AuthorPublication TitleConference NameOpen Access
Rafail Tsirbas, Giorgos Vasiliadis, Sotiris IoannidisThe Best of Many Worlds: Scheduling Machine Learning Inference on CPU-GPU Integrated Architectures2022 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW2022)zenodo
Francesco Paissan, Alberto Ancilotto, Alessio Brutti, Elisabetta FarellaScalable neural architectures for end-to-end environmental sound classificationIEEE International Conference on Acoustics, Speech, & Signal Processing (ICASSP)zenodo
Luca Zanella, Yiming Wang, Nicola Dall Asen, Alberto Ancilotto, Francesco Paissan, Elisa Ricci, Elisabetta Farella, Alessio Brutti and Marco PistoreResponsible AI at the edge: towards privacy-preserving smart citiesItal-IA 2022 Convegno del Laboratorio nazionale CINI-AIISzenodo
Arian Bakhtiarnia, Qi Zhang, Alexandros IosifidisMulti-Exit Vision Transformer for Dynamic Inference32nd British Machine Vision Conferencezenodo
Parthasaarathy Sudarsanam, Archontis Politis, Konstantinos DrossosAssessment of Self-Attention on Learned Features For Sound Event Localization and DetectionDCASE Challengezenodo
Jan Berg, Konstantinos DrossosContinual Learning for Automated Audio Captioning Using The Learning Without Forgetting ApproachDCASE Challengezenodo
Andreas Triantafyllopoulos, Manuel Milling, Konstantinos Drossos, Björn W. SchullerFairness and underspecification in acoustic scene classification: The case for disaggregated evaluations DCASE Challengezenodo
Andrea Simonelli, Samuel Rota Bulò, Lorenzo Porzi, Peter Kontschieder, Elisa RicciAre We Missing Confidence in Pseudo-LiDAR Methods for Monocular 3D Object Detection?International Conference on Computer Vision 2021zenodo
Dragana Bajovic, Arian Bakhtiarnia et. alMARVEL: Multimodal Extreme Scale Data Analytics for Smart Cities EnvironmentsFourth International Balkan Conference on Communications and Networking (BalkanCom 2021)zenodo
Einari Vaaras, Sari Ahlqvist-Björkroth, Konstantinos Drossos, Okko RäsänenAutomatic Analysis of the Emotional Content of Speech in Daylong Child-Centered Recordings from a Neonatal Intensive Care UnitInterspeech 2021zenodo
An Tran, Konstantinos Drossos, Tuomas VirtanenWaveTransformer: An Architecture for Audio Captioning Based on Learning Temporal and Time-Frequency Information2021 29th European Signal Processing Conference (EUSIPCO)zenodo
Firas Laakom, Jenni Raitoharju, Alexandros Iosifidis, Moncef GabboujWithin-layer Diversity Reduces Generalization GapICML-21zenodo
Arian Bakhtiarnia, Qi Zhang, Alexandros IosifidisImproving the Accuracy of Early Exits in Multi-Exit Architectures via Curriculum LearningIJCNN 2021zenodo
Francesco Paissan, Massimo Gottardi, Elisabetta FarellaEnabling energy efficient machine learning on a Ultra-Low-Power vision sensor for IoTSLOHA 2021 zenodo

AuthorPublication TitleTitle of the Journal/Magazine:Open Access
Gianmarco Cerutti, Renzo Andri, Lukas Cavigelli, Michele Magno, Elisabetta Farella, Luca Benini.Sub-mW Keyword Spotting on an MCU: Analog Binary Feature Extraction and Binary Neural NetworksIEEE Transactions on Circuits and Systems Izenodo
Kateryna Chumachenko, Alexandros Iosifidis, Moncef GabboujFeedforward neural networks initialization based on discriminant learningNeural Networkszenodo
Andres Ferraro, Xavier Favory, Konstantinos Drossos, Yuntae Kim, Dmitry BogdanovEnriched Music Representations With Multiple Cross-Modal Contrastive LearningIEEE Signal Processing Letterszenodo
Emmanuel Rovithis, Nikolaos Moustakas, Konstantinos Vogklis, Konstantinos Drossos. Andreas FlorosDesign Recommendations for a Collaborative Game of Bird Call Recognition Based on Internet of Sound PracticesJournal of the Audio Engineering Societyzenodo
Lorenzo Valerio, Franco Maria Nardini, Andrea Passarella, Raffaele PeregoDynamic hard pruning of Neural Networks at the edge of the internetJournal of Network and Computer Applications Vol. 200zenodo

Shaohua Wan, Chen Chen, Alexandros IosifidisCross-Media Learning for Visual Question AnsweringImage and Vision ComputingElsevier

Key Facts

  • Project Coordinator: Dr. Sotiris Ioannidis
  • Institution: Foundation for Research and Technology Hellas (FORTH)
  • E-mail: marvel-info{at} 
  • Start: 01.01.2021
  • Duration: 36 months
  • Participating Organisations: 17
  • Number of countries: 12

Get Connected



This project has received funding from the European Union’s Horizon 2020 Research and Innovation program under grant agreement No 957337. The website reflects only the view of the author(s) and the Commission is not responsible for any use that may be made of the information it contains.