An expressive text-driven 3D talking head

Creating a realistic talking head, which given an arbitrary text as input generates a realistic looking face speaking the text, has been a long standing research challenge. Talking heads which cannot express emotion have been made to look very realistic by using concatenative approaches [Wang et al. 2011], however allowing the head to express emotion creates a much more challenging problem and model based approaches have shown promise in this area. While 2D talking heads currently look more realistic than their 3D counterparts, they are limited both in the range of poses they can express and in the lighting conditions that they can be rendered under. Previous attempts to produce videorealistic 3D expressive talking heads [Cao et al. 2005] have produced encouraging results but not yet achieved the level of realism of their 2D counterparts.

Spawning areas and early development of long spiky-head carp (Luciobrama macrocephalus) in the Yangtze River and Pearl River, China

The spawning areas and early development of long spiky-head carp, Luciobrama macrocephalus (Lacepede), an endemic fish species in China, were investigated in the Yangtze River and Pearl River of central and southeastern China between 1961 and 1993. The potamodromous fish migrated upstream to spawn between May and July as the floodwater began to rise. The water-hardened eggs drifted down the river, and the embryos and larvae developed in the course of drifting. The spawning areas of the fish were widely found in the upper and middle main channels and large tributaries. Two large dams (Gezhouba dam and Danjiangkou dam) did not significantly impact on the reproduction of the fish. Fifty stages of the early development from one cell to the juvenile with fully formed fins were observed and characterized pictorially. The larvae of long spiky-head carp could be distinguished from the larvae of other co-occurring species by counting the number of somites and comparing the proportion of sizes of eye to otic capsule.

Morphology of head-to-tail poly(3-hexylthiophene) single crystals from solution crystallization

Single crystals of head-to-tail poly(3-hexylthiophene)s have been grown through the method of isothermal solution crystallization. Electron diffraction in combination with powder X-ray diffraction revealed the crystal structure, a = 1.52 nm, b = 3.36 nm, c = 1.56 nm and alpha = beta = gamma = 90 degrees.

Scophthalmus maximus cystatin B enhances head kidney macrophage-mediated bacterial killing

Cystatins form a large family of cysteine protease inhibitors found in a wide arrange of organisms. Studies have indicated that mammalian cystatins play important roles under both physiological and pathological conditions. However, much less is known about fish cystatins. In this report, we described the identification and analysis of a cystatin B homologue, SmCytB, from turbot Scophthalmus maximus. The open reading frame of SmCytB is 300 bp, which encodes a 99-residue protein that shares high levels of sequence identities with the cystatin B of a number of fish species and contains the conserved cysteine protease inhibitor motif of cystatin B. Constitutive expression of SmCytB is high in muscle, brain, heart and liver, and low in spleen. blood, gill and kidney. Bacterial infection upregulates SmCytB expression in kidney, spleen, liver and brain but not in muscle or heart. Functional analysis showed that recombinant SmCytB purified from Escherichia colt exhibits apparent cysteine protease inhibitor activity. Transient overexpression of SmCytB in head kidney macrophages enhances macrophage bactericidal activity probably through a nitric oxide-independent mechanism. These results indicate that SmCytB is involved in the immune defense of turbot against bacterial infection. (C) 2010 Elsevier Ltd. All rights reserved.

Exploring Vision-Based Interfaces: How to Use Your Head in Dual Pointing Tasks

The utility of vision-based face tracking for dual pointing tasks is evaluated. We first describe a 3-D face tracking technique based on real-time parametric motion-stereo, which is non-invasive, robust, and self-initialized. The tracker provides a real-time estimate of a ?frontal face ray? whose intersection with the display surface plane is used as a second stream of input for scrolling or pointing, in paral-lel with hand input. We evaluated the performance of com-bined head/hand input on a box selection and coloring task: users selected boxes with one pointer and colors with a second pointer, or performed both tasks with a single pointer. We found that performance with head and one hand was intermediate between single hand performance and dual hand performance. Our results are consistent with previously reported dual hand conflict in symmetric pointing tasks, and suggest that a head-based input stream should be used for asymmetric control.

