Balanced Mixture of Deformable Part Models With Automatic Part Configurations.
IEEE Transactions on Circuits and Systems for Video Technology(2017)
摘要
This paper presents a method to improve the traditional mixture of deformable part models (MDPM) method from the learning perspective. First, an object part configuration learning algorithm based on group sparsity constraint is introduced to automatically discover the object part number, size, and location. The algorithm imposes two additional regularization terms in addition to the standard hinge...
更多查看译文
关键词
Training,Object detection,Feature extraction,Deformable models,Shape,Computational modeling,Standards
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络