Motion field and optical flow: qualitative properties

It is shown that the motion field the 2-D vector field which is the perspective projection on the image plane of the 3-D velocity field of a moving scene, and the optical flow, defined as the estimate of the motion field which can be derived from the first-order variation of the image brightness pattern, are in general different, unless special conditions are satisfied. Therefore, dense optical flow is often ill-suited for computing structure from motion and for reconstructing the 3-D velocity field by algorithms which require a locally accurate estimate of the motion field. A different use of the optical flow is suggested. It is shown that the (smoothed) optical flow and the motion field can be interpreted as vector fields tangent to flows of planar dynamical systems. Stable qualitative properties of the motion field, which give useful informations about the 3-D velocity field and the 3-D structure of the scene, usually can be obtained from the optical flow. The idea is supported by results from the theory of structural stability of dynamical systems     

Visual Speech Synthesis by Morphing Visemes

We present MikeTalk, a text-to-audiovisual speech synthesizer which converts input text into an audiovisual speech stream. MikeTalk is built using visemes, which are a small set of images spanning a large range of mouth shapes. The visemes are acquired from a recorded visual corpus of a human subject which is specifically designed to elicit one instantiation of each viseme. Using optical flow methods, correspondence from every viseme to every other viseme is computed automatically. By morphing along this correspondence, a smooth transition between viseme images may be generated. A complete visual utterance is constructed by concatenating viseme transitions. Finally, phoneme and timing information extracted from a text-to-speech synthesizer is exploited to determine which viseme transitions to use, and the rate at which the morphing process should occur. In this manner, we are able to synchronize the visual speech stream with the audio speech stream, and hence give the impression of a photorealistic talking face.     

Putative Circulating MicroRNAs Are Able to Identify Patients with Mitral Valve Prolapse and Severe Regurgitation

Mitral valve prolapse (MVP) associated with severe mitral regurgitation is a debilitating disease with no pharmacological therapies available. MicroRNAs (miRNA) represent an emerging class of circulating biomarkers that have never been evaluated in MVP human plasma. Our aim was to identify a possible miRNA signature that is able to discriminate MVP patients from healthy subjects (CTRL) and to shed light on the putative altered molecular pathways in MVP. We evaluated a plasma miRNA profile using Human MicroRNA Card A followed by real-time PCR validations. In addition, to assess the discriminative power of selected miRNAs, we implemented a machine learning analysis. MiRNA profiling and validations revealed that miR-140-3p, 150-5p, 210-3p, 451a, and 487a-3p were significantly upregulated in MVP, while miR-223-3p, 323a-3p, 340-5p, and 361-5p were significantly downregulated in MVP compared to CTRL (p ≤ 0.01). Functional analysis identified several biological processes possible linked to MVP. In addition, machine learning analysis correctly classified MVP patients from CTRL with high accuracy (0.93) and an area under the receiving operator characteristic curve (AUC) of 0.97. To the best of our knowledge, this is the first study performed on human plasma, showing a strong association between miRNAs and MVP. Thus, a circulating molecular signature could be used as a first-line, fast, and cheap screening tool for MVP identification.     

Networks for approximation and learning

The problem of the approximation of nonlinear mapping, (especially continuous mappings) is considered. Regularization theory and a theoretical framework for approximation (based on regularization techniques) that leads to a class of three-layer networks called regularization networks are discussed. Regularization networks are mathematically related to the radial basis functions, mainly used for strict interpolation tasks. Learning as approximation and learning as hypersurface reconstruction are discussed. Two extensions of the regularization approach are presented, along with the approach's corrections to splines, regularization, Bayes formulation, and clustering. The theory of regularization networks is generalized to a formulation that includes task-dependent clustering and dimensionality reduction. Applications of regularization networks are discussed     

Incorporating prior information in machine learning by creatingvirtual examples

One of the key problems in supervised learning is the insufficient size of the training set. The natural way for an intelligent learner to counter this problem and successfully generalize is to exploit prior information that may be available about the domain or that can be learned from prototypical examples. We discuss the notion of using prior knowledge by creating virtual examples and thereby expanding the effective training-set size. We show that in some contexts this idea is mathematically equivalent to incorporating the prior knowledge as a regularizer, suggesting that the strategy is well motivated. The process of creating virtual examples in real-world pattern recognition tasks is highly nontrivial. We provide demonstrative examples from object recognition and speech recognition to illustrate the idea     

Report on workshop on high performance computing and communicationsfor grand challenge applications: computer vision, speech and naturallanguage processing, and artificial intelligence

The findings of a workshop, the goals of which were to identify applications, research problems, and designs of high performance computing and communications (HPCC) systems for supporting applications are discussed. In computer vision, the main scientific issues are machine learning, surface reconstruction, inverse optics and integration, model acquisition, and perception and action. In speech and natural language processing (SNLP), issues were identified statistical analysis in corpus-based speech and language understanding, search strategies for language analysis, auditory and vocal-tract modeling, integration of multiple levels of speech and language analyses, and connectionist systems. In AI, important issues that need immediate attention include the development of efficient machine learning and heuristic search methods that can adapt to different architectural configurations, and the design and construction of scalable and verifiable knowledge bases, active memories, and artificial neural networks     

The space-time domain magnetic vector potential integral equations

The space-frequency domain magnetic vector potential integral equations for the current distribution on wire antennas (Hallen's integral equation and Mei's generalization) are used to derive their counterparts in the space-time domain. Equations for both straight and curved wires are readily derived using a Fourier transform.     

Three-dimensional facial morphometry and conventional cephalometrics: a correlation study

Analysis of genomic sequences is necessarily an ongoing process. Initial gene assignments tend (wisely) to be on the conservative side (Venter, 1996). The analysis of the genome then grows in an iterative fashion as additional data and more sophisticated algorithms are brought to bear on the data. The present report is an emendation of the original gene list of Methanococcus jannaschii (Bult et al., 1996). By using a somewhat more updated database and more relaxed (and operator-intensive) pattern matching methods, we were able to add significantly to, and in a few cases amend, the gene identification table originally published by Bult et al. (1996).     

Speech Transport in Packet-Radio Networks with Mobile Nodes

A research effort to provide speech-carrying capabilities to a data-oriented packet-switching radio network is described. The features of the network that limit its ability to carry packetized speech are discussed, and their effects on the network performance are analyzed. A new protocol, called duct routing, that enhances the network capabilities in a mobile environment is presented. That protocol makes use of repeater redundancy to compensate for loss of communication connectivity due to node mobility. A series of experiments to evaluate the network performance in carrying speech traffic, both with data and voice protocols, is described, and the results are presented and discussed.