Vassilis Katsouros

81 papers A 9B 10C 1Misc 7Journal 30Unranked 23

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Disentangling Local and Global Semantics in Diffusion Models for Image Editing. Int. J. Comput. Vis. Manos Plitsis, Theodoros Kouzelis, Panagiotis Koromilas, Vassilis Katsouros, Mihalis A. Nicolaou, Yannis Panagakis
2026	J	`jnl`	Pay (Cross) Attention to the Melody: Curriculum Masking for Single-Encoder Melodic Harmonization. CoRR Maximos Kaliakatsos-Papakostas, Dimos Makris, Konstantinos Soiledis, Konstantinos-Theodoros Tsamis, Vassilis Katsouros, Emilios Cambouropoulos
2026	J	`jnl`	When Slots Compete: Slot Merging in Object-Centric Learning. CoRR Christos Chatzisavvas, Panagiotis Rigas, George Ioannakis, Vassilis Katsouros, Nikolaos Mitianoudis
2025	J	`jnl`	A Machine Learning Approach for MIDI to Guitar Tablature Conversion. CoRR Maximos Kaliakatsos-Papakostas, Gregoris Bastas, Dimos Makris, Dorien Herremans, Vassilis Katsouros, Petros Maragos
2025	J	`jnl`	DeepMLF: Multimodal language model with learnable tokens for deep fusion in sentiment analysis. CoRR Efthymios Georgiou, Vassilis Katsouros, Yannis Avrithis, Alexandros Potamianos
2025	J	`jnl`	Exposing Hidden Biases in Text-to-Image Models via Automated Prompt Search. CoRR Manos Plitsis, Giorgos Bouritsas, Vassilis Katsouros, Yannis Panagakis
2025	J	`jnl`	HarmonyTok: Comparing Methods for Harmony Tokenization for Machine Learning. Inf. Maximos Kaliakatsos-Papakostas, Dimos Makris, Konstantinos Soiledis, Konstantinos-Theodoros Tsamis, Vassilis Katsouros, Emilios Cambouropoulos
2025	—	`conf`	Incorporating Structure and Chord Constraints in Symbolic Transformer-based Melodic Harmonization. AIMC Maximos Kaliakatsos-Papakostas, Konstantinos Soiledis, Konstantinos-Theodoros Tsamis, Dimos Makris, Vassilis Katsouros, Emilios Cambouropoulos
2025	J	`jnl`	Incorporating Structure and Chord Constraints in Symbolic Transformer-based Melodic Harmonization. CoRR Maximos Kaliakatsos-Papakostas, Konstantinos Soiledis, Konstantinos-Theodoros Tsamis, Dimos Makris, Vassilis Katsouros, Emilios Cambouropoulos
2025	—	`conf`	Krikri: Advancing Open Large Language Models for Greek. EMNLP (Findings) Dimitris Roussis, Leon Voukoutis, Georgios Paraskevopoulos, Sokratis Sofianopoulos, Prokopis Prokopidis, Vassilis P. Plagianakos, Athanasios Katsamanis, Stelios Piperidis, Vassilis Katsouros
2025	J	`jnl`	Krikri: Advancing Open Large Language Models for Greek. CoRR Dimitris Roussis, Leon Voukoutis, Georgios Paraskevopoulos, Sokratis Sofianopoulos, Prokopis Prokopidis, Vassilis Papavasileiou, Athanasios Katsamanis, Stelios Piperidis, Vassilis Katsouros
2025	J	`jnl`	MEDUSA: A Multimodal Deep Fusion Multi-Stage Training Framework for Speech Emotion Recognition in Naturalistic Conditions. CoRR Georgios Chatzichristodoulou, Despoina Kosmopoulou, Antonios Kritikos, Anastasia Poulopoulou, Efthymios Georgiou, Athanasios Katsamanis, Vassilis Katsouros, Alexandros Potamianos
2025	A	`conf`	Medusa: A Multimodal Deep Fusion Multi-Stage Training Framework for Speech Emotion Recognition in Naturalistic Conditions. INTERSPEECH Georgios Chatzichristodoulou, Despoina Kosmopoulou, Antonios Kritikos, Anastasia Poulopoulou, Efthymios Georgiou, Athanasios Katsamanis, Vassilis Katsouros, Alexandros Potamianos
2025	B	`conf`	Old Greek OCR Result Correction Using LLMs. DocEng Andreas Evaggelatos, Konstantinos Palaiologos, Basilis Gatos, Panagiotis Kaddas, Aikaterini Christopoulou, Vassilis Katsouros
