Sciweavers

10 search results - page 1 / 2
» Predicting human gaze using low-level saliency combined with...
Sort
View
NIPS
2007
13 years 9 months ago
Predicting human gaze using low-level saliency combined with face detection
Under natural viewing conditions, human observers shift their gaze to allocate processing resources to subsets of the visual input. Many computational models try to predict such v...
Moran Cerf, Jonathan Harel, Wolfgang Einhäuse...
WACV
2012
IEEE
12 years 3 months ago
Predicting human gaze using quaternion DCT image signature saliency and face detection
We combine and extend the previous work on DCT-based image signatures and face detection to determine the visual saliency. To this end, we transfer the scalar definition of image...
Boris Schauerte, Rainer Stiefelhagen
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
ICIP
2007
IEEE
14 years 9 months ago
Finding Regions of Interest in Home Videos Based on Camera Motion
In this paper, we propose an algorithm for identifying regions of interest (ROIs) in video, particularly for the keyframes extracted from a home video. The camera motion is introd...
Golnaz Abdollahian, Edward J. Delp
NIPS
2007
13 years 9 months ago
Congruence between model and human attention reveals unique signatures of critical visual events
Current computational models of bottom-up and top-down components of attention are predictive of eye movements across a range of stimuli and of simple, fixed visual tasks (such a...
Robert J. Peters, Laurent Itti