Sciweavers

19 search results - page 3 / 4
» Efficient video text recognition using multiple frame integr...
Sort
View
CVPR
2010
IEEE
14 years 1 months ago
Figure-Ground Segmentation Improves Handled Object Recognition in Egocentric Video
Identifying handled objects, i.e. objects being manipulated by a user, is essential for recognizing the person’s activities. An egocentric camera as worn on the body enjoys many...
Xiaofeng Ren, Chunhui Gu
CVPR
2004
IEEE
14 years 7 months ago
Probabilistic Identity Characterization for Face Recognition
We present a general framework for characterizing the object identity in a single image or a group of images with each image containing a transformed version of the object, with a...
Shaohua Kevin Zhou, Rama Chellappa
MM
2010
ACM
126views Multimedia» more  MM 2010»
13 years 5 months ago
Restoration of out-of-focus lecture video by automatic slide matching
Restoring the fine detail in the slide area of a defocused lecture video is a challenging task. In this work, we propose to use clean images of slides available along with the def...
Ngai-Man Cheung, David M. Chen, Vijay Chandrasekha...
CVPR
2006
IEEE
14 years 7 months ago
Robust Fragments-based Tracking using the Integral Histogram
We present a novel algorithm (which we call "FragTrack") for tracking an object in a video sequence. The template object is represented by multiple image fragments or pa...
Amit Adam, Ehud Rivlin, Ilan Shimshoni
CVPR
2009
IEEE
13 years 9 months ago
"Who are you?" - Learning person specific classifiers from video
We investigate the problem of automatically labelling faces of characters in TV or movie material with their names, using only weak supervision from automaticallyaligned subtitle ...
Josef Sivic, Mark Everingham, Andrew Zisserman