2025	B	`conf`	Pay (Cross) Attention to the Melody: Curriculum Masking for Single-Encoder Melodic Harmonization. IEEE Big Data Maximos Kaliakatsos-Papakostas, Dimos Makris, Konstantinos Soiledis, Konstantinos-Theodoros Tsamis, Vassilis Katsouros, Emilios Cambouropoulos
2025	—	`conf`	Using LLMs for Improving the OCR Accuracy of Old Greek Handwritten Documents. TPDL (Short Papers and Workshops) Andreas Evangelatos, Konstantinos Palaiologos, Basilis Gatos, Panagiotis Kaddas, Aikaterini Christopoulou, Vassilis Katsouros, Andreas Kakridis
2025	J	`jnl`	VOX-KRIKRI: Unifying Speech and Language through Continuous Fusion. CoRR Dimitrios Damianos, Leon Voukoutis, Georgios Paraskevopoulos, Vassilis Katsouros
2024	—	`conf`	AI-Enabled Art Education: Unleashing Creative Potential and Exploring Co-Creation Frontiers. CSEDU (2) Vassilis Evangelidis, Helena G. Theodoropoulou, Vassilis Katsouros, Chairi Kiourt
2024	—	`conf`	Investigating Neural Networks and Transformer Models for Enhanced Comic Decoding. ICDAR (Workshops 1) Eleanna Kouletou, Vassilis Papavassiliou, Vassilis Katsouros
2024	Misc	`conf`	Investigating Personalization Methods in Text to Music Generation. ICASSP Manos Plitsis, Theodoros Kouzelis, Georgios Paraskevopoulos, Vassilis Katsouros, Yannis Panagakis
2024	J	`jnl`	Meltemi: The first open Large Language Model for Greek. CoRR Leon Voukoutis, Dimitris Roussis, Georgios Paraskevopoulos, Sokratis Sofianopoulos, Prokopis Prokopidis, Vassilis Papavasileiou, Athanasios Katsamanis, Stelios Piperidis, Vassilis Katsouros
2024	J	`jnl`	Sample-Efficient Unsupervised Domain Adaptation of Speech Recognition Systems: A Case Study for Modern Greek. IEEE ACM Trans. Audio Speech Lang. Process. Georgios Paraskevopoulos, Theodoros Kouzelis, Georgios Rouvalis, Athanasios Katsamanis, Vassilis Katsouros, Alexandros Potamianos
2024	A	`conf`	The Greek podcast corpus: Competitive speech models for low-resourced languages with weakly supervised data. INTERSPEECH Georgios Paraskevopoulos, Chara Tsoukala, Athanasios Katsamanis, Vassilis Katsouros
2024	J	`jnl`	The Greek podcast corpus: Competitive speech models for low-resourced languages with weakly supervised data. CoRR Georgios Paraskevopoulos, Chara Tsoukala, Athanasios Katsamanis, Vassilis Katsouros
2023	—	`conf`	A System for Processing and Recognition of Greek Byzantine and Post-Byzantine Documents. ICDAR (4) Panagiotis Kaddas, Konstantinos Palaiologos, Basilis Gatos, Vassilis Katsouros, Katerina Christopoulou
2023	J	`jnl`	Investigating Personalization Methods in Text to Music Generation. CoRR Manos Plitsis, Theodoros Kouzelis, Georgios Paraskevopoulos, Vassilis Katsouros, Yannis Panagakis
2023	J	`jnl`	Sample-Efficient Unsupervised Domain Adaptation of Speech Recognition Systems A case study for Modern Greek. CoRR Georgios Paraskevopoulos, Theodoros Kouzelis, Georgios Rouvalis, Athanasios Katsamanis, Vassilis Katsouros, Alexandros Potamianos
2023	J	`jnl`	Weakly-supervised Automated Audio Captioning via text only training. CoRR Theodoros Kouzelis, Vassilis Katsouros
2023	A	`conf`	Weakly-supervised forced alignment of disfluent speech using phoneme-level modeling. INTERSPEECH Theodoros Kouzelis, Georgios Paraskevopoulos, Athanasios Katsamanis, Vassilis Katsouros
2023	J	`jnl`	Weakly-supervised forced alignment of disfluent speech using phoneme-level modeling. CoRR Theodoros Kouzelis, Georgios Paraskevopoulos, Athanasios Katsamanis, Vassilis Katsouros
