Continuous Affect Recognition Research Articles

Video-based continuous affect recognition of children with Autism Spectrum Disorder using deep learning

Affect recognition is currently an active research area for machine learning researchers. Researchers are paying more and more attention to the assessment and the classification of emotions in people with mental disorders in order to propose monitoring healthcare systems and then to better assist patients. In this paper, a supervised learning method to classify Autism Spectrum Disorder (ASD) and to evaluate affect levels among autistic children is proposed. The use of methodologies for clinical patient monitoring and management is the focus of our research. YouTube video frames acquired in unconstrained environments and conditions of autistic children demonstrating typical autistic behaviors, as well as images of neurotypical people are used to evaluate the performance of the proposed approach. This paper also proposes an extended version of a dataset, including the additional affect labels corresponding to the affect levels of autistic children. Finally, experiments using different models were conducted to determine which architecture performed best. These experiments have shown very promising results for continuous affect recognition of children with ASD. Results show also that using a model that has only been trained on neurotypical subjects does not perform as great when the subjects are ASD children.

An ensemble learning-enhanced multitask learning method for continuous affect recognition from facial images

Continuous affect recognition from facial images aims to estimate the values of multiple affective dimensions from a facial image sequence. To leverage relevant information between multiple affective dimensions, multitask learning has been used in the estimation of continuous affective states. Most of the existing multitask continuous affect recognition methods focus on designing elaborate multitask networks. Meanwhile, a few research works consider using multitask training strategies for continuous affect recognition. In general, existing multitask continuous affect recognition methods face the problem of unstable training effects. In this work, to improve the stability of multitask learning, we propose an ensemble learning-enhanced multitask network architecture for continuous affect recognition. In addition, we introduce a novel adaptive weighted loss-based multitask learning strategy to effectively train the proposed multitask continuous affect recognition model. Experimental results, on the RECOLA, SEMAINE and AFEW-VA datasets for continuous affect recognition, demonstrate the potential of the proposed method compared to state-of-the-art methods.

Does Visual Self-Supervision Improve Learning of Speech Representations for Emotion Recognition?

Self-supervised learning has attracted plenty of recent research interest. However, most works for self-supervision in speech are typically unimodal and there has been limited work that studies the interaction between audio and visual modalities for cross-modal self-supervision. This work (1) investigates visual self-supervision via face reconstruction to guide the learning of audio representations; (2) proposes an audio-only self-supervision approach for speech representation learning; (3) shows that a multi-task combination of the proposed visual and audio self-supervision is beneficial for learning richer features that are more robust in noisy conditions; (4) shows that self-supervised pretraining can outperform fully supervised training and is especially useful to prevent overfitting on smaller sized datasets. We evaluate our learned audio representations for discrete emotion recognition, continuous affect recognition and automatic speech recognition. We outperform existing self-supervised methods for all tested downstream tasks. Our results demonstrate the potential of visual self-supervision for audio feature learning and suggest that joint visual and audio self-supervision leads to more informative audio representations for speech and emotion recognition.

Deep Learning-Based Approach for Continuous Affect Prediction From Facial Expression Images in Valence-Arousal Space

Facial emotion recognition has attracted extensive attention from the affective computing community and several approaches have been proposed, mainly providing classification of facial expressions images using a set of discrete emotional labels. The quantification of human emotions from faces has been studied in a continuous 2D emotional space of valence and arousal, that describes the level of pleasantness and the intensity of excitement, respectively. Emotion assessment using valence-arousal computation is a challenging topic with several possible applications in health monitoring, e-learning, mental health diagnosis and monitoring of customer interest. Supervised learning of emotional valence-arousal for continuous affect prediction requires labeled data. However, annotation of facial images with the values for valence and arousal requires training human experts. In this paper, we propose a new and robust approach based on deep learning for continuous affect recognition and prediction. The novelty of our approach is that it maps the discrete labels and a learned facial expression representation to the continuous valence-arousal dimensional space. Given a discrete class of emotion and a facial image, our deep learning-based approach can predict the valence and arousal values accurately. Our proposed approach outperforms existing approaches for arousal and valence prediction on AffectNet dataset and it shows an impressive generalization ability on an unseen dataset for valence prediction.

Transformer Encoder With Multi-Modal Multi-Head Attention for Continuous Affect Recognition

Continuous affect recognition is becoming an increasingly attractive research topic in affective computing. Previous works mainly focused on modelling the temporal dependency within a sensor modality, or adopting early or late fusion for multi-modal affective state recognition. However, early fusion suffers from the curse of dimensionality, and late fusion ignores the complementarity and redundancy between multiple modal streams. In this paper, we first introduce the transformer-encoder with a self-attention mechanism and propose a Convolutional Neural Network-Transformer Encoder (CNN-TE) framework to model the temporal dependency for single modal affect recognition. Further, to effectively consider the complementarity and redundancy between multiple streams we propose a Transformer Encoder with Multi-modal Multi-head Attention (TEMMA) for multi-modal affect recognition. TEMMA allows to progressively and simultaneously refine the inter-modality interactions and intra-modality temporal dependency. The learned multi-modal representations are fed to an Inference Sub-network with fully connected layers to estimate the affective state. The proposed framework is trained in a nutshell and demonstrates its effectiveness on the AVEC2016 and AVEC2019 datasets. Compared to state-of-the-art models, our approach obtains remarkable improvements on both arousal and valence in terms of concordance correlation coefficient (CCC) reaching 0.583 for arousal and 0.564 for valence on the AVEC2019 test set.

