Translator Disclaimer
19 February 2018 Adaptive metric learning with deep neural networks for video-based facial expression recognition
Author Affiliations +
Video-based facial expression recognition has become increasingly important for plenty of applications in the real world. Despite that numerous efforts have been made for the single sequence, how to balance the complex distribution of intra- and interclass variations well between sequences has remained a great difficulty in this area. We propose the adaptive ( N+M)-tuplet clusters loss function and optimize it with the softmax loss simultaneously in the training phrase. The variations introduced by personal attributes are alleviated using the similarity measurements of multiple samples in the feature space with many fewer comparison times as conventional deep metric learning approaches, which enables the metric calculations for large data applications (e.g., videos). Both the spatial and temporal relations are well explored by a unified framework that consists of an Inception-ResNet network with long short term memory and the two fully connected layer branches structure. Our proposed method has been evaluated with three well-known databases, and the experimental results show that our method outperforms many state-of-the-art approaches.
© 2018 SPIE and IS&T 1017-9909/2018/$25.00 © 2018 SPIE and IS&T
Xiaofeng Liu, Yubin Ge, Chao Yang, and Ping Jia "Adaptive metric learning with deep neural networks for video-based facial expression recognition," Journal of Electronic Imaging 27(1), 013022 (19 February 2018).
Received: 8 August 2017; Accepted: 23 January 2018; Published: 19 February 2018

Back to Top