2022	Misc	`conf`	A Few-Sample Strategy for Guitar Tablature Transcription Based on Inharmonicity Analysis and Playability Constraints. ICASSP Grigoris Bastas, Stefanos Koutoupis, Maximos Kaliakatsos-Papakostas, Vassilis Katsouros, Petros Maragos
2022	J	`jnl`	DanceConv: Dance Motion Generation With Convolutional Networks. IEEE Access Kosmas Kritsis, Aggelos Gkiokas, Aggelos Pikrakis, Vassilis Katsouros
2022	—	`conf`	NLP-Theatre: Employing Speech Recognition Technologies for Improving Accessibility and Augmenting the Theatrical Experience. IntelliSys (2) Alkiviadis Katsalis, Konstantinos Christantonis, Charalampos Tsioustas, Pantelis I. Kaplanoglou, Maximos Kaliakatsos-Papakostas, Athanasios Katsamanis, Konstantinos I. Diamantaras, Vassilis Katsouros, Evita F. Fotinea, Depy Panga, Dimitra Loupi
2022	—	`conf`	Regotron: Regularizing the Tacotron2 Architecture Via Monotonic Alignment Loss. SLT Efthymios Georgiou, Kosmas Kritsis, Georgios Paraskevopoulos, Athanasios Katsamanis, Vassilis Katsouros, Alexandros Potamianos
2022	J	`jnl`	Regotron: Regularizing the Tacotron2 architecture via monotonic alignment loss. CoRR Efthymios Georgiou, Kosmas Kritsis, Georgios Paraskevopoulos, Athanasios Katsamanis, Vassilis Katsouros, Alexandros Potamianos
2022	B	`conf`	SciPar: A Collection of Parallel Corpora from Scientific Abstracts. LREC Dimitrios Roussis, Vassilis Papavassiliou, Prokopis Prokopidis, Stelios Piperidis, Vassilis Katsouros
2022	—	`conf`	Towards a DHH Accessible Theater: Real-Time Synchronization of Subtitles and Sign Language Videos with ASR and NLP Solutions. PETRA Grigoris Bastas, Maximos Kaliakatsos-Papakostas, Georgios Paraskevopoulos, Pantelis I. Kaplanoglou, Konstantinos Christantonis, Charalampos Tsioustas, Dimitris Mastrogiannopoulos, Depy Panga, Evita F. Fotinea, Athanasios Katsamanis, Vassilis Katsouros, Konstantinos I. Diamantaras, Petros Maragos
2022	A	`conf`	Zero-Shot Cross-lingual Aphasia Detection using Automatic Speech Recognition. INTERSPEECH Gerasimos Chatzoudis, Manos Plitsis, Spyridoula Stamouli, Athanasia-Lida Dimou, Nassos Katsamanis, Vassilis Katsouros
2022	J	`jnl`	Zero-Shot Cross-lingual Aphasia Detection using Automatic Speech Recognition. CoRR Gerasimos Chatzoudis, Manos Plitsis, Spyridoula Stamouli, Athanasia-Lida Dimou, Athanasios Katsamanis, Vassilis Katsouros
2021	B	`conf`	Attention-based Multimodal Feature Fusion for Dance Motion Generation. ICMI Kosmas Kritsis, Aggelos Gkiokas, Aggelos Pikrakis, Vassilis Katsouros
2020	B	`conf`	Air-Writing Recognition using Deep Convolutional and Recurrent Neural Network Architectures. ICFHR Grigoris Bastas, Kosmas Kritsis, Vassilis Katsouros
2020	J	`jnl`	Educational Technology - Introduction to the Special Theme. ERCIM News Vassilis Katsouros
2020	J	`jnl`	Music in Education through Technology. ERCIM News Maximos Kaliakatsos-Papakostas, Kosmas Kritsis, Vassilis Katsouros
2020	J	`jnl`	On the Adaptability of Recurrent Neural Networks for Real-Time Jazz Improvisation Accompaniment. Frontiers Artif. Intell. Kosmas Kritsis, Theatina Kylafi, Maximos Kaliakatsos-Papakostas, Aggelos Pikrakis, Vassilis Katsouros
2020	—	`conf`	Towards a Classification and Evaluation of Symbolic Music Encodings for RNN Music Generation. AIMC Manos Plitsis, Kosmas Kritsis, Maximos Kaliakatsos-Papakostas, Aggelos Pikrakis, Vassilis Katsouros
