In this research, we analyze a Convolutional Long Short-Term Memory Recurrent Neural Network (CNNLSTM) in the context of gesture recognition. CNNLSTMs are able to successfully learn gestures of varying duration and complexity. For this reason, we analyze the architecture by presenting a qualitative evaluation of the model, based on the visualization of the internal representations of the convolutional layers and on the examination of the temporal classification outputs at a frame level, in order to check if they match the cognitive perception of a gesture. We show that CNNLSTM learns the temporal evolution of the gestures classifying correctly their meaningful part, known as Kendons stroke phase. With the visualization, for which we use the deconvolution process that maps specific feature map activations to original image pixels, we show that the network learns to detect the most intense body motion. Finally, we show that CNNLSTM outperforms both plain CNN and LSTM in gesture recognition.

A new architecture based on the Multi-channel Convolutional Neural Network (MCCNN) is proposed for recognizing facial expressions. Two hard-coded feature extractors are replaced by a single channel which is partially trained in an unsupervised fashion as a Convolutional Autoencoder (CAE). One additional channel that contains a standard CNN is left unchanged. Information from both channels converges in a fully connected layer and is then used for classification. We perform two distinct experiments on the JAFFE dataset (leave-one-out and ten-fold cross validation) to evaluate our architecture. Our comparison with the previous model that uses hard-coded Sobel features shows that an additional channel of information with unsupervised learning can significantly boost accuracy and reduce the overall training time. Furthermore, experimental results are compared with benchmarks from the literature showing that our method provides state-of-the-art recognition rates for facial expressions. Our method outperforms previously published methods that used hand-crafted features by a large margin.

This paper is the basis paper for the accepted IJCNN challenge One-Minute Gradual-Emotion Recognition (OMG-Emotion) ¹ by which we hope to foster long-emotion classification using neural models for the benefit of the IJCNN community. The proposed corpus has as novelty the data collection and annotation strategy based on emotion expressions which evolve over time into a specific context. Different from other corpora, we propose a novel multimodal corpus for emotion expression recognition, which uses gradual annotations with a focus on contextual emotion expressions. Our dataset was collected from Youtube videos using a specific search strategy based on restricted keywords and filtering which guaranteed that the data follow a gradual emotion expression transition, i.e. emotion expressions evolve over time in a natural and continuous fashion. We also provide an experimental protocol and a series of unimodal baseline experiments which can be used to evaluate deep and recurrent neural models in a fair and standard manner.

Emotional state recognition has become an important topic for human-robot interaction in the past years. By determining emotion expressions, robots can identify important variables of human behavior and use these to communicate in a more human-like fashion and thereby extend the interaction possibilities. Human emotions are multimodal and spontaneous, which makes them hard to be recognized by robots. Each modality has its own restrictions and constraints which, together with the non-structured behavior of spontaneous expressions, create several difficulties for the approaches present in the literature, which are based on several explicit feature extraction techniques and manual modality fusion. Our model uses a hierarchical feature representation to deal with spontaneous emotions, and learns how to integrate multiple modalities for non-verbal emotion recognition, making it suitable to be used in an HRI scenario. Our experiments show that a significant improvement of recognition accuracy is achieved when we use hierarchical features and multimodal information, and our model improves the accuracy of state-of-the-art approaches from 82.5% reported in the literature to 91.3% for a benchmark dataset on spontaneous emotion expressions.

A robot capable of understanding emotion expressions can increase its own capability of solving problems by using emotion expressions as part of its own decision-making, in a similar way to humans. Evidence shows that the perception of human interaction starts with an innate perception mechanism, where the interaction between different entities is perceived and categorized into two very clear directions: positive or negative. While the person is developing during childhood, the perception evolves and is shaped based on the observation of human interaction, creating the capability to learn different categories of expressions. In the context of human–robot interaction, we propose a model that simulates the innate perception of audio–visual emotion expressions with deep neural networks, that learns new expressions by categorizing them into emotional clusters with a self-organizing layer. The proposed model is evaluated with three different corpora: The Surrey Audio–Visual Expressed Emotion (SAVEE) database, the visual Bi-modal Face and Body benchmark (FABO) database, and the multimodal corpus of the Emotion Recognition in the Wild (EmotiW) challenge. We use these corpora to evaluate the performance of the model to recognize emotional expressions, and compare it to state-of-the-art research.

Spatial attention in humans and animals involves the visual pathway and the superior colliculus, which integrate multimodal information. Recent research has shown that affective stimuli play an important role in attentional mechanisms, and behavioral studies show that the focus of attention in a given region of the visual field is increased when affective stimuli are present. This work proposes a neurocomputational model that learns to attend to emotional expressions and to modulate emotion recognition. Our model consists of a deep architecture which implements convolutional neural networks to learn the location of emotional expressions in a cluttered scene. We performed a number of experiments for detecting regions of interest, based on emotion stimuli, and show that the attention model improves emotion expression recognition when used as emotional attention modulator. Finally, we analyze the internal representations of the learned neural filters and discuss their role in the performance of our model.