Audio visual word spotting
Ming Liu, Ziyou Xiong, et al.
ICASSP 2004
Two results are presented in this paper. First, it is shown that in estimating three-dimensional motion of a rigid planar patch, the eight pure parameters used in [1] and [2] are uniquely determined from the image correspondences of four points, no three collinear, and can be estimated by solving a set of linear equations. The second result concerns the three-view problem. It is proved that given four image point correspondences in three perspective views of a planar patch undergoing general three-dimensional rigid body motion, the number of solutions for the motion parameters is one, as opposed to two [2] when only two perspective views are given. © 1984 IEEE
Ming Liu, Ziyou Xiong, et al.
ICASSP 2004
Milind R. Naphade, Thomas S. Huang
IEEE Transactions on Neural Networks
Zhangyang Wang, Ding Liu, et al.
IJCNN 2017
Shyamsundar Rajaram, Ashutosh Garg, et al.
ECML 2003