Previous research has provided inconsistent results regarding visual search for emotional faces, yielding evidence for either anger superiority (i.e., more efficient search for angry faces) or happiness superiority effects (i.e., more efficient search for happy faces), suggesting that these results do not reflect on emotional expression, but on emotion (un-)related low-level perceptual features...

The area of custom database applications is a large and rapidly growing domain, as evidenced by the appearance of tools for developing web front-ends to databases (e.g. Microsoft Visual InterDev), the large number of commercial programming environments now providing \database wizards" (e.g. Symantec Visual Caf e, Microsoft Visual C++) and the emergence of database interconnectivity standards (e...

This chapter presents our research on real-time speech-driven face animation. First, a visual representation, called Motion Unit (MU), for facial deformation is learned from a set of labeled face deformation data. A facial deformation can be approximated by a linear combination of MUs weighted by the corresponding MU parameters (MUPs), which are used as the visual features of facial deformation...

Encouraged by the good performance of the DCT in audiovisual speech recognition [1], we investigate how the selection of the DCT coefficients influences the recognition scores in a hybridANN/HMM audio-visual speech recognition system on a continuous word recognition task with a vocabulary of 30 numbers. Three sets of coefficients, based on the mean energy, the variance and the variance relative...

In this paper, we describe a query system that provides visual relevance feedback in querying large databases. Our goal is to support the process of data mining by representing as many data items as possible on the display. By arranging and coloring the data items as pixels according to their relevance for the query, the user gets a visual impression of the resulting data set. Using an interact...

In this paper we present the Bilingual Audio-Visual Corpus with Depth information (BAVCD). The database contains utterances of connected digits, spoken by 15 subjects in English and 6 subjects in Greek, and collected employing multiple audio-visual sensors. Among them, of particular interest is the use of the Microsoft Kinect device, which is able to capture facial depth images using the struct...

The increasing amount of internet based television broadcasts has lead to new approachs to interactivity in TV programs. We developed a system which is able to supply the viewer of the program upon interaction with information relating to the program, only based on the low-level visual content of the scene. This aim is achieved by comparing signatures describing the visual content of single fra...

Encouraged by the good performance of the DCT in audiovisual speech recognition [1], we investigate how the selection of the DCT coefficients influences the recognition scores in a hybrid ANN/HMM audio-visual speech recognition system on a continuous word recognition task with a vocabulary of 30 numbers. Three sets of coefficients, based on the mean energy, the variance and the variance relativ...

The task of visual speech synthesis is usually solved by concatenation of basic speech units selected from a visual speech database. Acoustical part is carried out separately using similar method. There are two main problems in this process. The first problem is a design of a database, that means estimation of the database parameters for all basic speech units. Second problem is a way how to co...

primary immunodeficiencies are rare diseases, characterized by an increased susceptibility to infections. early diagnosis and appropriate treatment are critical for reducing morbidity and mortality. given the rarity of these diseases, the awareness of these disorders by physicians is often insufficient, leading to delayed diagnosis and inappropriate treatment which are the major causes of sever...