aRTIFICIAL iNTELLIGENCE for the Deaf

Livrables

Network compression leveraging i the Bayesian inference arguments that underly the envisaged machine learning models of WP4 and WP5 ii network distillation approaches

Generative system translating language to SL gesture trajectories

The algorithms developed for translating language (speech/text) to SL trajectories, trained using the dataset of D5.1, and embedded into an AR environment.

System translating SL footage to language

The Deep Learning models aiD will devise to address the problem of generating text transcription and synthetic speech pertaining to SL video footage trained using the dataset of D41

Website and social media presence

A public website and accounts in social media Publicity material including videos describing the project rationale and ambition

Publications

Dialog speech sentiment classification for imbalanced datasets

Auteurs: Sergis Nicolaou, Lambros Mavrides, Georgina Tryfou, Kyriakos Tolias, Konstantinos Panousis, Sotirios Chatzis, Sergios Theodoridis
Publié dans: Proceedings of SPECOM 2021, 2021
Éditeur: Springer Nature

Variational Conditional Dependence Hidden Markov Models for Skeleton-Based Action Recognition

Auteurs: Panousis, Konstantinos Panagiotis; Chatzis, Sotirios; Theodoridis, Sergios
Publié dans: Proceedings of ISVC 2021, 2021
Éditeur: Springer

Stochastic Local Winner-Takes-All Networks Enable Profound Adversarial Robustness

Auteurs: Konstantinos P. Panousis, Sotirios Chatzis, and Sergios Theodoridis
Publié dans: NeurIPS Workshops 2022, 2021
Éditeur: NeurIPS
DOI: 10.5281/zenodo.6000329

A New Dataset for End-to-End Sign Language Translation: The Greek Elementary School Dataset

Auteurs: Andreas Voskou, Konstantinos P. Panousis, Harris Partaourides, Kyriakos Tolias, Sotirios Chatzis
Publié dans: Proceedings of the IEEE/CVF International Conference on Computer Vision. 2023. p. 1966-1975, 2023
Éditeur: ICCVW2023 - ACVR
DOI: 10.48550/arxiv.2310.04753

Local Competition and Stochasticity for Adversarial Robustness in Deep Learning

Auteurs: Konstantinos Panousis, Sotirios Chatzis, Antonios Alexos, Sergios Theodoridis
Publié dans: Proceedings of AISTATS 2021, 2021
Éditeur: PMLR
DOI: 10.5281/zenodo.5498188

Competing Mutual Information Constraints with Stochastic Competition-based Activations for Learning Diversified Representations

Auteurs: Konstantinos P. Panousis, Anastasios Antoniadis, Sotirios Chatzis
Publié dans: Proceedings of AAAI 2022, 2022
Éditeur: AAAI
DOI: 10.5281/zenodo.6000363

Making Vision Networks Interpretable viaCompetition and Dissection

Auteurs: Konstantinos Panousis, Sotirios Chatzis
Publié dans: Proceedings of NeurIPS 2023, 2023
Éditeur: Konstantinos Panousis
DOI: 10.48550/arxiv.2310.04929

Stochastic Transformer Networks with Linear Competing Units: Application to end-to-end SL Translation

Auteurs: Voskou, Andreas; Panousis, Konstantinos P.; Kosmopoulos, Dimitrios; Metaxas, Dimitris N.; Chatzis, Sotirios
Publié dans: Proc. ICCV 2021, 2021
Éditeur: ICCV
DOI: 10.5281/zenodo.5498338

Stochastic Deep Networks with Linear Competing Units for Model-Agnostic Meta-Learning

Auteurs: Konstantinos Kalais, Sotirios Chatzis
Publié dans: Proc. ICML 2022, 2022
Éditeur: ICML
DOI: 10.5281/zenodo.6580332

Stochastic Transformer Networks with Linear Competing Units: Application to end-to-end SL Translation

Auteurs: Andreas Voskou, Konstantinos P. Panousis, Dimitrios Kosmopoulos, Dimitris N. Metaxas, Sotirios Chatzis
Publié dans: Proceedings of IEEE ICCV 2021, 2021
Éditeur: IEEE

Livrables

Publications

Partager cette page

Télécharger