机译:辨别性的双层特征选择,实现现实人体行动识别
South China University of Technology Guangzhou 510640 China The University of Sydney NSW 2006 Australia;
The University of Sydney NSW 2006 Australia;
South China University of Technology Guangzhou 510640 China;
The University of Sydney NSW 2006 Australia;
South China University of Technology Guangzhou 510640 China;
The University of Sydney NSW 2006 Australia;
Realistic human action recognition; Visual saliency; Space-time interest points; Unsupervised codeword selection; Maximal information compression index; Bag-of-features model; Saliency map; Support vector machine;
机译:区分性两级特征选择,可实现逼真的人体动作识别
机译:区分性两级特征选择,可实现逼真的人体动作识别
机译:辨别性的双层特征选择,实现现实人体行动识别
机译:图嵌入在人类动作识别中的区别性原型选择方法
机译:使用遗传算法进行人的步态识别的特征选择。
机译:使用COTS Wi-Fi设备的CSI进行高阶特征提取和选择以实现可靠的手势识别
机译:通过多模式特征选择和融合实现逼真的人类动作识别