The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
We have applied Latent Topic Models to facial expression recognition. We showed that the latent topic learned from a topic model is very similar to the Action Units defined by psychologists in the Facial Action Coding Systems (FACS). Furthermore, we noted that the topics thus obtained may be correlated with each other, and we tried to model this by the correlated topic model (CTM). Preliminary results...
Facial expressions are dynamic events comprised of meaningful temporal segments. A common approach to facial expression recognition in video is to first convert variable-length expression sequences into a vector representation by computing summary statistics of image-level features or of spatio-temporal features. These representations are then passed to a discriminative classifier such as a support...
ADFA-LD is a recently released data set for evaluating host-based anomaly detection systems, aiming to substitute the existing benchmark data sets which have failed to reflect the characteristics of modern computer systems. In a previous work, we had attempted to evaluate ADFA-LD with a highly efficient frequency model but the performance is inferior. In this paper, we focus on the other typical technical...
Data-driven methods based on machine learning enable powerful frameworks for analyzing complex physiological signals in medical-sensor applications; however, these methods are not well supported by traditional DSPs. A general-purpose microprocessor is presented in 130nm CMOS that integrates configurable accelerators, enabling low-energy hardware to support the broadest range of machine-learning frameworks...
Automatic speech recognition analysis has been an active part in computer science for more than two decades. In general, to detect an emotion, long continuous signal is needed. Relative amplitude reduces bias of glottal mutation of speech wave amplitude and obtains a normalized measure without concern of information from being distinct in feature. Nonverbal communication plays crucial role in human-human...
Generative embeddings use generative probabilistic models to project objects into a vectorial space of reduced dimensionality - where the so-called generative kernels can be defined. Some of these approaches employ generative models on latent variables to project objects into a feature space where the dimensions are related to the latent variables. Here, we propose to enhance the discriminative power...
We propose a new method for the detection of evoked potentials that combines a generative model and a discriminative classifier. The method is a variant of the support vector machine (SVM), which uses the Fisher kernel. The kernel function is derived from a generative statistical model known as mixed effects model (MEM). Instead of arbitrarily selecting the Gaussian kernel for the SVM, we exploit...
Mispronunciation detection is an important component in computer assisted language learning (CALL) system. In this work, we introduce an efficient GLDS-SVM based detection method, which is successfully used in language and speaker identification systems, and combine it with traditional methods. The main ideas include: extended MFCC features with normalized formant trajectory information, and then...
In conjunction with physics-based feature extraction, Hidden Markov Model. (HMM) classifiers have been used successfully to fuse scattering data from multiple target orientations where the target-sensor orientation is generally unknown or “hidden” [1]. The use of prior knowledge concerning sensor motion is employed in modeling the sequential data, improving classification performance. However, the...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.