Sciweavers

41 search results - page 7 / 9
» Improved semantic region labeling based on scene context
Sort
View
ETRA
2008
ACM
235views Biometrics» more  ETRA 2008»
13 years 9 months ago
Using semantic content as cues for better scanpath prediction
Under natural viewing conditions, human observers use shifts in gaze to allocate processing resources to subsets of the visual input. There are many computational models that try ...
Moran Cerf, E. Paxon Frady, Christof Koch
MM
2006
ACM
157views Multimedia» more  MM 2006»
14 years 1 months ago
Player action recognition in broadcast tennis video with applications to semantic analysis of sports game
Recognition of player actions in broadcast sports video is a challenging task due to low resolution of the players in video frames. In this paper, we present a novel method to rec...
Guangyu Zhu, Changsheng Xu, Qingming Huang, Wen Ga...
MIA
2010
104views more  MIA 2010»
13 years 2 months ago
Combining atlas based segmentation and intensity classification with nearest neighbor transform and accuracy weighted vote
In this paper, different methods to improve atlas based segmentation are presented. The first technique is a new mapping of the labels of an atlas consistent with a given intensit...
Michaël Sdika
ICPR
2010
IEEE
13 years 5 months ago
Unsupervised Image Retrieval with Similar Lighting Conditions
In this work a new method to retrieve images with similar lighting conditions is presented. It is based on automatic clustering and automatic indexing. Our proposal belongs to Con...
J. Felix Serrano, Carlos Avilés, Humberto S...
ECCV
2006
Springer
14 years 9 months ago
Figure/Ground Assignment in Natural Images
Abstract. Figure/ground assignment is a key step in perceptual organization which assigns contours to one of the two abutting regions, providing information about occlusion and all...
Xiaofeng Ren, Charless Fowlkes, Jitendra Malik