Accelerating temporal action proposal generation via high performance computing

Temporal action proposal generation aims to output the starting and ending times of each potential action for long videos and often suffers from high computation cost. To address the issue, we propose a new temporal convolution network called Multipath Temporal ConvNet (MTCN). In our work, one novel high performance ring parallel architecture based is further introduced into temporal action proposal generation in order to respond to the requirements of large memory occupation and a large number of videos. Remarkably, the total data transmission is reduced by adding a connection between multiplecomputing load in the newly developed architecture. Compared to the traditional Parameter Server architecture, our parallel architecture has higher efficiency on temporal action detection tasks with multiple GPUs. We conduct experiments on ActivityNet-1.3 and THUMOS14, where our method outperformsother state-of-art temporal action detection methods with high recall and high temporal precision. In addition, a time metric is further proposed here to evaluate the speed performancein the distributed training process.     

A fair comparison of SAC-OCDMA system configurations based on two dimensional cyclic shift code and spectral direct detection

This paper investigates shortcomings that limit the performance of optical code division multiple access (OCDMA) systems including the low cardinality and data rate as well as the high power at reception. The main drawback for such systems known as multiple access interference accompanying by phase induced intensity noise is also investigated to effeciencly propose a novel two dimensional cyclic shift (2D-CS) code to be implemented in non-coherent OCDMA systems. The developed code is based on a one dimensional cyclic shift (1D-CS) code previously provided by research works processing spectral amplitude coding for optical code division multiple access (SAC-OCDMA) systems. Numerical results obtained by this study are therefore compared to previous studies employing different codes like two dimensional extended double weight (2D-EDW), two dimensional flexible cross correlation/modified double weight (2D-FCC/MDW), two dimensional perfect difference (2D-PD), two dimensional diluted perfect difference (2D-DPD), two dimensional multi service (2D-MS) and two dimensional zero cross correlation/multi diagonal (2D-ZCC/MD) codes. Accordingly, it is demonstrated that the proposed 2D-CS code outperforms all codes given previously in terms of system capacity where the small increasing percentage is about 40% compared to 2D-ZCC/MD and 2D-MS. Systems using 2D-CS code can support until 203 simultaneous users with a total code length equal to 171. System performance investigation leads to a BER and Q-Factor closely to1.0E?12 and 1.0E?27, and 6.6 dB and 10.6 dB at 20 km of single mode fiber length using white light source and Laser, respectively. Furthermore, such a code can be easily adopted by OCDMA systems for a long distance up to approximately 55 and 100 km.

     

Characterisation of gamma‐irradiated polyetherimide films with infrared spectroscopy and thermally stimulated current measurements

The performance of insulators is usually affected by the presence of space charges. The evolution of these charges under applied constraints in many cases leads to the degradation of these materials. To evaluate the performance of an insulator it is necessary to study the evolution of the physical and chemical properties in the presence of space charges. In this paper, the effect of gamma irradiation on the space charge behaviour in polyetherimide (PEI; Ultem 1000) has been investigated at different radiation doses. Space charge measurements were made using thermally stimulated currents. Infrared spectroscopy characterisation was performed to investigate the effect of gamma irradiation on the physicochemical properties of PEI. The results obtained show minor differences in the infrared spectra, mainly in the 410 cm^?1 region. It is found that irradiation leads to a few structural changes in the material. The thermostimulated depolarisation current (TSDC) results show that β relaxations in PEI are affected by gamma irradiation. The activation energies of dipoles were calculated from the TSDC curves. Copyright © 2006 Society of Chemical Industry     

Mid-level features and spatio-temporal context for activity recognition

Local spatio-temporal features have been shown to be effective and robust in order to represent simple actions. However, for high level human activities with long-range motion or multiple interactive body parts and persons, the limitation of low-level features blows up because of their localness. This paper addresses the problem by suggesting a framework that computes mid-level features and takes into account their contextual information.First, we represent human activities by a set of mid-level components, referred to as activity components, which have consistent structure and motion in spatial and temporal domain respectively. These activity components are extracted hierarchically from videos, i.e., extracting key-points, grouping them into trajectories and finally clustering trajectories into components. Second, to further exploit the interdependencies of the activity components, we introduce a spatio-temporal context kernel (STCK), which not only captures local properties of features but also considers their spatial and temporal context information. Experiments conducted on two challenging activity recognition datasets show that the proposed approach outperforms standard spatio-temporal features and our STCK context kernel improves further the performance.     

Beneficial Effects of Silicon (Si) on Sea Barley (Hordeum marinum Huds.) under Salt Stress

Silicon - Silicon (Si) plays an important role in providing beneficial effects on plant growth and yield, especially under stressful environments such as salinity. The objective of this work is to...     

一种用于说话人头部动画的Viseme语音识别系统

Viseme是在语音驱动说话人头部动画中一种常用的为口形建立的音频-视频模型。本文尝试建立viseme隐马尔可夫模型(HMM)，用于驱动说话人头部的语音识别系统，称为前映射系统。为了得到更精确的模型以提高识别率，引入考虑发音口形上下文的Triseme模型。但是引入Triseme模型后，随着模型数量的急剧增加将导致训练数据的严重不足。本文使用决策树状态捆绑方法来缓解这一问题，同时引入了一种以口形相似度为基础的决策树视频问题设计方法。为了比较viseme系统的性能，本文也建立了一个以phoneme为基本HMM模型的语音识别系统。在评价准则上，使用了一种客观评价说话人头部动画的加权识别率。实验表明，以viseme为基本HMM模型的前映射系统可以为说话人头部提供更加合理的口形。     

A direct algebraic method for eigensolution sensitivity computation of damped asymmetric systems

In general, the derivative of an eigenvector of a vibrating symmetric system is the solution of a singular problem. Further complications are encountered in dealing with asymmetric damped systems for which the left and right eigenvectors and their derivatives become distinct and complex. Several approaches have been proposed to overcome this singularity such as Nelson's method and the modal method. In the present work, a new approach is presented for calculating simultaneously the derivatives of the eigenvalues and their associated derivatives of the left and right eigenvectors for asymmetric damped systems. With the proposed method, the exact eigenderivatives can be obtained by solving a first‐order linear algebraic system of equations. The method is applied on a 104 DOF ventilator–rotor system, which is used as an example of an asymmetric damped system with distinct eigenvalues. The diameter of the shaft has been chosen as the design parameter. The comparison of the computational time shows that the proposed method is more efficient than both Nelson's approach and the modal method. Copyright © 2006 John Wiley & Sons, Ltd.     

基于Viseme的连续语音识别系统及Talking Head

为实现听觉/视觉驱动的说话人头部动画,该文给出了一个基于viseme(说话时的基本嘴形单位)的连续语音识别系统。它训练viseme隐马尔可夫模型(HMM),识别语音为viseme图像序列。建模采用triseme的概念来考虑viseme的上下文相关性,但它需要超大量的训练数据。该文根据viseme图像及其相似度权值(VSW)定义视觉问题集,用来建立triseme决策树,以实现triseme的状态捆绑及HMM参数共享。为比较系统性能,基于phoneme(听觉领域的语音基本单位)的语音识别结果也被映射为viseme序列。在评价准则上,定义viseme图像相似度加权识别精度,更全面地考虑输出和参考图像序列的差别,并用嘴形圆度和VSW曲线中的突变点来评估所得viseme序列的平滑性。结果表明,基于viseme的语音识别系统能给出更平滑和合理的嘴形图像序列。