高斯核尺度空间中的采样算法研究

将线性尺度空间的特征点扩展问题转化为多尺度数据集的同尺度内分类问题,该问题属于尺度不变的非平衡数据集分类问题。提出了一种基于尺度空间的核学习的采样算法来处理支持向量机(support vector machine,SVM)在非平衡数据集上的分类问题。其核心思想是首先在核空间中对少数类样本进行上采样,然后通过输入空间和核空间的距离关系寻找所合成样本在输入空间的原像,最后再采用SVM对其进行训练,从而有效克服了目前采样方法在不同空间处理训练样本所带来的数据不一致问题。该算法所采用的采样策略不仅能够降低数据失衡率,而且能够拓展少数类样本所形成的凸壳,从而更为有效地纠正最优分类超平面偏移问题。实验结果证明,所获得的结果分类器具有更好的泛化性能,能够在同尺度内有效扩展稳定特征点数量。     

多任务学习的不平衡SVM+算法

处理不平衡数据分类时,传统支持向量机技术（SVM）对少数类样本识别率较低。鉴于SVM+技术能利用样本间隐藏信息的启发,提出了多任务学习的不平衡SVM+算法（MTL-IC-SVM+）。MTL-IC-SVM+基于SVM+将不平衡数据的分类表示为一个多任务的学习问题,并从纠正分类面的偏移出发,分别赋予多数类和少数类样本不同的错分惩罚因子,且设置少数类样本到分类面的距离大于多数类样本到分类面的距离。UCI数据集上的实验结果表明,MTL-IC-SVM+在不平衡数据分类问题上具有较高的分类精度。     

Fast and compact dynamic data compression based on composite rigid body construction

3D dynamic datasets compression still poses two challenges. One is high time cost due to growing data and complex computation of compression algorithms. The other is low compression factor because of complex motions of dynamic scenes and unknown motion equations. In this paper, composite rigid body construction for fast and compact compression of 3D dynamic datasets is proposed to solve these two problems. It accelerates the compression with a fast rigid body decomposition based on disjoint union, and avoids serial searching, comparing and merging of the rigid body decomposition. To increase the compression factor, composite rigid body is introduced with consideration of motion consistency among rigid bodies at different time periods. The results of the experiments show that our algorithm compresses dynamic datasets quickly and achieves a high compression factor.     

基于最小包含球的非静态大数据集的快速分类算法

对于小规模的非静态数据,最近提出的时间自适应支持向量机(TA-SVM)方法表现出良好的性能,它从兼顾局部优化和全局优化的角度同时求解多个子分类器的特性.但对于大数据集,较高的计算代价限制了它的实用性.针对此不足,结合核心向量机(CVM)理论提出了针对非静态大数据集的新颖分类方法,即基于中心约束最小包含球(CCMEB)的TA-CVM,简称CCTA-CVM.该方法具有渐近线性时间复杂度的优点,同时继承了TA-SVM的良好性能.最后通过实验验证了所提出方法的有效性.     

基于Huber指数平方损失函数的二维人体姿态估计网络

人体姿态估计是计算机视觉领域的一个研究热点,已经应用于教育、体育等方面,在视频监控、人机交互、智能校园等领域有着广阔的应用前景.简单的姿态估计基线方法在沙漏残差模块中加入几层反卷积层,使用均方误差(MSE)损失函数,结构和算法复杂度较低且能够较为精确地预测出关节点热图.首先,采用分段函数H-ESL(huber-exponential squared loss)损失函数,克服了MSE损失函数对于异常值较为敏感的缺点.其次,提出的网络在基线方法的网络上加入了注意力机制,并将大的卷积核转换成小的卷积核,使得网络精度提升的同时减少参数量及计算量,从而提高网络的预测效率.拟建网络利用COCO2017数据集的地面真实值分别进行训练和验证,均实现了高精度,mAP提高了2.6％,证明该方法适用于各种人类关键热图的输入,并能取得良好的效果.     

Comprehensive color solutions: CAM16, CAT16, and CAM16‐UCS

The CIECAM02 color‐appearance model enjoys popularity in scientific research and industrial applications since it was recommended by the CIE in 2002. However, it has been found that computational failures can occur in certain cases such as during the image processing of cross‐media color reproduction applications. Some proposals have been developed to repair the CIECAM02 model. However, all the proposals developed have the same structure as the original CIECAM02 model and solve the problems concerned at the expense of losing accuracy of predicted visual data compared with the original model. In this article, the structure of the CIECAM02 model is changed and the color and luminance adaptations to the illuminant are completed in the same space rather than in two different spaces, as in the original CIECAM02 model. It has been found that the new model (named CAM16) not only overcomes the previous problems, but also the performance in predicting the visual results is as good as if not better than that of the original CIECAM02 model. Furthermore the new CAM16 model is simpler than the original CIECAM02 model. In addition, if considering only chromatic adaptation, a new transformation, CAT16, is proposed to replace the previous CAT02 transformation. Finally, the new CAM16‐UCS uniform color space is proposed to replace the previous CAM02‐UCS space. A new complete solution for color‐appearance prediction and color‐difference evaluation can now be offered.     

Analysis and clustering of multiblock datasets by means of the STATIS and CLUSTATIS methods. Application to sensometrics

The STATIS method has been successfully applied to the analysis of sensory profiling data and other kinds data in sensometrics. We discuss its use and benefits and compare its outcomes to alternative methods for the analysis of multiblock data arising in situations such as projective mapping and free sorting experiments. More importantly, a method of clustering a collection of datasets measured on the same individuals, called CLUSTATIS, is introduced. It is based on the optimization of a criterion and consists in a hierarchical cluster analysis and a partitioning algorithm akin to the K-means algorithm. The procedure of analysis can be seen as an extension of the cluster analysis of variables around latent components (CLV, Vigneau & Qannari, 2003) to the case of blocks of variables. Alongside the determination of the clusters, a latent configuration is determined by the STATIS method. The interest of CLUSTATIS in sensometrics is discussed and illustrated on the basis of two case studies pertaining to the projective mapping also called Napping and the free sorting tasks, respectively.     

A Consistent Dataset of Kinetic Solubilities for Early‐Phase Drug Discovery

Herein, we describe a new dataset of kinetic aqueous solubilities determined by nephelometry for 711 druglike compounds. The solubilities are reported in twelve classes ranging from <2 μg mL^?1 to >250 μg mL^?1. The measurements were designed to provide the appropriate data for applications in the early phases of drug discovery. Three class classification models (insoluble, moderately soluble, soluble) were built using the random forest algorithm and their performance for this dataset was analyzed.     

Fragile Watermarking of 3D Models Using Genetic Algorithms

This paper describes a novel algorithm for fragile watermarking of 3D models. Fragile watermarking requires detection of even minute intentional changes to the 3D model along with the location of the change. This poses a challenge since inserting random amount of watermark in all the vertices of the model would generally introduce perceptible distortion. The proposed algorithm overcomes this challenge by using genetic algorithm to modify every vertex location in the model so that there is no perceptible distortion. Various experimental results are used to justify the choice of the genetic algorithm design parameters. Experimental results also indicate that the proposed algorithm can accurately detect location of any mesh modification.