Head Tracking via Robust Registration in Texture Map Images

A novel method for 3D head tracking in the presence of large head rotations and facial expression changes is described. Tracking is formulated in terms of color image registration in the texture map of a 3D surface model. Model appearance is recursively updated via image mosaicking in the texture map as the head orientation varies. The resulting dynamic texture map provides a stabilized view of the face that can be used as input to many existing 2D techniques for face recognition, facial expressions analysis, lip reading, and eye tracking. Parameters are estimated via a robust minimization procedure; this provides robustness to occlusions, wrinkles, shadows, and specular highlights. The system was tested on a variety of sequences taken with low quality, uncalibrated video cameras. Experimental results are reported.

Automatic Detection of Relevant Head Gestures in American Sign Language Communication

An automated system for detection of head movements is described. The goal is to label relevant head gestures in video of American Sign Language (ASL) communication. In the system, a 3D head tracker recovers head rotation and translation parameters from monocular video. Relevant head gestures are then detected by analyzing the length and frequency of the motion signal's peaks and valleys. Each parameter is analyzed independently, due to the fact that a number of relevant head movements in ASL are associated with major changes around one rotational axis. No explicit training of the system is necessary. Currently, the system can detect "head shakes." In experimental evaluation, classification performance is compared against ground-truth labels obtained from ASL linguists. Initial results are promising, as the system matches the linguists' labels in a significant number of cases.

Fast, Reliable Head Tracking under Varying Illumination

An improved technique for 3D head tracking under varying illumination conditions is proposed. The head is modeled as a texture mapped cylinder. Tracking is formulated as an image registration problem in the cylinder's texture map image. To solve the registration problem in the presence of lighting variation and head motion, the residual error of registration is modeled as a linear combination of texture warping templates and orthogonal illumination templates. Fast and stable on-line tracking is then achieved via regularized, weighted least squares minimization of the registration error. The regularization term tends to limit potential ambiguities that arise in the warping and illumination templates. It enables stable tracking over extended sequences. Tracking does not require a precise initial fit of the model; the system is initialized automatically using a simple 2-D face detector. The only assumption is that the target is facing the camera in the first frame of the sequence. The warping templates are computed at the first frame of the sequence. Illumination templates are precomputed off-line over a training set of face images collected under varying lighting conditions. Experiments in tracking are reported.

Fast, Reliable Head Tracking under Varying Illumination: An Approach Based on Registration of Texture-Mapped 3D Model

An improved technique for 3D head tracking under varying illumination conditions is proposed. The head is modeled as a texture mapped cylinder. Tracking is formulated as an image registration problem in the cylinder's texture map image. The resulting dynamic texture map provides a stabilized view of the face that can be used as input to many existing 2D techniques for face recognition, facial expressions analysis, lip reading, and eye tracking. To solve the registration problem in the presence of lighting variation and head motion, the residual error of registration is modeled as a linear combination of texture warping templates and orthogonal illumination templates. Fast and stable on-line tracking is achieved via regularized, weighted least squares minimization of the registration error. The regularization term tends to limit potential ambiguities that arise in the warping and illumination templates. It enables stable tracking over extended sequences. Tracking does not require a precise initial fit of the model; the system is initialized automatically using a simple 2D face detector. The only assumption is that the target is facing the camera in the first frame of the sequence. The formulation is tailored to take advantage of texture mapping hardware available in many workstations, PC's, and game consoles. The non-optimized implementation runs at about 15 frames per second on a SGI O2 graphic workstation. Extensive experiments evaluating the effectiveness of the formulation are reported. The sensitivity of the technique to illumination, regularization parameters, errors in the initial positioning and internal camera parameters are analyzed. Examples and applications of tracking are reported.

Fast Head Tilt Detection for Human-Computer Interaction

Accurate head tilt detection has a large potential to aid people with disabilities in the use of human-computer interfaces and provide universal access to communication software. We show how it can be utilized to tab through links on a web page or control a video game with head motions. It may also be useful as a correction method for currently available video-based assistive technology that requires upright facial poses. Few of the existing computer vision methods that detect head rotations in and out of the image plane with reasonable accuracy can operate within the context of a real-time communication interface because the computational expense that they incur is too great. Our method uses a variety of metrics to obtain a robust head tilt estimate without incurring the computational cost of previous methods. Our system runs in real time on a computer with a 2.53 GHz processor, 256 MB of RAM and an inexpensive webcam, using only 55% of the processor cycles.

