Sciweavers

594 search results - page 32 / 119
» Using Approximation to Relate Computational Classes over the...
Sort
View
SIBGRAPI
2007
IEEE
14 years 2 months ago
Graph-based Object Tracking Using Structural Pattern Recognition
This paper proposes a model-based methodology for recognizing and tracking objects in digital image sequences. Objects are represented by attributed relational graphs (or ARGs), w...
Ana Beatriz V. Graciano, Roberto Marcondes Cesar J...
CORR
2012
Springer
170views Education» more  CORR 2012»
12 years 4 months ago
What Cannot be Learned with Bethe Approximations
We address the problem of learning the parameters in graphical models when inference is intractable. A common strategy in this case is to replace the partition function with its B...
Uri Heinemann, Amir Globerson
CVIU
2010
89views more  CVIU 2010»
13 years 8 months ago
Spherical approximation for multiple cameras in motion estimation: Its applicability and advantages
Estimating motions of a multi-camera system which may not have overlapping fields of view is generally complex and computationally expensive because of the non-zero offset between...
Jun-Sik Kim, Myung Hwangbo, Takeo Kanade
ECAI
2008
Springer
13 years 10 months ago
Towards Efficient Belief Update for Planning-Based Web Service Composition
At the "functional level", Semantic Web Services (SWS) are described akin to planning operators, with preconditions and effects relative to an ontology; the ontology prov...
Jörg Hoffmann
CVPR
2010
IEEE
14 years 5 months ago
Beyond Trees: MRF Inference via Outer-Planar Decomposition
Maximum a posteriori (MAP) inference in Markov Random Fields (MRFs) is an NP-hard problem, and thus research has focussed on either finding efficiently solvable subclasses (e.g. t...
Dhruv Batra, Andrew Gallagher, Devi Parikh, Tsuhan...