ACCV
2006
Springer
13 years 10 months ago
2006
Springer
ACCV
2006
Springer
13 years 10 months ago
2006
Springer
Relevance feedback (RF) and region-based image retrieval (RBIR) are two widely used methods to enhance the performance of contentbased image retrieval (CBIR) systems. In this paper...
ACCV
2006
Springer
13 years 10 months ago
2006
Springer
We consider the task of computing the pose of an object relative to a camera, for the case where the camera has no direct view of the object. This problem was encountered in work o...
ACCV
2006
Springer
13 years 10 months ago
2006
Springer
This paper presents a practical method for hypothesizing hand locations and subsequently recognizing a discrete number of poses in image sequences. In a typical setting the user is...
ACCV
2006
Springer
13 years 10 months ago
2006
Springer
Abstract. To develop statistical models for shapes, we utilize an elastic string representation where curves (denoting shapes) can bend and locally stretch (or compress) to optimal...
ACCV
2006
Springer
13 years 10 months ago
2006
Springer
We present a bottom up algebraic approach for segmenting multiple 2D motion models directly from the partial derivatives of an image sequence. Our method fits a polynomial called ...
ACCV
2006
Springer
13 years 10 months ago
2006
Springer
In this paper, we propose a new method for face recognition under varying illumination conditions using a single input image. Our method is based on a statistical shape-from-shadin...
ACCV
2006
Springer
13 years 10 months ago
2006
Springer
Segmenting an image into semantically meaningful parts is a fundamental and challenging task in computer vision. Automatic methods are able to segment an image into coherent region...
ACCV
2006
Springer
13 years 10 months ago
2006
Springer
Abstract. We propose an efficient way to account for spatial smoothness in foreground-background segmentation of video sequences. Most statistical background modeling techniques re...
ACCV
2006
Springer
13 years 10 months ago
2006
Springer
This paper describes a new method to track people walking by matching their gait image sequences in the frequency domain. When a person walks at a distance from a camera, that pers...