We propose a method for estimating the pose of a human body using its approximate 3D volume (visual hull) obtained in real time from synchronized videos. Our method can cope with ...
In this paper we identify the constraints under which the generally ill-posed problem of the simultaneous recovery of surface shape and its photometric invariants can be rendered ...
In this paper we present a new method for categorizing video sequences capturing different scene classes. This can be seen as a generalization of previous work on scene classifica...
Paritosh Gupta, Sai Sankalp Arrabolu, Mathew Brown...
We present a semi-automatic system that converts conventional video shots to stereoscopic video pairs. The system requires just a few user-scribbles in a sparse set of frames. The...
The human visual system observes and understands a scene/image by making a series of fixations. Every "fixation point" lies inside a particular region of arbitrary shape...
Ajay K. Mishra, Yiannis Aloimonos, Loong Fah Cheon...
This paper introduces an efficient algorithm that reconstructs 3D human poses as well as camera parameters from a small number of 2D point correspondences obtained from uncalibrat...
In this work, we address the problem of building recognition across two camera views with large changes in scales and viewpoints. The main idea is to construct a semantically rich...
We propose a subspace learning algorithm for face recognition by directly optimizing recognition performance scores. Our approach is motivated by the following observations: 1) Di...