2019	—	`conf`	An Environment for Gestural Interaction with 3D Virtual Musical Instruments as an Educational Tool. EUSIPCO Christos Garoufis, Athanasia Zlatintsi, Kosmas Kritsis, Panagiotis Paraskevas Filntisis, Vassilis Katsouros, Petros Maragos
2019	—	`conf`	Deep Convolutional and LSTM Neural Network Architectures on Leap Motion Hand Tracking Data Sequences. EUSIPCO Kosmas Kritsis, Maximos Kaliakatsos-Papakostas, Vassilis Katsouros, Aggelos Pikrakis
2019	J	`jnl`	Enabling the human in the loop: Linked data and knowledge in industrial cyber-physical systems. Annu. Rev. Control. Christos Emmanouilidis, Petros Pistofidis, Luka Bertoncelj, Vassilis Katsouros, Apostolos P. Fournaris, Christos Koulamas, Cristobal Ruiz-Carcel
2018	—	`conf`	A Web-based Real-Time Kinect Application for Gestural Interaction with Virtual Musical Instruments. Audio Mostly Conference Athanasia Zlatintsi, Panagiotis Paraskevas Filntisis, Christos Garoufis, Antigoni Tsiami, Kosmas Kritsis, Maximos A. Kaliakatsos-Papakostas, Aggelos Gkiokas, Vassilis Katsouros, Petros Maragos
2018	—	`conf`	A web-based 3D environment for gestural interaction with virtual music instruments as a STEAM education tool. NIME Kosmas Kritsis, Aggelos Gkiokas, Carlos Árpád Acosta, Quentin Lamerand, Robert Piéchaud, Maximos Kaliakatsos-Papakostas, Vassilis Katsouros
2018	—	`conf`	Interactive Control of Explicit Musical Features in Generative LSTM-based Systems. Audio Mostly Conference Maximos Kaliakatsos-Papakostas, Aggelos Gkiokas, Vassilis Katsouros
2018	J	`jnl`	Musical track popularity mining dataset: Extension & experimentation. Neurocomputing Ioannis Karydis, Aggelos Gkiokas, Vassilis Katsouros, Lazaros S. Iliadis
2018	—	`ch.`	iMuSciCA: Interactive Music Science Collaborative Activities for STEAM Learning. Designing for the User Experience in Learning Systems Vassilis Katsouros, Evita F. Fotinea, Renaat Frans, Erica Andreotti, Petros Stergiopoulos, Manolis Chaniotakis, Thomas Fischer, Robert Piéchaud, Zoltan Karpati, Pierre LaBorde, Daniel Martín-Albo, Fotini Simistira, Marcus Liwicki
2017	—	`conf`	Convolutional Neural Networks for Real-Time Beat Tracking: A Dancing Robot Application. ISMIR Aggelos Gkiokas, Vassilis Katsouros
2016	Misc	`conf`	Musical Track Popularity Mining Dataset. AIAI Ioannis Karydis, Aggelos Gkiokas, Vassilis Katsouros
2016	B	`conf`	Recognition of Greek Polytonic on Historical Degraded Texts Using HMMs. DAS Vassilis Katsouros, Vassilis Papavassiliou, Fotini Simistira, Basilis Gatos
2016	J	`jnl`	Towards Multi-Purpose Spectral Rhythm Features: An Application to Dance Style, Meter and Tempo Estimation. IEEE ACM Trans. Audio Speech Lang. Process. Aggelos Gkiokas, Vassilis Katsouros, George Carayannis
2015	A	`conf`	GRPOLY-DB: An old Greek polytonic document image database. ICDAR Basilis Gatos, Nikolaos Stamatopoulos, Georgios Louloudis, Giorgos Sfikas, George Retsinas, Vassilis Papavassiliou, Fotini Sunistira, Vassilis Katsouros
2015	A	`conf`	Recognition of historical Greek polytonic scripts using LSTM networks. ICDAR Fotini Simistira, Adnan Ul-Hassan, Vassilis Papavassiliou, Basilis Gatos, Vassilis Katsouros, Marcus Liwicki
2015	J	`jnl`	Recognition of online handwritten mathematical formulas using probabilistic SVMs and stochastic context free grammars. Pattern Recognit. Lett. Fotini Simistira, Vassilis Katsouros, George Carayannis
2014	—	`conf`	Deploying Deep Belief Nets for content based audio music similarity. IISA Aggelos Gkiokas, Vassilis Katsouros, George Carayannis
