CVPR2012_oral Weakly Supervised Structured Output Learning for Semantic Segmentation-We address the problem of weakly supervised semantic segmentation. The training images are labeled only by the classes they contain, not by their location in t

In predicting electrical tree growth behavior of practical insulation materials under operating voltages, one must consider the effects of mechanical tensile residual stresses, electrical field stresses and the voids distribution to the electri

了适应跟踪过程中目标光照条件的变化，并对目标特征进行在线更新，提出一种将局部二元模式(LBP) 特征与图像灰度信息相融合，同时结合增量线性判别分析对目标进行跟踪的算法．跟踪开始前，为了获得比较准确的目标描述，使用混合高斯模型和期望最大化算法对目标进行分割；跟踪过程中，通过蒙特卡罗方法对目标区域和背景区域进行采样，并更新特征空间参数．得到目标和背景的最优分类面；最后使用粒子滤波器结合最优分类面对目标状态进行预测．通过光照变化的仿真视频和自然场景视频的跟踪实验，验证了文中算法的有效性．-Trac