Sciweavers

342 search results - page 29 / 69
» Learning from Ambiguously Labeled Images
Sort
View
ICCV
2009
IEEE
15 years 1 months ago
Unlabeled data improves word prediction
Labeling image collections is a tedious task, especially when multiple labels have to be chosen for each image. In this paper we introduce a new framework that extends state of ...
Nicolas Loeff, Ali Farhadi, Ian Endres and David A...
CRV
2011
IEEE
305views Robotics» more  CRV 2011»
12 years 8 months ago
Motion Segmentation by Learning Homography Matrices from Motor Signals
—Motion information is an important cue for a robot to separate foreground moving objects from the static background world. Based on the observation that the motion of the backgr...
Changhai Xu, Jingen Liu, Benjamin Kuipers
MCAM
2007
Springer
129views Multimedia» more  MCAM 2007»
14 years 2 months ago
Learning Concepts by Modeling Relationships
Supporting multimedia search has emerged as an important research topic. There are three paradigms on the research spectrum that ranges from the least automatic to the most automat...
Yong Rui, Guo-Jun Qi
CVPR
2010
IEEE
13 years 8 months ago
Label propagation in video sequences
This paper proposes a probabilistic graphical model for the problem of propagating labels in video sequences, also termed the label propagation problem. Given a limited amount of ...
Vijay Badrinarayanan, Fabio Galasso, Roberto Cipol...
DICTA
2007
13 years 10 months ago
The Tower of Knowledge Scheme for Learning in Computer Vision
A scheme, named tower of knowledge (ToK), is proposed for interpreting 3D scenes. The ToK encapsulates causal dependencies between object appearance and functionality. We demonstr...
Maria Petrou, Mai Xu