In this paper, we introduce a framework for classifying images according to high-level sentiment. We subdivide the task into three primary problems: emotion classification on faces, human pose estimation, and 3D estimation and clustering of groups of people. We introduce novel algorithms for matching body parts to a common individual and clustering people in images based on physical location and orientation. Our results outperform several baseline approaches.
Music emotion recognition (MER) is usually regarded as a multi-label tagging task, and each segment of music can inspire specific emotion tags. Most researchers extract acoustic features from music and explore the relations between these features and their corresponding emotion tags. Considering the inconsistency of emotions inspired by the same music segment for human beings, seeking for the key acoustic features that really affect on emotions is really a challenging task. In this paper, we propose a novel MER method by using deep convolutional neural network (CNN) on the music spectrograms that contains both the original time and frequency domain information. By the proposed method, no additional effort on extracting specific features required, which is left to the training procedure of the CNN model. Experiments are conducted on the standard CAL500 and CAL500exp dataset. Results show that, for both datasets, the proposed method outperforms state-of-the-art methods.
We present MoodSwipe, a soft keyboard that suggests text messages given the user-specified emotions utilizing the real dialog data. The aim of MoodSwipe is to create a convenient user interface to enjoy the technology of emotion classification and text suggestion, and at the same time to collect labeled data automatically for developing more advanced technologies. While users select the MoodSwipe keyboard, they can type as usual but sense the emotion conveyed by their text and receive suggestions for their message as a benefit. In MoodSwipe, the detected emotions serve as the medium for suggested texts, where viewing the latter is the incentive to correcting the former. We conduct several experiments to show the superiority of the emotion classification models trained on the dialog data, and further to verify good emotion cues are important context for text suggestion.
Emotion recognition is attracting great interest for its potential application in a multitude of real-life situations. Much of the Computer Vision research in this field has focused on relating emotions to facial expressions, with investigations rarely including more than upper body. In this work, we propose a new scenario, for which emotional states are related to 3D dynamics of the whole body motion. To address the complexity of human body movement, we used covariance descriptors of the sequence of the 3D skeleton joints, and represented them in the non-linear Riemannian manifold of Symmetric Positive Definite matrices. In doing so, we exploited geodesic distances and geometric means on the manifold to perform emotion classification. Using sequences of spontaneous walking under the five primary emotional states, we report a method that succeeded in classifying the different emotions, with comparable performance to those observed in a human-based force-choice classification task.
Classification of social media data is an important approach in understanding user behavior on the Web. Although information on social media can be of different modalities such as texts, images, audio or videos, traditional approaches in classification usually leverage only one prominent modality. Techniques that are able to leverage multiple modalities are often complex and susceptible to the absence of some modalities. In this paper, we present simple models that combine information from different modalities to classify social media content and are able to handle the above problems with existing techniques. Our models combine information from different modalities using a pooling layer and an auxiliary learning task is used to learn a common feature space. We demonstrate the performance of our models and their robustness to the missing of some modalities in the emotion classification domain. Our approaches, although being simple, can not only achieve significantly higher accuracies than traditional fusion approaches but also have comparable results when only one modality is available.
This paper addresses the question of emotion classification. The task consists in predicting emotion labels (taken among a set of possible labels) best describing the emotions contained in short video clips. Building on a standard framework -- lying in describing videos by audio and visual features used by a supervised classifier to infer the labels -- this paper investigates several novel directions. First of all, improved face descriptors based on 2D and 3D Convo-lutional Neural Networks are proposed. Second, the paper explores several fusion methods, temporal and multimodal, including a novel hierarchical method combining features and scores. In addition, we carefully reviewed the different stages of the pipeline and designed a CNN architecture adapted to the task; this is important as the size of the training set is small compared to the difficulty of the problem, making generalization difficult. The so-obtained model ranked 4th at the 2017 Emotion in the Wild challenge with the accuracy of 58.8 %.
Emotion cause extraction aims to identify the reasons behind a certain emotion expressed in text. It is a much more difficult task compared to emotion classification. Inspired by recent advances in using deep memory networks for question answering (QA), we propose a new approach which considers emotion cause identification as a reading comprehension task in QA. Inspired by convolutional neural networks, we propose a new mechanism to store relevant context in different memory slots to model context information. Our proposed approach can extract both word level sequence features and lexical features. Performance evaluation shows that our method achieves the state-of-the-art performance on a recently released emotion cause dataset, outperforming a number of competitive baselines by at least 3.01% in F-measure.
