4 research outputs found
INTERACTIVE MODELING OF 3D FACIAL EXPRESSIONS WITH HIERARCHICAL GAUSSIAN PROCESS LATENT VARIABLE MODELS
No full textThe natural expressions play an important role in the daily communication. The efficient and intuitive facial expression editing based on the limited constraints is desirable in the facial animation. In this paper, we present an interactive 3D facial expression editing system with the hierarchical Gaussian process latent variable model (HGPLVM). The hierarchical model incorporates the joint work of the local facial features to produce the natural expressions. To deal with the holistic expression modeling from the local constraints, the inverse mapping between the low-level feature nodes and the high-level facial region nodes is established by the RBF regression model in the latent space. A propagation algorithm is introduced to predict the holistic facial configurations. The experiments demonstrate the 3D facial expressions satisfying the user constraints can be produced efficiently.Computer Science, Artificial IntelligenceComputer Science, Information SystemsEngineering, Electrical & ElectronicCPCI-S(ISTP)
Unsupervised Image Matching Based on Manifold Alignment
No full textThis paper challenges the issue of automatic matching between two image sets with similar intrinsic structures and different appearances, especially when there is no prior correspondence. An unsupervised manifold alignment framework is proposed to establish correspondence between data sets by a mapping function in the mutual embedding space. We introduce a local similarity metric based on parameterized distance curves to represent the connection of one point with the rest of the manifold. A small set of valid feature pairs can be found without manual interactions by matching the distance curve of one manifold with the curve cluster of the other manifold. To avoid potential confusions in image matching, we propose an extended affine transformation to solve the nonrigid alignment in the embedding space. The comparatively tight alignments and the structure preservation can be obtained simultaneously. The point pairs with the minimum distance after alignment are viewed as the matchings. We apply manifold alignment to image set matching problems. The correspondence between image sets of different poses, illuminations, and identities can be established effectively by our approach.http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000305188500016&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=8e1609b174ce4e31116a60747a720701Computer Science, Artificial IntelligenceEngineering, Electrical & ElectronicSCI(E)PubMed9ARTICLE81658-16643
Personalized Tooth Shape Estimation From Radiograph and Cast
No full textThree-dimensional geometric information of teeth is usually needed in pre- and postoperative diagnoses of orthodontic dentistry. The computerized tomography can provide comprehensive 3-D teeth geometries. However, there is still a discussion on computed tomography (CT) as a routine in orthodontic dentistry due to radiation dose. Moreover, the CT is useless when a dentist needs to extract 3-D structures from old archive files with only radiographs and casts, where patient's teeth changed ever since. In this paper, we propose a reconstruction framework for patient-specific teeth based on an integration of 2-D radiographs and digitized casts. The reconstruction is under a template-fitting framework. The shape and orientation of teeth templates are tuned in accordance with patient's radiographs. Specially, the tooth root morphology is controlled by 2-D contours in radiographs. With ray tracing and a contour plane assumption, 2-D root contours in radiographs are projected back to 3-D space, and guide tooth root deformations. Moreover, the template's crown is deformed nonrigidly to fit digitized casts that bear patient's crown details. The system allows 3-D tooth reconstruction with patient-specific geometric details from just casts and 2-D radiographs.http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000307895000003&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=8e1609b174ce4e31116a60747a720701Engineering, BiomedicalSCI(E)EIPubMed5ARTICLE92400-24115
The Representation of Gender in Contemporary Chinese Television Advertising: An Analysis of Content, Meaning, and Production
No full textThis thesis examines how gender is portrayed in Chinese television commercials and how these representations reflect the social and cultural contexts of their production and the institutional practices of advertising production personnel. To date, while there have been a plethora of studies on gender representation in advertising in western contexts only limited attention has been given to Chinese advertising portrayals of gender. This study, therefore, explores particular ways in which femininity and masculinity are discursively constructed, and how this process, in turn, contributes to reinforcing and/or challenging certain gender ideologies, in particular those found in Chinese Confucian culture. The study is unique in its approach to Chinese television advertising in that it combines methods from textual analysis (quantitative content analysis, semiotic analysis and critical discourse analysis) and empirical research (interview). A sample of 679 television commercials was collected and analysed in this investigation. Content analysis was initially applied to identify recurrent patterns and characteristics of gender representation which, in turn, formed the basis for in-depth semiotic and discourse analysis. Specific signs, images, codes, discourses and myths were subsequently discussed. The study also included semi-structured interviews with 26 Chinese advertising personnel in order to understand their multiple dispositions toward gender and their actual experiences of depicting female and male characters in the creative process. Several main findings emerged from this study. The portrayal of gender in Chinese television commercials is complex because it embodies a series of simultaneously conflicting and complementary discourses on what constitute femininity and masculinity. The results of the content analysis revealed that the representation of gender in this study’s sample still remains stereotypical in terms of the different distribution of the sexes across product category, role, dress, age, credibility and voice-over. By focusing on the constructs of gender in domestic, occupational and recreational contexts, the use of semiotic and discourse analysis revealed that Chinese television advertising not only portrays women and men in line with the significant aspects embedded in both Chinese and western patriarchal traditions, but is also constitutive of cultural shifts in gender ideologies through highlighting modern (western) values. In addition, the interview findings yielded support for the conclusions of textual analysis, demonstrating that the process of advertising production is significantly influenced by traditional and modern gender values, the restriction of advertising regulations, client expectations, and the professionals’ divergent perceptions of gender and their assumptions about the audience
