Sciweavers

2903 search results - page 361 / 581
» The Dark Side of Object Learning: Learning Objects
Sort
View
CVPR
2009
IEEE
16 years 10 months ago
What's It Going to Cost You?: Predicting Effort vs. Informativeness for Multi-Label Image Annotations
Active learning strategies can be useful when manual labeling effort is scarce, as they select the most informative examples to be annotated first. However, for visual category ...
Sudheendra Vijayanarasimhan (University of Texas a...
CVPR
2008
IEEE
16 years 5 months ago
Parameterized Kernel Principal Component Analysis: Theory and applications to supervised and unsupervised image alignment
Parameterized Appearance Models (PAMs) (e.g. eigentracking, active appearance models, morphable models) use Principal Component Analysis (PCA) to model the shape and appearance of...
Fernando De la Torre, Minh Hoai Nguyen
ICCV
2007
IEEE
16 years 5 months ago
Unsupervised Joint Alignment of Complex Images
Many recognition algorithms depend on careful positioning of an object into a canonical pose, so the position of features relative to a fixed coordinate system can be examined. Cu...
Gary B. Huang, Vidit Jain, Erik G. Learned-Miller
ICML
2006
IEEE
16 years 4 months ago
Permutation invariant SVMs
We extend Support Vector Machines to input spaces that are sets by ensuring that the classifier is invariant to permutations of subelements within each input. Such permutations in...
Pannagadatta K. Shivaswamy, Tony Jebara
125
Voted
IROS
2009
IEEE
140views Robotics» more  IROS 2009»
15 years 10 months ago
Transferring embodied concepts between perceptually heterogeneous robots
— This paper explores methods and representations that allow two perceptually heterogeneous robots, each of which represents concepts via grounded properties, to transfer knowled...
Zsolt Kira