In this paper we propose an implement a general convolutional neural network (CNN) building framework for designing real-time CNNs. We validate our models by creating a real-time vision system which accomplishes the tasks of face detection, gender classification and emotion classification simultaneously in one blended step using our proposed CNN architecture. After presenting the details of the training procedure setup we proceed to evaluate on standard benchmark sets. We report accuracies of 96% in the IMDB gender dataset and 66% in the FER-2013 emotion dataset. Along with this we also introduced the very recent real-time enabled guided back-propagation visualization technique. Guided back-propagation uncovers the dynamics of the weight changes and evaluates the learned features. We argue that the careful implementation of modern CNN architectures, the use of the current regularization methods and the visualization of previously hidden features are necessary in order to reduce the gap between slow performances and real-time architectures. Our system has been validated by its deployment on a Care-O-bot 3 robot used during RoboCup@Home competitions. All our code, demos and pre-trained architectures have been released under an open-source license in our public repository.
Long short-term memory (LSTM) is normally used in recurrent neural network (RNN) as basic recurrent unit. However,conventional LSTM assumes that the state at current time step depends on previous time step. This assumption constraints the time dependency modeling capability. In this study, we propose a new variation of LSTM, advanced LSTM (A-LSTM), for better temporal context modeling. We employ A-LSTM in weighted pooling RNN for emotion recognition. The A-LSTM outperforms the conventional LSTM by 5.5% relatively. The A-LSTM based weighted pooling RNN can also complement the state-of-the-art emotion classification framework. This shows the advantage of A-LSTM.
In this paper we describe a solution to our entry for the emotion recognition challenge EmotiW 2017. We propose an ensemble of several models, which capture spatial and audio features from videos. Spatial features are captured by convolutional neural networks, pretrained on large face recognition datasets. We show that usage of strong industry-level face recognition networks increases the accuracy of emotion recognition. Using our ensemble we improve on the previous best result on the test set by about 1 %, achieving a 60.03 % classification accuracy without any use of visual temporal information.
Preserving privacy of continuous and/or high-dimensional data such as images, videos and audios, can be challenging with syntactic anonymization methods which are designed for discrete attributes. Differential privacy, which provides a more formal definition of privacy, has shown more success in sanitizing continuous data. However, both syntactic and differential privacy are susceptible to inference attacks, i.e., an adversary can accurately infer sensitive attributes from sanitized data. The paper proposes a novel filter-based mechanism which preserves privacy of continuous and high-dimensional attributes against inference attacks. Finding the optimal utility-privacy tradeoff is formulated as a min-diff-max optimization problem. The paper provides an ERM-like analysis of the generalization error and also a practical algorithm to perform the optimization. In addition, the paper proposes an extension that combines minimax filter and differentially-private noisy mechanism. Advantages of the method over purely noisy mechanisms is explained and demonstrated with examples. Experiments with several real-world tasks including facial expression classification, speech emotion classification, and activity classification from motion, show that the minimax filter can simultaneously achieve similar or better target task accuracy and lower inference accuracy, often significantly lower than previous methods.
It is a difficult task to classify images with multiple class labels using only a small number of labeled examples, especially when the label (class) distribution is imbalanced. Emotion classification is such an example of imbalanced label distribution, because some classes of emotions like \emph{disgusted} are relatively rare comparing to other labels like {\it happy or sad}. In this paper, we propose a data augmentation method using generative adversarial networks (GAN). It can complement and complete the data manifold and find better margins between neighboring classes. Specifically, we design a framework with a CNN model as the classifier and a cycle-consistent adversarial networks (CycleGAN) as the generator. In order to avoid gradient vanishing problem, we employ the least-squared loss as adversarial loss. We also propose several evaluation methods on three benchmark datasets to validate GAN's performance. Empirical results show that we can obtain 5%~10% increase in the classification accuracy after employing the GAN-based data augmentation techniques.
Deep learning based discriminative methods, being the state-of-the-art machine learning techniques, are ill-suited for learning from lower amounts of data. In this paper, we propose a novel framework, called simultaneous two sample learning (s2sL), to effectively learn the class discriminative characteristics, even from very low amount of data. In s2sL, more than one sample (here, two samples) are simultaneously considered to both, train and test the classifier. We demonstrate our approach for speech/music discrimination and emotion classification through experiments. Further, we also show the effectiveness of s2sL approach for classification in low-resource scenario, and for imbalanced data.
We present EmoTxt, a toolkit for emotion recognition from text, trained and tested on a gold standard of about 9K question, answers, and comments from online interactions. We provide empirical evidence of the performance of EmoTxt. To the best of our knowledge, EmoTxt is the first open-source toolkit supporting both emotion recognition from text and training of custom emotion classification models.
