Tefas, “Initializing Photonic Feed-forward Neural Networks using Auxiliary Tasks”, Neural Networks, 2020
- N. Passalis, G. Mourgias-Alexandris, A. Tsakyridis, N. Pleros and A. Tefas, “Training Deep Photonic Convolutional Neural Networks with Sinusoidal Activations”, IEEE Transactions on Emerging Topics in Computational Intelligence, 2019
- N. Passalis, G. Mourgias-Alexandris, A. Tsakyridis, N. Pleros, and A. Tefas, “Variance Preserving Initialization for Training Deep Neuromorphic Photonic Networks with Sinusoidal Activations,” IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2019
- G. Mourgias-Alexandris, N. Passalis, G. Dabos, A. Totovic, A. Tefas, and N. Pleros “A Photonic Recurrent Neuron for Time-Series Classification”, IEEE/OSA Journal of Lightwave Technology, 2020
- A. Totovic, G. Dabos, N. Passalis, A. Tefas, N. Pleros, “Femtojoule per MAC Neuromorphic Photonics: An Energy and Technology Roadmap,” IEEE Journal of Selected Topics in Quantum Electronics, 2020
- G. Mourgias-Alexandris, G. Dabos, N. Passalis, A. Totovic, A. Tefas, and N. Pleros, “All-optical WDM Recurrent Neural Networks with Gating,” IEEE Journal of Selected Topics in Quantum Electronics, 2020
- G. Mourgias-Alexandris, A. Totovic, A. Tsakyridis, N. Passalis, A. Tefas K. Vyrsokinos, and N. Pleros, “Neuromorphic Photonics with Coherent Linear Neurons using dual-IQ modulation cells”, Journal of Lightwave Technology, 2019
- G. Mourgias-Alexandris, A. Tsakyridis, N. Passalis, A. Tefas, K. Vyrsokinos, and N. Pleros, “An all-optical neuron with sigmoid activation function,” Optics Express, 2019
Noise-resilient Deep Learning
Other Deep Learning Topics
Deep Generative Models
Privacy Preserving Learning
- M. Yamac, M. Ahishali, J. Raitharju, N. Passalis, M. Gabbouj, B. Sankur, “Multi-level Reversible Data Anonymization via Compressive Sensing and Data Hiding”, IEEE Transactions on Information Forensics & Security., 2020
- M. Yamac, M. Ahishali, N. Passalis, J. Raitharju, M. Gabbouj, B. Sankur, “Reversible Privacy Preservation Using Multi-level Encryption and Compressive Sensing,” European Signal Processing Conference (EUSIPCO)
Few-shot Learning
Exploratory Data Analysis
- N. Passalis, and A. Tefas, “Discriminative clustering using regularized subspace learning,” Pattern Recognition, 2019
- D. Spathis, N. Passalis, and A. Tefas, “Interactive dimensionality reduction using similarity projections,” Knowledge-Based Systems, 2018
- N. Passalis and A. Tefas, “Information Clustering using Manifold-based Optimization of the Bag-of-Features Representation,” Transactions on Cybernetics, 2018
- D. Spathis, N. Passalis and A. Tefas, “Fast, visual and interactive semi-supervised dimensionality reduction,” European Conference on Computer Vision Workshops - International Workshop on Compact and Efficient Feature Representation and Learning in Computer Vision - (ECCVW), 2018
Sentiment Analysis
- C. Tzogka, N. Passalis, A. Iosifidis, M. Gabbouj and A. Tefas, “Less is More: Deep Learning using Subjective Annotations for Sentiment Analysis from Social Media,” IEEE International Workshop on Machine Learning for Signal Processing (MLSP), 2019
- N. Passalis, S. Seficha, A. Tsantekidis, and A. Tefas, “Learning Sentiment-aware Trading Strategies for Bitcoin leveraging Deep Learning-based Financial News Analysis,” International Conference on Artificial Intelligence Applications and Innovations (AIAI), 2021
- D. Chatzakou, N. Passalis, and A. Vakali, “Multispot: Spotting sentiments with semantic aware multilevel cascaded analysis,” International Conference on Big Data Analytics and Knowledge Discovery, 2015
Multimodal Fusion
Neural Style Transfer
Brain Decoding
- A. Papadimitriou, N. Passalis and A. Tefas, “Decoding generic visual representations from human brain activity using machine learning,” European Conference on Computer Vision Workshops - Workshop on Brain Driven Computer Vision - (ECCVW), 2018
- A. Papadimitriou, N. Passalis, and A. Tefas, “Visual representation decoding from human brain activity using machine learning: A baseline study”, Pattern Recognition Letters, 2019
Optimization
Visual Question Answering
- T. Bozinis, N. Passalis, and A. Tefas, “Improving Visual Question Answering using Active Perception on Static Images,” International Conference on Pattern Recognition (ICPR), 2020
- V. Lioutas, N. Passalis and A. Tefas, “Explicit ensemble attention learning for improving visual question answering,” Pattern Recognition Letters, 2018
- V. Lioutas, N. Passalis and A. Tefas, “Visual Question Answering Using Explicit Visual Attention,” International Symposium on Circuits and Systems (ISCAS), 2018
Action Recognition
Information Retrieval
- N. Passalis, and A. Tefas, “Deep supervised hashing using quadratic spherical mutual information for efficient image retrieval”, Signal Processing: Image Communication, 2021
- N. Passalis, A. Iosifidis, M. Gabbouj and A. Tefas, “Variance-preserving deep metric learning for content-based image retrieval”, Pattern Recognition Letters, 2019
- N. Passalis and A. Tefas, “Learning bag-of-embedded-words representations for textual information retrieval,” Pattern Recognition, 2018
- N. Passalis and A. Tefas, “Learning Neural Bag-of-Features for Large Scale Information Retrieval,” IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2017