Neural Representations for Sensory-Motor Control I: Head-Centered 3-D Target Positions from Opponent Eye Commands

This article describes how corollary discharges from outflow eye movement commands can be transformed by two stages of opponent neural processing into a head-centered representation of 3-D target position. This representation implicitly defines a cyclopean coordinate system whose variables approximate the binocular vergence and spherical horizontal and vertical angles with respect to the observer's head. Various psychophysical data concerning binocular distance perception and reaching behavior are clarified by this representation. The representation provides a foundation for learning head-centered and body-centered invariant representations of both foveated and non-foveated 3-D target positions. It also enables a solution to be developed of the classical motor equivalence problem, whereby many different joint configurations of a redundant manipulator can all be used to realize a desired trajectory in 3-D space.

Coordinated activation of candidate proto-oncogenes and cancer testes antigens via promoter demethylation in head and neck cancer and lung cancer.

BACKGROUND: Epigenetic alterations have been implicated in the pathogenesis of solid tumors, however, proto-oncogenes activated by promoter demethylation have been sporadically reported. We used an integrative method to analyze expression in primary head and neck squamous cell carcinoma (HNSCC) and pharmacologically demethylated cell lines to identify aberrantly demethylated and expressed candidate proto-oncogenes and cancer testes antigens in HNSCC. METHODOLOGY/PRINCIPAL FINDINGS: We noted coordinated promoter demethylation and simultaneous transcriptional upregulation of proto-oncogene candidates with promoter homology, and phylogenetic footprinting of these promoters demonstrated potential recognition sites for the transcription factor BORIS. Aberrant BORIS expression correlated with upregulation of candidate proto-oncogenes in multiple human malignancies including primary non-small cell lung cancers and HNSCC, induced coordinated proto-oncogene specific promoter demethylation and expression in non-tumorigenic cells, and transformed NIH3T3 cells. CONCLUSIONS/SIGNIFICANCE: Coordinated, epigenetic unmasking of multiple genes with growth promoting activity occurs in aerodigestive cancers, and BORIS is implicated in the coordinated promoter demethylation and reactivation of epigenetically silenced genes in human cancers.

Locomotor head movements and semicircular canal morphology in primates.

Animal locomotion causes head rotations, which are detected by the semicircular canals of the inner ear. Morphologic features of the canals influence rotational sensitivity, and so it is hypothesized that locomotion and canal morphology are functionally related. Most prior research has compared subjective assessments of animal "agility" with a single determinant of rotational sensitivity: the mean canal radius of curvature (R). In fact, the paired variables of R and body mass are correlated with agility and have been used to infer locomotion in extinct species. To refine models of canal functional morphology and to improve locomotor inferences for extinct species, we compare 3D vector measurements of head rotation during locomotion with 3D vector measures of canal sensitivity. Contrary to the predictions of conventional models that are based upon R, we find that axes of rapid head rotation are not aligned with axes of either high or low sensitivity. Instead, animals with fast head rotations have similar sensitivities in all directions, which they achieve by orienting the three canals of each ear orthogonally (i.e., along planes at 90° angles to one another). The extent to which the canal configuration approaches orthogonality is correlated with rotational head speed independent of body mass and phylogeny, whereas R is not.

Impact of tumor board recommendations on treatment outcome for locally advanced head and neck cancer

Background/Aims: To identify physician selection factors in the treatment of locally advanced head and neck cancer and how treatment outcome is affected by Tumor Board recommendations. Methods: A retrospective analysis of 213 patients treated for locally advanced head and neck cancer in a single institution was performed. All treatments followed Tumor Board recommendations: 115 patients had chemotherapy and radiation, and 98 patients received postoperative radiation. Patient characteristics, treatment toxicity, locoregional control and survival between these two treat- ment groups were compared. Patient survival was compared with survival data reported in randomized studies of locally advanced head and neck cancer. Results: There were no differences in comorbidity factors, and T or N stages between the two groups. A statistically significant number of patients with oropharyngeal and oral cavity tumors had chemoradiation and postoperative radiation, respectively (p < 0.0001). Grade 3-4 toxicities during treatment were 48 and 87% for the postoperative radiation and chemoradiation groups, respectively (p = 0.0001). There were no differences in survival, locoregional recurrences and distant metastases between the two groups. Patient survival was comparable to survival rates reported by randomized studies of locally advanced head and neck cancer. Conclusion: Disease sites remained the key determining factor for treatment selection. Multidisciplinary approaches provided optimal treatment outcome for locally advanced head and neck cancer, with overall survival in these patients being comparable to that reported in randomized clinical trials. Copyright © 2008 S. Karger AG.