By Topic

Affective Computing, IEEE Transactions on

Issue 2 • Date April-June 2011

Filter Results

Displaying Results 1 - 5 of 5
  • Introduction to the Affect-Based Human Behavior Understanding Special Issue

    Publication Year: 2011 , Page(s): 64 - 65
    Save to Project icon | Request Permissions | PDF file iconPDF (81 KB) |  | HTML iconHTML  
    Freely Available from IEEE
  • Real-Time Recognition of Affective States from Nonverbal Features of Speech and Its Application for Public Speaking Skill Analysis

    Publication Year: 2011 , Page(s): 66 - 78
    Cited by:  Papers (4)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1804 KB) |  | HTML iconHTML  

    This paper presents a new classification algorithm for real-time inference of affect from nonverbal features of speech and applies it to assessing public speaking skills. The classifier identifies simultaneously occurring affective states by recognizing correlations between emotions and over 6,000 functional-feature combinations. Pairwise classifiers are constructed for nine classes from the Mind Reading emotion corpus, yielding an average cross-validation accuracy of 89 percent for the pairwise machines and 86 percent for the fused machine. The paper also shows a novel application of the classifier for assessing public speaking skills, achieving an average cross-validation accuracy of 81 percent and a leave-one-speaker-out classification accuracy of 61 percent. Optimizing support vector machine coefficients using grid parameter search is shown to improve the accuracy by up to 25 percent. The emotion classifier outperforms previous research on the same emotion corpus and is successfully applied to analyze public speaking skills. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Dynamic Cascades with Bidirectional Bootstrapping for Action Unit Detection in Spontaneous Facial Behavior

    Publication Year: 2011 , Page(s): 79 - 91
    Cited by:  Papers (9)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2668 KB) |  | HTML iconHTML  

    Automatic facial action unit detection from video is a long-standing problem in facial expression analysis. Research has focused on registration, choice of features, and classifiers. A relatively neglected problem is the choice of training images. Nearly all previous work uses one or the other of two standard approaches. One approach assigns peak frames to the positive class and frames associated with other actions to the negative class. This approach maximizes differences between positive and negative classes, but results in a large imbalance between them, especially for infrequent AUs. The other approach reduces imbalance in class membership by including all target frames from onsets to offsets in the positive class. However, because frames near onsets and offsets often differ little from those that precede them, this approach can dramatically increase false positives. We propose a novel alternative, dynamic cascades with bidirectional bootstrapping (DCBB), to select training samples. Using an iterative approach, DCBB optimally selects positive and negative samples in the training data. Using Cascade Adaboost as basic classifier, DCBB exploits the advantages of feature selection, efficiency, and robustness of Cascade Adaboost. To provide a real-world test, we used the RU-FACS (a.k.a. M3) database of nonposed behavior recorded during interviews. For most tested action units, DCBB improved AU detection relative to alternative approaches. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Continuous Prediction of Spontaneous Affect from Multiple Cues and Modalities in Valence-Arousal Space

    Publication Year: 2011 , Page(s): 92 - 105
    Cited by:  Papers (34)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1855 KB) |  | HTML iconHTML  

    Past research in analysis of human affect has focused on recognition of prototypic expressions of six basic emotions based on posed data acquired in laboratory settings. Recently, there has been a shift toward subtle, continuous, and context-specific interpretations of affective displays recorded in naturalistic and real-world settings, and toward multimodal analysis and recognition of human affect. Converging with this shift, this paper presents, to the best of our knowledge, the first approach in the literature that: 1) fuses facial expression, shoulder gesture, and audio cues for dimensional and continuous prediction of emotions in valence and arousal space, 2) compares the performance of two state-of-the-art machine learning techniques applied to the target problem, the bidirectional Long Short-Term Memory neural networks (BLSTM-NNs), and Support Vector Machines for Regression (SVR), and 3) proposes an output-associative fusion framework that incorporates correlations and covariances between the emotion dimensions. Evaluation of the proposed approach has been done using the spontaneous SAL data from four subjects and subject-dependent leave-one-sequence-out cross validation. The experimental results obtained show that: 1) on average, BLSTM-NNs outperform SVR due to their ability to learn past and future context, 2) the proposed output-associative fusion framework outperforms feature-level and model-level fusion by modeling and learning correlations and patterns between the valence and arousal dimensions, and 3) the proposed system is well able to reproduce the valence and arousal ground truth obtained from human coders. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Toward a Minimal Representation of Affective Gestures

    Publication Year: 2011 , Page(s): 106 - 118
    Cited by:  Papers (12)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (934 KB) |  | HTML iconHTML  

    This paper presents a framework for analysis of affective behavior starting with a reduced amount of visual information related to human upper-body movements. The main goal is to individuate a minimal representation of emotional displays based on nonverbal gesture features. The GEMEP (Geneva multimodal emotion portrayals) corpus was used to validate this framework. Twelve emotions expressed by 10 actors form the selected data set of emotion portrayals. Visual tracking of trajectories of head and hands were performed from a frontal and a lateral view. Postural/shape and dynamic expressive gesture features were identified and analyzed. A feature reduction procedure was carried out, resulting in a 4D model of emotion expression that effectively classified/grouped emotions according to their valence (positive, negative) and arousal (high, low). These results show that emotionally relevant information can be detected/measured/obtained from the dynamic qualities of gesture. The framework was implemented as software modules (plug-ins) extending the EyesWeb XMI Expressive Gesture Processing Library and is going to be used in user centric, networked media applications, including future mobiles, characterized by low computational resources, and limited sensor systems. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.

Aims & Scope

The IEEE Transactions on Affective Computing is a cross-disciplinary and international archive journal aimed at disseminating results of research on the design of systems that can recognize, interpret, and simulate human emotions and related affective phenomena. 

Full Aims & Scope

Meet Our Editors

Editor In Chief

Björn W. Schuller
Imperial College London 
Department of Computing
180 Queens' Gate, Huxley Bldg.
London SW7 2AZ, UK
e-mail: schuller@ieee.org