Recursive compositional models: representation, learning, and inference
Recursive compositional models (RCMs) are hierarchical models which enable us to represent the shape/geometry and visual appearance of objects and images at different scales. The key design principle is recursive compositionality. Objects are represented by RCMs in a hierarchical form where complex...
Main Authors: | Yuille, Alan (Author), Zhu, Long (Contributor) |
---|---|
Other Authors: | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory (Contributor) |
Format: | Article |
Language: | English |
Published: |
Institute of Electrical and Electronics Engineers,
2010-11-12T18:39:10Z.
|
Subjects: | |
Online Access: | Get fulltext |
Similar Items
-
Part and appearance sharing: Recursive compositional models for multi-view multi-object detection
by: Zhu, Long, et al.
Published: (2012) -
Recursive FMP for distributed inference in Gaussian graphical models
by: Liu, Ying, et al.
Published: (2014) -
Type Inference for Bimorphic Recursion
by: Makoto Tatsuta, et al.
Published: (2011-06-01) -
Recursive Variational Bayesian Inference to Simultaneous Registration and Fusion
by: Hao Zhu, et al.
Published: (2016-06-01) -
Learning a Hierarchical Deformable Template for Rapid Deformable Object Parsing
by: Long, Zhu, et al.
Published: (2010)