We consider the problem of computing the likelihood of a gesture from regular, unaided video sequences, without relying on perfect segmentation of the scene. Instead of requiring ...
Abstract. In this work, we present an approach to jointly segment a rigid object in a two-dimensional (2D) image and estimate its three-dimensional (3D) pose, using the knowledge o...
Samuel Dambreville, Romeil Sandhu, Anthony J. Yezz...
Problem of segmenting individual humans in crowded situations from stationary video camera sequences is exacerbated by object inter-occlusion. We pose this problem as a “model-b...
This work proposes a biologically inspired approach to integrate latent topic model with saliency detection. Firstly, a saliency detection algorithm is presented to discriminate s...
Zhidong Li, Yang Wang, Jing Chen, Jie Xu, John Lai...
This paper proposes a real-time, robust and effective tracking framework for visual servoing applications. The algorithm is based on the fusion of visual cues and on the estimatio...