PAMI
2008
14 years 1 months ago
2008
Traditional stereo matching algorithms are limited in their ability to produce accurate results near depth discontinuities, due to partial occlusions and violation of smoothness co...
PAMI
2008
14 years 1 months ago
2008
Detecting different categories of objects in image and video content is one of the fundamental tasks in computer vision research. The success of many applications such as visual s...
PAMI
2008
14 years 1 months ago
2008
Little attention has been paid so far to physiological signals for emotion recognition compared to audiovisual emotion channels such as facial expression or speech. This paper inve...
PAMI
2008
14 years 1 months ago
2008
Mutual Information (MI) is popular for registration via function optimization. This work proposes an inverse compositional formulation of MI for Levenberg-Marquardt optimization. T...
PAMI
2008
14 years 1 months ago
2008
This paper addresses the problem of visual tracking under very general conditions: a possibly nonrigid target whose appearance may drastically change over time, general camera moti...
PAMI
2008
14 years 1 months ago
2008
This paper proposes a novel graph matching algorithm and applies it to shape recognition based on object silhouettes. The main idea is to match skeleton graphs by comparing the geo...
PAMI
2008
14 years 1 months ago
2008
Behavior analysis of social insects has garnered impetus in recent years and has led to some advances in fields like control systems, flight navigation etc. Manual labeling of ins...
PAMI
2008
14 years 1 months ago
2008
Abstract-Similarity searching often reduces to finding the k nearest neighbors to a query object. Finding the k nearest neighbors is achieved by applying either a depth-first or a ...
PAMI
2008
14 years 1 months ago
2008
In this paper, we develop a new effective multiple kernel learning algorithm. First, we map the input data into m different feature spaces by m empirical kernels, where each genera...
PAMI
2008
14 years 1 months ago
2008
Recently, manifold learning has been widely exploited in pattern recognition, data analysis, and machine learning. This paper presents a novel framework, called Riemannian manifold...