Search

Emotion recognition is challenging due to the emotional gap between emotions and audio–visual features. Motivated by the powerful feature learning ability of deep neural networks, this paper proposes to bridge the emotional gap by using a hybrid deep model, which first produces audio–visual segment features with Convolutional Neural Networks (CNNs) and 3D-CNN, then fuses audio–visual segment features in a Deep Belief Networks (DBNs). The proposed method is trained in two stages. First, CNN and 3D-CNN models pre-trained on corresponding large-scale image and video classification tasks are fine-tuned on emotion recognition tasks to learn audio and visual segment features, respectively. Second, the outputs of CNN and 3D-CNN models are combined into a fusion network built with a DBN model. The fusion network is trained to jointly learn a discriminative audio–visual segment feature representation. After average-pooling segment features learned by DBN to form a fixed-length global video feature, a linear Support Vector Machine is used for video emotion classification. Experimental results on three public audio–visual emotional databases, including the acted RML database, the acted eNTERFACE05 database, and the spontaneous BAUM-1s database, demonstrate the promising performance of the proposed method. To the best of our knowledge, this is an early work fusing audio and visual cues with CNN, 3D-CNN, and DBN for audio–visual emotion recognition. [ABSTRACT FROM AUTHOR]

This letter describes a high-performance face recognition system by combining two recently proposed neural network models, namely Gabor wavelet network (GWN) and kernel associative memory (KAM), into a unified structure called Gabor wavelet associative memory (GWAM). GWAM has superior representation capability inherited from GWN and consequently demonstrates a much better recognition performance than KAM. Extensive experiments have been conducted to evaluate a GWAM-based recognition scheme using three popular face databases. i.e., FERET database, Olivetti-Oracle Research Lab (ORL) database and AR face database. The experimental results consistently show our scheme's superiority and demonstrate its very high-performance comparing favorably to some recent face recognition methods, achieving 99.3% and 100% accuracy, respectively, on the former two databases, exhibiting very robust performance on the last database against varying ilium i nation conditions. [ABSTRACT FROM AUTHOR]

A vocabulary hierarchy optimization and transfer framework uses density-based metric learning to correct quantization biases, without supervision. [ABSTRACT FROM PUBLISHER]

The size of databases is the key to success to face recognition systems. However, building such a database is both time-consuming and labor intensive. In this paper, we address the problem by proposing a database generation framework based on text–video correlation. Specifically, visual content of a video can be presented as a character sequence by face detection, tracking and recognition, while text information extracted from subtitles and scripts provides complementary identity sequence. By correlating these two sequences, faces recognized can be refined without manual intervention. Experiments demonstrate that 90% of the human effort in face database construction can be reduced. [ABSTRACT FROM AUTHOR]