PAMI
2008
13 years 8 months ago
2008
This paper develops a theory of frequency domain invariants in computer vision. We derive novel identities using spherical harmonics, which are the angular frequency domain analog ...
PAMI
2008
13 years 8 months ago
2008
We investigate whether dimensionality reduction using a latent generative model is beneficial for the task of weakly supervised scene classification. In detail we are given a set ...
PAMI
2008
13 years 8 months ago
2008
Defocus can be modeled as a diffusion process and represented mathematically using the heat equation, where image blur corresponds to the diffusion of heat. This analogy can be ext...
PAA
2008
13 years 8 months ago
2008
Recently, Automated Multiple View Inspection (AMVI) has been developed for automated defect detection of manufactured objects, and the framework was successfully implemented for ca...
PAA
2008
13 years 8 months ago
2008
Abstract We introduce a system that processes a sequence of images of a front-facing human face and recognises a set of facial expressions. We use an efficient appearance-based fac...
FTCGV
2007
13 years 8 months ago
2007
Matting refers to the problem of accurate foreground estimation in images and video. It is one of the key techniques in many image editing and film production applications, thus ...
MMS
2006
13 years 8 months ago
2006
In content-based image retrieval (CBIR), relevant images are identified based on their similarities to query images. Most CBIR algorithms are hindered by the semantic gap between ...
MMS
2006
13 years 8 months ago
2006
This paper addresses automatic image annotation problem and its application to multi-modal image retrieval. The contribution of our work is three-fold. (1) We propose a probabilis...
MTA
2008
13 years 8 months ago
2008
The problem of content based image retrieval (CBIR) has traditionally been investigated within a framework that emphasises the explicit formulation of a query: users initiate an au...
KAIS
2006
13 years 8 months ago
2006
Generating captions or annotations automatically for still images is a challenging task. Traditionally, techniques involving higher-level (semantic) object detection and complex f...