12943 search results - page 2319 / 2589 » Predicting When Not to Predict |
213
click to vote
CVPR
2011
IEEE
15 years 3 months ago
2011
IEEE
Many successful models for predicting attention in a scene involve three main steps: convolution with a set of filters, a center-surround mechanism and spatial pooling to constru...
203
click to vote
CVPR
2011
IEEE
15 years 3 months ago
2011
IEEE
We propose a novel approach for ranking and retrieval of images based on multi-attribute queries. Existing image retrieval methods train separate classifiers for each word and he...
186
click to vote
CVPR
2011
IEEE
15 years 3 months ago
2011
IEEE
We present a novel theory for characterizing defocus blurs in multi-perspective cameras such as catadioptric mirrors. Our approach studies how multi-perspective ray geometry trans...
197
click to vote
CVPR
2011
IEEE
15 years 2 months ago
2011
IEEE
Human saccade is a dynamic process of information pursuit. Based on the principle of information maximization, we propose a computational model to simulate human saccadic scanpath...
222
click to vote
CVPR
2011
IEEE
15 years 2 months ago
2011
IEEE
While most existing enhancement tools for photographs have universal auto-enhancement functionality, recent research [8] shows that users can have personalized preferences. In thi...