Focusing computational visual attention in multi-modal human-robot interaction.
Boris SchauerteGernot A. FinkPublished in: ICMI-MLMI (2010)
Keyphrases
- multi modal
- visual attention
- human robot interaction
- humanoid robot
- saliency map
- eye tracking
- human robot
- eye movements
- visual search
- vision system
- visual attention model
- multi modality
- salient regions
- audio visual
- higher level
- gesture recognition
- pointing gestures
- object based visual attention
- attention mechanism
- biologically inspired
- visual saliency
- robot programming
- human computer interaction
- uni modal
- high dimensional
- computer vision
- service robots
- image quality
- higher order
- spatio temporal