Faces convey rich information including identity, gender and expression. Current neural models of face processing suggest a dissociation between the processing of invariant facial aspects such as identity and gender, that engage the fusiform face are...
In this paper, we propose a novel deep learning framework, called spatial-temporal recurrent neural network (STRNN), to integrate the feature learning from both spatial and temporal information of signal sources into a unified spatial-temporal depend...
IEEE transactions on pattern analysis and machine intelligence
Jan 10, 2018
In this paper, we propose a deep learning based approach for facial action unit (AU) detection by enhancing and cropping regions of interest of face images. The approach is implemented by adding two novel nets (a.k.a. layers): the enhancing layers an...
Neural networks : the official journal of the International Neural Network Society
Dec 7, 2017
Affect presentation is periodic and multi-modal, such as through facial movements, body gestures, and so on. Studies have shown that temporal selection and multi-modal combinations may benefit affect recognition. In this article, we therefore propose...
It is quite difficult for android robots to replicate the numerous and various types of human facial expressions owing to limitations in terms of space, mechanisms, and materials. This situation could be improved with greater knowledge regarding thes...
Computational intelligence and neuroscience
Sep 19, 2017
This paper proposes two multimodal fusion methods between brain and peripheral signals for emotion recognition. The input signals are electroencephalogram and facial expression. The stimuli are based on a subset of movie clips that correspond to four...
IEEE transactions on pattern analysis and machine intelligence
Aug 22, 2017
We address the problem of video classification for facial analysis and human action recognition. We propose a novel weakly supervised learning method that models the video as a sequence of automatically mined, discriminative sub-events (e.g., onset a...
IEEE transactions on pattern analysis and machine intelligence
Aug 14, 2017
We propose a general approach to the gaze redirection problem in images that utilizes machine learning. The idea is to learn to re-synthesize images by training on pairs of images with known disparities between gaze directions. We show that such lear...
IEEE transactions on pattern analysis and machine intelligence
Aug 10, 2017
Face attribute estimation has many potential applications in video surveillance, face retrieval, and social media. While a number of methods have been proposed for face attribute estimation, most of them did not explicitly consider the attribute corr...
IEEE transactions on pattern analysis and machine intelligence
Aug 1, 2017
In this paper, we propose a two-stream transformer networks (TSTN) approach for video-based face alignment. Unlike conventional image-based face alignment approaches which cannot explicitly model the temporal dependency in videos and motivated by the...