Nikolaos Sarafianos
Nikolaos Sarafianos
Research Scientist at Facebook Reality Labs
Bestätigte E-Mail-Adresse bei oculus.com - Startseite
TitelZitiert vonJahr
3d human pose estimation: A review of the literature and analysis of covariates
N Sarafianos, B Boteanu, B Ionescu, IA Kakadiaris
Computer Vision and Image Understanding 152, 1-20, 2016
882016
Deep Imbalanced Attribute Classification using Visual Attention Aggregation
N Sarafianos, X Xu, IA Kakadiaris
European Conference on Computer Vision, Munich, Germany, Sept. 8 - 14, 2018, 2018
282018
Show me your body: Gender classification from still images
IA Kakadiaris, N Sarafianos, C Nikou
International Conference on Image Processing (ICIP), 3156-3160, 2016
152016
Curriculum learning of visual attribute clusters for multi-task classification
N Sarafianos, T Giannakopoulos, C Nikou, IA Kakadiaris
Pattern Recognition 80, 94-108, 2018
112018
Curriculum Learning for Multi-Task Classification of Visual Attributes
N Sarafianos, T Giannakopoulos, C Nikou, IA Kakadiaris
arXiv preprint arXiv:1708.08728, 2017
112017
Audio-visual speaker diarization using fisher linear semi-discriminant analysis
N Sarafianos, T Giannakopoulos, S Petridis
Multimedia Tools and Applications 75 (1), 115-130, 2016
112016
Adaptive svm+: Learning with privileged information for domain adaptation
N Sarafianos, M Vrigkas, IA Kakadiaris
Proceedings of the IEEE International Conference on Computer Vision, 2637-2644, 2017
92017
Predicting Privileged Information For Height Estimation
N Sarafianos, C Nikou, IA Kakadiaris
International Conference on Pattern Recognition (ICPR), 3115--3120, 2016
72016
Fusing active orientation models and mid-term audio features for automatic depression estimation
C Smailis, N Sarafianos, T Giannakopoulos, S Perantonis
Proceedings of the 9th ACM International Conference on PErvasive …, 2016
22016
Adversarial Representation Learning for Text-to-Image Matching
N Sarafianos, X Xu, IA Kakadiaris
arXiv preprint arXiv:1908.10534, 2019
2019
Das System kann den Vorgang jetzt nicht ausführen. Versuchen Sie es später erneut.
Artikel 1–10