Y
Yannis Panagakis
Researcher at National and Kapodistrian University of Athens
Publications - 129
Citations - 2624
Yannis Panagakis is an academic researcher from National and Kapodistrian University of Athens. The author has contributed to research in topics: Computer science & Robustness (computer science). The author has an hindex of 24, co-authored 115 publications receiving 1942 citations. Previous affiliations of Yannis Panagakis include Aristotle University of Thessaloniki & Middlesex University.
Papers
More filters
Posted Content
TensorLy: Tensor Learning in Python
TL;DR: TensorLy is a Python library that provides a high-level API for tensor methods and deep tensorized neural networks and aims to follow the same standards adopted by the main projects of the Python scientific community, and to seamlessly integrate with them.
Journal ArticleDOI
SEWA DB: A Rich Database for Audio-Visual Emotion and Sentiment Research in the Wild
Jean Kossaifi,Robert Walecki,Yannis Panagakis,Jie Shen,Maximilian Schmitt,Fabien Ringeval,Jing Han,Vedhas Pandit,Antoine Toisoul,Björn Schuller,Kam Star,Elnar Hajiyev,Maja Pantic +12 more
TL;DR: The SEWA database as mentioned in this paper contains more than 2,000 minutes of audio-visual data of 398 people coming from six cultures, 50 percent female, and uniformly spanning the age range of 18 to 65 years old.
Journal Article
TensorLy: tensor learning in python
TL;DR: TensorLy as discussed by the authors is a Python library that provides a high-level API for tensor methods and deep tensorized neural networks, which can be scaled on multiple CPU or GPU machines.
Proceedings ArticleDOI
3D Face Morphable Models "In-the-Wild"
James Booth,Epameinondas Antonakos,Stylianos Ploumpis,George Trigeorgis,Yannis Panagakis,Stefanos Zafeiriou +5 more
TL;DR: This paper proposes the first, to the best of the knowledge, in-the-wild 3DMM by combining a powerful statistical model of facial shape, which describes both identity and expression, with an in- the-wild texture model, and demonstrates the first 3D facial database with relatively unconstrained conditions.
Journal ArticleDOI
Non-Negative Multilinear Principal Component Analysis of Auditory Temporal Modulations for Music Genre Classification
TL;DR: Three different sets of experiments conducted on the GTZAN and the ISMIR2004 Genre datasets demonstrate the superiority of NMPCA against the aforementioned subspace analysis techniques in extracting more discriminating features, especially when the training set has small cardinality.