A block based video coder that supports multiple motion models is proposed. Apart from the typical translational motion model, we employ parametric models to more accurately repre...
Haricharan Lakshman, Heiko Schwarz, Thomas Wiegand
We offer, in this paper, a new method to segment text in natural scenes. This method is based on the use of a morphological operator: the Toggle Mapping. The efficiency of the met...
Jonathan Fabrizio, Beatriz Marcotegui, Matthieu Co...
We propose a game-theory-based cross-layer optimization scheme for wireless Direct Sequence Code Division Multiple Access (DSCDMA) visual sensor networks. The scheme uses the Nash...
Conventional approaches to automatic image annotation usually suffer from two problems: (1) They cannot guarantee a good semantic coherence of the annotated words for each image, ...
Tao Mei, Yong Wang, Xian-Sheng Hua, Shaogang Gong,...
Spatial, temporal and spatio-temporal aggregates over continuous streams of remotely sensed image data build a fundamental operation in many applications in the environmental scie...