Recently the deep learning techniques have achieved success in multi-label classification due to its automatic representation learning ability and the end-to-end learning framework. Existing deep neural networks in multi-label classification can be divided into two kinds: binary relevance neural network (BRNN) and threshold dependent neural network (TDNN). However, the former needs to train a set of isolate binary networks which ignore dependencies between labels and have heavy computational load, while the latter needs an additional threshold function mechanism to transform the multi-class probabilities to multi-label outputs. In this paper, we propose a joint binary neural network (JBNN), to address these shortcomings. In JBNN, the representation of the text is fed to a set of logistic functions instead of a softmax function, and the multiple binary classifications are carried out synchronously in one neural network framework. Moreover, the relations between labels are captured via training on a joint binary cross entropy (JBCE) loss. To better meet multi-label emotion classification, we further proposed to incorporate the prior label relations into the JBCE loss. The experimental results on the benchmark dataset show that our model performs significantly better than the state-of-the-art multi-label emotion classification methods, in both classification performance and computational efficiency.
The goal of music highlight extraction is to get a short consecutive segment of a piece of music that provides an effective representation of the whole piece. In a previous work, we introduced an attention-based convolutional recurrent neural network that uses music emotion classification as a surrogate task for music highlight extraction, for Pop songs. The rationale behind that approach is that the highlight of a song is usually the most emotional part. This paper extends our previous work in the following two aspects. First, methodology-wise we experiment with a new architecture that does not need any recurrent layers, making the training process faster. Moreover, we compare a late-fusion variant and an early-fusion variant to study which one better exploits the attention mechanism. Second, we conduct and report an extensive set of experiments comparing the proposed attention-based methods against a heuristic energy-based method, a structural repetition-based method, and a few other simple feature-based methods for this task. Due to the lack of public-domain labeled data for highlight extraction, following our previous work we use the RWC POP 100-song data set to evaluate how the detected highlights overlap with any chorus sections of the songs. The experiments demonstrate the effectiveness of our methods over competing methods. For reproducibility, we open source the code and pre-trained model at https://github.com/remyhuang/pop-music-highlighter/.
The majority of existing speech emotion recognition research focuses on automatic emotion detection using training and testing data from same corpus collected under the same conditions. The performance of such systems has been shown to drop significantly in cross-corpus and cross-language scenarios. To address the problem, this paper exploits a transfer learning technique to improve the performance of speech emotion recognition systems that is novel in cross-language and cross-corpus scenarios. Evaluations on five different corpora in three different languages show that Deep Belief Networks (DBNs) offer better accuracy than previous approaches on cross-corpus emotion recognition, relative to a Sparse Autoencoder and SVM baseline system. Results also suggest that using a large number of languages for training and using a small fraction of the target data in training can significantly boost accuracy compared with baseline also for the corpus with limited training examples.
Learning the latent representation of data in unsupervised fashion is a very interesting process that provides relevant features for enhancing the performance of a classifier. For speech emotion recognition tasks, generating effective features is crucial. Currently, handcrafted features are mostly used for speech emotion recognition, however, features learned automatically using deep learning have shown strong success in many problems, especially in image processing. In particular, deep generative models such as Variational Autoencoders (VAEs) have gained enormous success for generating features for natural images. Inspired by this, we propose VAEs for deriving the latent representation of speech signals and use this representation to classify emotions. To the best of our knowledge, we are the first to propose VAEs for speech emotion classification. Evaluations on the IEMOCAP dataset demonstrate that features learned by VAEs can produce state-of-the-art results for speech emotion classification.
In this work, we tackle a problem of speech emotion classification. One of the issues in the area of affective computation is that the amount of annotated data is very limited. On the other hand, the number of ways that the same emotion can be expressed verbally is enormous due to variability between speakers. This is one of the factors that limits performance and generalization. We propose a simple method that extracts audio samples from movies using textual sentiment analysis. As a result, it is possible to automatically construct a larger dataset of audio samples with positive, negative emotional and neutral speech. We show that pretraining recurrent neural network on such a dataset yields better results on the challenging EmotiW corpus. This experiment shows a potential benefit of combining textual sentiment analysis with vocal information.
Acoustically expressed emotions can make communication with a robot more efficient. Detecting emotions like anger could provide a clue for the robot indicating unsafe/undesired situations. Recently, several deep neural network-based models have been proposed which establish new state-of-the-art results in affective state evaluation. These models typically start processing at the end of each utterance, which not only requires a mechanism to detect the end of an utterance but also makes it difficult to use them in a real-time communication scenario, e.g. human-robot interaction. We propose the EmoRL model that triggers an emotion classification as soon as it gains enough confidence while listening to a person speaking. As a result, we minimize the need for segmenting the audio signal for classification and achieve lower latency as the audio signal is processed incrementally. The method is competitive with the accuracy of a strong baseline model, while allowing much earlier prediction.