1 code implementation • 19 Feb 2024 • James Oldfield, Markos Georgopoulos, Grigorios G. Chrysos, Christos Tzelepis, Yannis Panagakis, Mihalis A. Nicolaou, Jiankang Deng, Ioannis Patras
The Mixture of Experts (MoE) paradigm provides a powerful way to decompose inscrutable dense layers into smaller, modular computations often more amenable to human interpretation, debugging, and editability.
no code implementations • 26 Sep 2023 • Georgia Kourmouli, Nikos Kostagiolas, Yannis Panagakis, Mihalis A. Nicolaou
We present a locality-aware method for interpreting the latent space of wavelet-based Generative Adversarial Networks (GANs), that can well capture the large spatial and spectral variability that is characteristic to satellite imagery.
2 code implementations • 23 May 2023 • James Oldfield, Christos Tzelepis, Yannis Panagakis, Mihalis A. Nicolaou, Ioannis Patras
Latent image representations arising from vision-language models have proved immensely useful for a variety of downstream tasks.
2 code implementations • 3 Aug 2022 • Nikos Kostagiolas, Mihalis A. Nicolaou, Yannis Panagakis
In recent years, considerable advancements have been made in the area of Generative Adversarial Networks (GANs), particularly with the advent of style-based architectures that address many key shortcomings - both in terms of modeling capabilities and network interpretability.
1 code implementation • 31 May 2022 • James Oldfield, Christos Tzelepis, Yannis Panagakis, Mihalis A. Nicolaou, Ioannis Patras
Recent advances in the understanding of Generative Adversarial Networks (GANs) have led to remarkable progress in visual editing and synthesis tasks, capitalizing on the rich semantics that are embedded in the latent spaces of pre-trained GANs.
no code implementations • 23 Nov 2021 • James Oldfield, Markos Georgopoulos, Yannis Panagakis, Mihalis A. Nicolaou, Ioannis Patras
This paper addresses the problem of finding interpretable directions in the latent space of pre-trained Generative Adversarial Networks (GANs) to facilitate controllable image synthesis.
1 code implementation • 9 Aug 2021 • Charalambos Chrysostomou, Floris Alexandrou, Mihalis A. Nicolaou, Huseyin Seker
This paper focuses on accurately predicting if an Influenza type A virus can infect specific hosts, and more specifically, Human, Avian and Swine hosts, using only the protein sequence of the HA gene.
no code implementations • 7 Jul 2021 • Yannis Panagakis, Jean Kossaifi, Grigorios G. Chrysos, James Oldfield, Mihalis A. Nicolaou, Anima Anandkumar, Stefanos Zafeiriou
Tensors, or multidimensional arrays, are data structures that can naturally represent visual data of multiple dimensions.
no code implementations • 6 Jun 2020 • Markos Georgopoulos, James Oldfield, Mihalis A. Nicolaou, Yannis Panagakis, Maja Pantic
By evaluating on several age-annotated datasets in both single- and cross-database experiments, we show that the proposed method outperforms state-of-the-art algorithms for age transfer, especially in the case of age groups that lie in the tails of the label distribution.
1 code implementation • 31 May 2019 • Charles Ringer, James Alfred Walker, Mihalis A. Nicolaou
Video game streaming provides the viewer with a rich set of audio-visual data, conveying information both with regards to the game itself, through game footage and audio, as well as the streamer's emotional state and behaviour via webcam footage and audio.
1 code implementation • 9 Apr 2019 • James Oldfield, Yannis Panagakis, Mihalis A. Nicolaou
Recently, a multitude of methods for image-to-image translation have demonstrated impressive results on problems such as multi-domain or multi-attribute transfer.
no code implementations • 25 Jul 2018 • Charles Ringer, Mihalis A. Nicolaou
We consider the problem of automatic highlight-detection in video game streams.
1 code implementation • 29 Apr 2018 • Dimitrios Kollias, Panagiotis Tzirakis, Mihalis A. Nicolaou, Athanasios Papaioannou, Guoying Zhao, Björn Schuller, Irene Kotsia, Stefanos Zafeiriou
Automatic understanding of human affect using visual signals is of great importance in everyday human-machine interactions.
2 code implementations • 27 Apr 2017 • Panagiotis Tzirakis, George Trigeorgis, Mihalis A. Nicolaou, Björn Schuller, Stefanos Zafeiriou
The system is then trained in an end-to-end fashion where - by also taking advantage of the correlations of the each of the streams - we manage to significantly outperform the traditional approaches based on auditory and visual handcrafted features for the prediction of spontaneous and natural emotions on the RECOLA database of the AVEC 2016 research challenge on emotion recognition.
no code implementations • CVPR 2016 • George Trigeorgis, Patrick Snape, Mihalis A. Nicolaou, Epameinondas Antonakos, Stefanos Zafeiriou
Cascaded regression has recently become the method of choice for solving non-linear least squares problems such as deformable image alignment.
no code implementations • CVPR 2016 • George Trigeorgis, Mihalis A. Nicolaou, Stefanos Zafeiriou, Bjorn W. Schuller
Thus, they fail to capture complex, hierarchical non-linear representations which may prove to be beneficial towards the task of temporal alignment, particularly when dealing with multi-modal data (e. g., aligning visual and acoustic information).
no code implementations • CVPR 2013 • Yannis Panagakis, Mihalis A. Nicolaou, Stefanos Zafeiriou, Maja Pantic
The superiority of the proposed method against the state-of-the-art time alignment methods, namely the canonical time warping and the generalized time warping, is indicated by the experimental results on both synthetic and real datasets.
no code implementations • 13 Mar 2013 • Mihalis A. Nicolaou, Stefanos Zafeiriou, Maja Pantic
We present a unifying framework which reduces the construction of probabilistic component analysis techniques to a mere selection of the latent neighbourhood, thus providing an elegant and principled framework for creating novel component analysis models as well as constructing probabilistic equivalents of deterministic component analysis methods.