Dynamic Markov random fields for stochastic modeling of visual attention.
Akisato KimuraDerek PangTatsuto TakeuchiJunji YamatoKunio KashinoPublished in: ICPR (2008)
Keyphrases
- markov random field
- visual attention
- saliency map
- higher order
- eye tracking
- eye movements
- random fields
- vision system
- graph cuts
- visual search
- energy minimization
- natural scenes
- visual attention model
- belief propagation
- energy function
- maximum a posteriori
- parameter estimation
- image segmentation
- potential functions
- mrf model
- visual saliency
- pairwise
- higher level
- image restoration
- textured images
- low level vision
- salient regions
- attention mechanism
- conditional random fields
- human computer interaction
- bit rate
- natural images
- software engineering
- prior models
- map inference
- user interface
- discriminative random fields