| Mmlatch: Bottom-up top-down fusion for multimodal sentiment analysis G Paraskevopoulos, E Georgiou, A Potamianos ICASSP 2022-2022 IEEE international conference on acoustics, speech and …, 2022 | 62 | 2022 |
| Deep Hierarchical Fusion with Application in Sentiment Analysis. E Georgiou, C Papaioannou, A Potamianos Interspeech, 1646-1650, 2019 | 39 | 2019 |
| M3: MultiModal Masking Applied to Sentiment Analysis. E Georgiou, G Paraskevopoulos, A Potamianos Interspeech, 2876-2880, 2021 | 16 | 2021 |
| Multimodal classification of safety-report observations G Paraskevopoulos, P Pistofidis, G Banoutsos, E Georgiou, V Katsouros Applied Sciences 12 (12), 5781, 2022 | 13 | 2022 |
| owMix: A Versatile Regularizer for Multimodal Sentiment Analysis E Georgiou, Y Avrithis, A Potamianos IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2024 | 6 | 2024 |
| Deep hierarchical fusion for machine intelligence applications E Georgiou, G Paraskevopoulos, J Gibson, A Potamianos, S Narayanan US Patent 11,862,145, 2024 | 6 | 2024 |
| Alternating objectives generates stronger PGD-based adversarial attacks N Antoniou, E Georgiou, A Potamianos arXiv preprint arXiv:2212.07992, 2022 | 6 | 2022 |
| DeepMLF: Multimodal language model with learnable tokens for deep fusion in sentiment analysis E Georgiou, V Katsouros, Y Avrithis, A Potamianos arXiv preprint arXiv:2504.11082, 2025 | 4 | 2025 |
| A multi-task bert model for schema-guided dialogue state tracking E Kapelonis, E Georgiou, A Potamianos arXiv preprint arXiv:2207.00828, 2022 | 4 | 2022 |
| SeqAug: Sequential Feature Resampling as a modality agnostic augmentation method E Georgiou, A Potamianos arXiv preprint arXiv:2305.01954, 2023 | 3 | 2023 |
| Regotron: Regularizing the Tacotron2 architecture via monotonic alignment loss E Georgiou, K Kritsis, G Paraskevopoulos, A Katsamanis, V Katsouros, ... 2022 IEEE Spoken Language Technology Workshop (SLT), 977-983, 2023 | 3 | 2023 |
| Mechanistic Learning with Guided Diffusion Models to Predict Spatio-Temporal Brain Tumor Growth D Laslo, E Georgiou, MG Linguraru, A Rauschecker, S Muller, ... arXiv preprint arXiv:2509.09610, 2025 | 2 | 2025 |
| MEDUSA: A Multimodal Deep Fusion Multi-Stage Training Framework for Speech Emotion Recognition in Naturalistic Conditions G Chatzichristodoulou, D Kosmopoulou, A Kritikos, A Poulopoulou, ... arXiv preprint arXiv:2506.09556, 2025 | 2 | 2025 |
| Y-Drop: A Conductance based Dropout for fully connected layers E Georgiou, G Paraskevopoulos, A Potamianos arXiv preprint arXiv:2409.09088, 2024 | 2 | 2024 |
| End-to-end generative zero-shot learning via few-shot learning G Chochlakis, E Georgiou, A Potamianos arXiv preprint arXiv:2102.04379, 2021 | 1 | 2021 |
| Masked Diffusion Language Models with Frequency-Informed Training D Kosmopoulou, E Georgiou, V Dorovatas, G Paraskevopoulos, ... Proceedings of the First BabyLM Workshop, 531-539, 2025 | | 2025 |
| Multimodal representation learning with application in sentiment analysis E Georgiou National Technical University of Athens (NTUA), 2025 | | 2025 |
| A Principled Framework for Multi-View Contrastive Learning P Koromilas, E Georgiou, G Bouritsas, T Giannakopoulos, MA Nicolaou, ... arXiv preprint arXiv:2507.06979, 2025 | | 2025 |
| Rethinking Objectives for Multi-View and Multi-Modal Contrastive Learning P Koromilas, E Georgiou, G Bouritsas, T Giannakopoulos, M Nicolaou, ... UniReps: 3rd Edition of the Workshop on Unifying Representations in Neural …, 2025 | | 2025 |
| AudioVisual Speech Synthesis: A brief literature review E Georgiou, A Katsamanis arXiv preprint arXiv:2103.03927, 2021 | | 2021 |
Alexandros PotamianosNational Technical University of AthensVerified email at central.ntua.gr
