Sciweavers

5101 search results - page 872 / 1021
» Capturing Context Requirements
Sort
View
CVPR
2008
IEEE
14 years 10 months ago
ANSIG - An analytic signature for permutation-invariant two-dimensional shape representation
Many applications require a computer representation of 2D shape, usually described by a set of 2D points. The challenge of this representation is that it must not only capture the...
José J. Rodrigues, Pedro M. Q. Aguiar, Jo&a...
CVPR
2008
IEEE
14 years 10 months ago
Geo-located image analysis using latent representations
Image categorization is undoubtedly one of the most challenging open problems faced in Computer Vision, far from being solved by employing pure visual cues. Recently, additional t...
Marco Cristani, Alessandro Perina, Umberto Castell...
CVPR
2008
IEEE
14 years 10 months ago
Principled fusion of high-level model and low-level cues for motion segmentation
High-level generative models provide elegant descriptions of videos and are commonly used as the inference framework in many unsupervised motion segmentation schemes. However, app...
Arasanathan Thayananthan, Masahiro Iwasaki, Robert...
ECCV
2008
Springer
14 years 10 months ago
Cross-View Action Recognition from Temporal Self-similarities
This paper concerns recognition of human actions under view changes. We explore self-similarities of action sequences over time and observe the striking stability of such measures ...
Imran N. Junejo, Emilie Dexter, Ivan Laptev, Patri...
ECCV
2008
Springer
14 years 10 months ago
Unified Crowd Segmentation
Abstract. This paper presents a unified approach to crowd segmentation. A global solution is generated using an Expectation Maximization framework. Initially, a head and shoulder d...
Gianfranco Doretto, Jens Rittscher, Nils Krahnstoe...