Welcome to my page!

My name is George and I like to think about optimisation problems.

I am currently a machine learning researcher with Citadel, London. I obtained my Ph.D. in machine learning from the Department of Computing, at Imperial College London (2013-2017). My work mostly focused in the unification of component analysis techniques with deep learning, predominantly for unsupervised and semi-supervised applications.

The application areas I touched upon are that of 3d reconstruction, object alignment, facial biometrics, and emotion recognition.

I am also lucky enough to be a recipient of the prestigious Google Fellowship in Machine Perception, Speech Technology, and Computer Vision.



You can reach me at trigeorgis@gmail.com

Articles


Joint multi-view face alignment in the wild
J. Deng, G. Trigeorgis, Y. Zhou, S. Zafeiriou
IEEE Transactions on Image Processing, 2019
@article{deng2019joint,
  title = {Joint multi-view face alignment in the wild},
  author = {Deng, Jiankang and Trigeorgis, George and Zhou, Yuxiang and Zafeiriou, Stefanos},
  journal = {IEEE Transactions on Image Processing},
  volume = {28},
  number = {7},
  pages = {3636--3648},
  year = {2019},
  publisher = {IEEE}
}
Deep Canonical Time Warping for simultaneous alignment and representation learning of sequences
G. Trigeorgis, M. Nicolaou, S. Zafeiriou, B. Schuller
Transactions of Pattern Analysis and Machine Intelligence (TPAMI), 2018
@article{dsnmf2015,
  title = {{Deep Canonical Time Warping for simultaneous alignment and representation learning of sequences}},
  author = {Trigeorgis, George and Nicolaou, Mihalis and Zafeiriou, Stefanos and Schuller, Bjoern W.},
  journal = {{Transactions of Pattern Analysis and Machine Intelligence (TPAMI)}},
  year = {2018}
}
A deep matrix factorization method for learning attribute representations
G. Trigeorgis, K. Bousmalis, S. Zafeiriou, B. Schuller
Transactions of Pattern Analysis and Machine Intelligence (TPAMI), 2016
@article{dsnmf2015,
  title = {{A deep matrix factorization method for learning attribute representations}},
  author = {Trigeorgis, George and Bousmalis, Konstantinos and Zafeiriou, Stefanos and Schuller, Bjoern W.},
  journal = {{Transactions of Pattern Analysis and Machine Intelligence (TPAMI)}},
  year = {2016}
}
An algorithm for finding biologically significant features in microarray data based on a priori manifold learning
Z. Hira*, G. Trigeorgis*, D. Gillies
PloS one, 2014
* denotes joint authorship.
@article{manifold2014,
  title = {{An algorithm for finding biologically significant features in microarray data based on a priori manifold learning}},
  author = {Hira, Zena M and Trigeorgis, George and Gillies, Duncan F},
  journal = {PloS one},
  volume = {9},
  number = {3},
  pages = {e90562},
  year = {2014},
  publisher = {Public Library of Science}
}

