Sciweavers

23 search results - page 2 / 5
» Simulation and weights of multiple cues for robust object re...
Sort
View
ECCV
2002
Springer
14 years 7 months ago
Probabilistic and Voting Approaches to Cue Integration for Figure-Ground Segmentation
This paper describes techniques for fusing the output of multiple cues to robustly and accurately segment foreground objects from the background in image sequences. Two different m...
Eric Hayman, Jan-Olof Eklundh
CIVR
2008
Springer
279views Image Analysis» more  CIVR 2008»
13 years 7 months ago
Semi-supervised learning of object categories from paired local features
This paper presents a semi-supervised learning (SSL) approach to find similarities of images using statistics of local matches. SSL algorithms are well known for leveraging a larg...
Wen Wu, Jie Yang
CVPR
2004
IEEE
14 years 7 months ago
Cue Integration through Discriminative Accumulation
Object recognition systems aiming to work in real world settings should use multiple cues in order to achieve robustness. We present a new cue integration scheme which extends the...
Maria-Elena Nilsback, Barbara Caputo
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
ICASSP
2011
IEEE
12 years 9 months ago
Robust video object tracking based on multiple kernels with projected gradients
In kernel-based video object tracking, the use of single kernel often suffers from the occlusion. In order to provide more robust tracking performance, multiple inter-related kern...
Chun-Te Chu, Jenq-Neng Hwang, Hung-I. Pai, Kung-Mi...