Home Δημοσιεύσεις

On Line Emotion Detection Using Retrainable Deep Neural Networks

Ερευνητική Περιοχή: Τεχνητά Νευρωνικά Δίκτυα Έτος: 2016
Είδος Δημοσίευσης: Σε Συνεδρίο Λέξεις Κλειδιά: on line facial expression analysis, deep neural networks, transfer learning, retraining, drift detection, emotion recognition
Τίτλος Βιβλίου: 2016 IEEE Symposium Series on Computational Intelligence (SSCI)
Σελίδες: 1-8
Μήνας: Dec.
ISBN: 9781509042401
This paper presents a new methodology for detecting deterioration in performance of deep neural networks when applied to on line visual analysis problems and enabling fine-tuning, or retraining, of the network to the current data characteristics. Pre-trained deep neural networks which have a satisfactory performance on the problem under tudy constitute the basis of the approach, with efficient transfer learning being performed whenever drift is detected in network operation. The method is applied and validated on the problem of emotion detection using line facial expression analysis based on a dimensional emotion representation.

Powered by Joomla!. Valid XHTML and CSS.