Pose pooling kernels for sub-category recognition
CVPR(2012)
摘要
The ability to normalize pose based on super-category landmarks can significantly improve models of individual categories when training data are limited. Previous methods have considered the use of volumetric or morphable models for faces and for certain classes of articulated objects. We consider methods which impose fewer representational assumptions on categories of interest, and exploit contemporary detection schemes which consider the ensemble of responses of detectors trained for specific posekeypoint configurations. We develop representations for poselet-based pose normalization using both explicit warping and implicit pooling as mechanisms. Our method defines a pose normalized similarity or kernel function that is suitable for nearest-neighbor or kernel-based learning methods.
更多查看译文
关键词
morphable model,individual category,contemporary detection scheme,previous method,kernel function,certain class,articulated object,normalized similarity,sub-category recognition,fewer representational assumption,explicit warping,pose estimation,vectors,kernel,learning artificial intelligence,feature extraction,face recognition,head,training data,detectors
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络