Truncated max-of-convex models
Truncated convex models (TCM) are a special case of pairwise random fields that have been widely used in computer vision. However, by restricting the order of the potentials to be at most two, they fail to capture useful image statistics. We propose a natural generalization of TCM to high-order rand...
Egile Nagusiak: | Pansari, P, Mudigonda, P |
---|---|
Formatua: | Conference item |
Argitaratua: |
Computer Vision Foundation
2017
|
Antzeko izenburuak
-
Truncated max-of-convex models
nork: Mudigonda, P, et al.
Argitaratua: (2017) -
Improved moves for truncated convex models
nork: Kumar, MP, et al.
Argitaratua: (2009) -
Improved moves for truncated convex models
nork: Pawan Kumar, M, et al.
Argitaratua: (2011) -
Optimal submodular extensions for marginal estimation
nork: Pansari, P, et al.
Argitaratua: (2018) -
On hyperspaces of max-plus and max-min convex sets
nork: Bazylevych Lidiya, et al.
Argitaratua: (2017-01-01)