2014	B	`conf`	Recognition of Spatial Relations in Mathematical Formulas. ICFHR Fotini Simistira, Vassilis Papavassiliou, Vassilis Katsouros, George Carayannis
2013	—	`conf`	Structural analysis of online handwritten mathematical symbols based on support vector machines. DRR Fotini Simistira, Vassilis Papavassiliou, Vassilis Katsouros, George Carayannis
2012	B	`conf`	A Morphology Based Approach for Binarization of Handwritten Documents. ICFHR Vassilis Papavassiliou, Fotini Simistira, Vassilis Katsouros, George Carayannis
2012	B	`conf`	A System for Recognition of On-Line Handwritten Mathematical Expressions. ICFHR Fotini Simistira, Vassilis Papavassiliou, Vassilis Katsouros, George Carayannis
2012	—	`conf`	A mean shift algorithm for manifolds of exponential families. ISSPA Themos Stafylakis, Vassilis Katsouros, Patrick Kenny, Pierre Dumouchel
2012	—	`conf`	Mean shift algorithm for exponential families with applications to speaker clustering. Odyssey Themos Stafylakis, Vassilis Katsouros, Patrick Kenny, Pierre Dumouchel
2012	Misc	`conf`	Music tempo estimation and beat tracking by applying source separation and metrical relations. ICASSP Aggelos Gkiokas, Vassilis Katsouros, George Carayannis, Themos Stafylakis
2012	—	`conf`	Reducing Tempo Octave Errors by Periodicity Vector Coding And SVM Learning. ISMIR Aggelos Gkiokas, Vassilis Katsouros, George Carayannis
2011	Misc	`conf`	Closed-form expressions vs. BIC: A comparison for speaker clustering. ICASSP Themos Stafylakis, Xavier Anguera Miró, Vassilis Katsouros, George Carayannis
2011	A	`conf`	Enhancing Handwritten Word Segmentation by Employing Local Spatial Features. ICDAR Fotini Simistira, Vassilis Papavassiliou, Themos Stafylakis, Vassilis Katsouros
2010	B	`conf`	A Morphological Approach for Text-Line Segmentation in Handwritten Documents. ICFHR Vassilis Papavassiliou, Vassilis Katsouros, George Carayannis
2010	Misc	`conf`	A new penalty term for the BIC with respect to speaker diarization. ICASSP Themos Stafylakis, Georgios Tzimiropoulos, Vassilis Katsouros, George Carayannis
2010	J	`jnl`	Handwritten document image segmentation into text lines and words. Pattern Recognit. Vassilis Papavassiliou, Themos Stafylakis, Vassilis Katsouros, George Carayannis
2010	—	`conf`	Speaker clustering via the mean shift algorithm. Odyssey Themos Stafylakis, Vassilis Katsouros, George Carayannis
2010	—	`conf`	Tempo Induction Using Filterbank Analysis and Tonal Features. ISMIR Aggelos Gkiokas, Vassilis Katsouros, George Carayannis
2010	J	`jnl`	The Segmental Bayesian Information Criterion and Its Applications to Speaker Diarization. IEEE J. Sel. Top. Signal Process. Themos Stafylakis, Vassilis Katsouros, George Carayannis
2009	A	`conf`	Redefining the Bayesian information criterion for speaker diarisation. INTERSPEECH Themos Stafylakis, Vassilis Katsouros, George Carayannis
2008	Misc	`conf`	Robust text-line and word segmentation for handwritten documents images. ICASSP Themos Stafylakis, Vassilis Papavassiliou, Vassilis Katsouros, George Carayannis
2007	A	`conf`	A Parametric Spectral-Based Method for Verification of Text in Videos. ICDAR Vassilis Papavassiliou, Themos Stafylakis, Vassilis Katsouros, George Carayannis
2007	C	`conf`	Efficient combination of parametric spaces, models and metrics for speaker diarization ASRU Themos Stafylakis, Vassilis Katsouros, George Carayannis