Monocular 3D Facial Expression Features for Continuous Affect Recognition

Automated facial expression analysis from image sequences for continuous emotion recognition is a very challenging task due to the loss of the three-dimensional information during the image formation process. State-of-the-art relied on estimating dynamic textures features and convolutional neural network features to derive spatio-temporal features. Despite their great success, such features are insensitive to micro facial muscle deformations and are affected by identity, face pose, illumination variation, and self-occlusion. In this work, we argue that retrieving, from image sequences, 3D facial spatio-temporal information, which describes the natural facial muscle deformation, provides a semantical and efficient way of representation and is useful for emotion recognition. In this paper, we propose a framework for extracting three-dimensional facial spatio-temporal features from monocular image sequences using an extended 3D Morphable Model (3DMM) which disentangles the identity factor from the facial expressions of a specific person. An LSTM model is used to evaluate the effectiveness of the proposed spatio-temporal features on video-based facial expression recognition task and continuous affect recognition task. Experimental results, on the AFEW6.0 datasets for facial expression recognition, and the RECOLA and SEMAINE datasets for continuous emotion prediction, illustrate the potential of the proposed 3D spatio-temporal features for facial expressions analysis and continuous affect recognition, as well as their efficiency compared to recent state-of-the-art features.

An efficient model-level fusion approach for continuous affect recognition from audiovisual signals

Continuous affect recognition has a huge potential in human computer interaction applications. How to efficiently fuse speech and facial information for inferring the affective state of a person from data captured in real-world conditions is a very important issue for continuous affect recognition. Currently, late fusion is usually used in multi-modal continuous affect recognition to improve system performance. However, late fusion ignores the complementarity and redundancy between multiple streams from the different modalities. In this work, we propose an efficient model-level fusion approach for audiovisual continuous affect recognition.First, we propose a LSTM based model-level fusion approach for audiovisual continuous affect recognition. Our approach considers the complementarity and redundancy between multiple streams from different modalities. In addition, our model can efficiently incorporate side information such as gender using adaptive weight network. At last, we design a deep supervision based effective optimization strategy for training the proposed audiovisual continuous affect recognition model.We demonstrate the effectiveness of our approach on the RECOLA dataset. Our experimental results show that the proposed adaptive weight network improves the performance compared to a plain neural network without adaptive weights. Our approach obtains remarkable improvements on both arousal and valence in terms of concordance correlation coefficient (CCC) compared to state-of-the-art early fusion and model-level fusion approaches. Therefore, we believe that our proposed approach gives a promising direction for further improving the performance of audiovisual continuous affect recognition.

Continuous affect recognition with weakly supervised learning

Recognizing a person’s affective state from audio-visual signals is an essential capability for intelligent interaction. Insufficient training data and the unreliable labels of affective dimensions (e.g., valence and arousal) are two major challenges in continuous affect recognition. In this paper, we propose a weakly supervised learning approach based on hybrid deep neural network and bidirectional long short-term memory recurrent neural network (DNN-BLSTM). It firstly maps the audio/visual features into a more discriminative space via the powerful modelling capacities of DNN, then models the temporal dynamics of affect via BLSTM. To reduce the negative impact of the unreliable labels, we utilize a temporal label (TL) along with a robust loss function (RL) for incorporating weak supervision into the learning process of the DNN-BLSTM model. Therefore, the proposed method not only has a simpler structure than the deep BLSTM model in He et al. (24) which requires more training data, but also is robust to noisy and unreliable labels. Single modal and multimodal affect recognition experiments have been carried out on the RECOLA dataset. Single modal recognition results show that the proposed method with TL and RL obtains remarkable improvements on both arousal and valence in terms of concordance correlation coefficient (CCC), while multimodal recognition results show that with less feature streams, our proposed approach obtains better or comparable results with the state-of-the-art methods.

Strength modelling for real-worldautomatic continuous affect recognition from audiovisual signals

Automatic continuous affect recognition from audiovisual cues is arguably one of the most active research areas in machine learning. In addressing this regression problem, the advantages of the mod...

Strength modelling for real-worldautomatic continuous affect recognition from audiovisual signals

Automatic continuous affect recognition from audiovisual cues is arguably one of the most active research areas in machine learning. In addressing this regression problem, the advantages of the models, such as the global-optimisation capability of Support Vector Machine for Regression and the context-sensitive capability of memory-enhanced neural networks, have been frequently explored, but in an isolated way. Motivated to leverage the individual advantages of these techniques, this paper proposes and explores a novel framework, Strength Modelling, where two models are concatenated in a hierarchical framework. In doing this, the strength information of the first model, as represented by its predictions, is joined with the original features, and this expanded feature space is then utilised as the input by the successive model. A major advantage of Strength Modelling, besides its ability to hierarchically explore the strength of different machine learning algorithms, is that it can work together with the conventional feature- and decision-level fusion strategies for multimodal affect recognition. To highlight the effectiveness and robustness of the proposed approach, extensive experiments have been carried out on two time- and value-continuous spontaneous emotion databases (RECOLA and SEMAINE) using audio and video signals. The experimental results indicate that employing Strength Modelling can deliver a significant performance improvement for both arousal and valence in the unimodal and bimodal settings. The results further show that the proposed systems is competitive or outperform the other state-of-the-art approaches, but being with a simple implementation.