Conference Publications


Deep and Deformable: Convolutional Mixtures of Deformable Part-Based Models
K. Songsri-in, G. Trigeorgis, S. Zafeiriou
2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018), 2018
Best paper award
@inproceedings{songsri2018deep,
  title = {Deep and Deformable: Convolutional Mixtures of Deformable Part-Based Models},
  author = {Songsri-in, Kritaphat and Trigeorgis, George and Zafeiriou, Stefanos},
  booktitle = {2018 13th IEEE International Conference on Automatic Face \& Gesture Recognition (FG 2018)},
  pages = {218--225},
  year = {2018},
  organization = {IEEE}
}
Normal Estimation For "in-the-wild" Faces Using Fully Convolutional Networks
G. Trigeorgis, P. Snape, S. Zafeiriou, I. Kokkinos
Computer Vision and Pattern Recognition (CVPR), 2017
@inproceedings{trigeorgis2017normals,
  author = {Trigeorgis, George and Snape, Patrick and Zafeiriou, Stefanos and Kokkinos, Iasonas},
  booktitle = {{Computer Vision and Pattern Recognition (CVPR)}},
  title = {{Normal Estimation For "in-the-wild" Faces Using Fully Convolutional Networks}},
  year = {2017}
}
3D Face Morphable Models "In-the-Wild"
J. Booth, E. Antonakos, S. Ploumpis, G. Trigeorgis, Y. Panagakis, S. Zafeiriou
Computer Vision and Pattern Recognition (CVPR), 2017
Spotlight.
@inproceedings{booth2017itw3dmm,
  author = {Booth, J. and Antonakos, E. and Ploumpis, S. and Trigeorgis, G. and Panagakis, Y. and Zafeiriou, S.},
  booktitle = {{Computer Vision and Pattern Recognition (CVPR)}},
  month = jan,
  title = {3D Face Morphable Models "In-the-Wild"},
  url = {https://arxiv.org/abs/1701.05360},
  year = {2017},
  month_numeric = {1}
}
DenseReg: Fully Convolutional Dense Shape Regression In-the-Wild
R. Guler, G. Trigeorgis, E. Antonakos, P. Snape, S. Zafeiriou, I. Kokkinos
Computer Vision and Pattern Recognition (CVPR), 2017
@inproceedings{guler2017densereg,
  author = {Guler, R. and Trigeorgis, George and Antonakos, E. and Snape, P. and Zafeiriou, S. and Kokkinos, I.},
  booktitle = {{Computer Vision and Pattern Recognition (CVPR)}},
  title = {DenseReg: Fully Convolutional Dense Shape Regression In-the-Wild},
  url = {https://arxiv.org/pdf/1612.01202v1.pdf},
  year = {2017}
}
Domain Separation Networks
K. Bousmalis*, G. Trigeorgis*, N. Silberman, D. Krishnan, D. Erhan
Neural Information Processing Systems (NIPS), 2016
* denotes joint first-authorship.
@inproceedings{domain_separation_nets16,
  title = {{Domain Separation Networks}},
  author = {Bousmalis, Konstantinos and Trigeorgis, George and Silberman, Nathan and Krishnan, Dilip and Erhan, Dumitru},
  booktitle = {{Neural Information Processing Systems (NIPS)}},
  year = {2016}
}
Mnemonic Descent Method: A recurrent process applied for end-to-end face alignment
G. Trigeorgis, P. Snape, E. Antonakos, M. Nicolaou, S. Zafeiriou
Computer Vision and Pattern Recognition (CVPR), 2016
@inproceedings{trigeorgis_mdm16,
  title = {{Mnemonic Descent Method: A recurrent process applied for end-to-end face alignment}},
  author = {Trigeorgis, George and Snape, Patrick and Antonakos, Epameinondas and Nicolaou, Mihalis A. and Zafeiriou, Stefanos},
  booktitle = {{Computer Vision and Pattern Recognition (CVPR)}},
  year = {2016}
}
Deep Canonical Time Warping
G. Trigeorgis, M. Nicolaou, S. Zafeiriou, B. Schuller
Computer Vision and Pattern Recognition (CVPR), 2016
@inproceedings{trigeorgis_dctw16,
  title = {{Deep Canonical Time Warping}},
  author = {Trigeorgis, George and Nicolaou, Mihalis and Zafeiriou, Stefanos and Schuller, Bjoern W.},
  booktitle = {{Computer Vision and Pattern Recognition (CVPR)}},
  year = {2016}
}
Adieu Features? End-to- End Speech Emotion Recognition using a Deep Convolutional Recurrent Network
G. Trigeorgis, F. Ringeval, R. B., E. Marchi, M. Nicolaou, B. Schuller, S. Zafeiriou
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2016
Oral. Winner of the IEEE Spoken Language Processing Student Grant.
@inproceedings{trigeorgis_icassp16,
  author = {Trigeorgis, George and Ringeval, Fabien and B., Ray and Marchi, Erik and Nicolaou, Mihalis A. and Schuller, Bjoern and Zafeiriou, Stefanos},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  title = {Adieu Features? End-to- End Speech Emotion Recognition using a Deep Convolutional Recurrent Network},
  year = {2016}
}
Towards Deep Multimodal Alignment
G. Trigeorgis, M. Nicolaou, S. Zafeiriou, B. Schuller
Neural Information Processing Systems (NIPS) Multimodal Machine Learning Workshop, 2015
Spotlight.
@inproceedings{trigeorgis_dctw15,
  title = {{Towards Deep Multimodal Alignment}},
  author = {Trigeorgis, George and Nicolaou, Mihalis and Zafeiriou, Stefanos and Schuller, Bjoern W.},
  booktitle = {{Neural Information Processing Systems (NIPS) Multimodal Machine Learning Workshop}},
  year = {2015}
}
A Deep Semi-NMF Model for Learning Hidden Representations
G. Trigeorgis, K. Bousmalis, S. Zafeiriou, B. Schuller
International Conference on Machine Learning (ICML), 2014
@inproceedings{dsnmf2014,
  title = {{A Deep Semi-NMF Model for Learning Hidden Representations}},
  author = {Trigeorgis, George and Bousmalis, Konstantinos and Zafeiriou, Stefanos and Schuller, Bjoern W.},
  booktitle = {{International Conference on Machine Learning (ICML)}},
  year = {2014}
}