Probabilistic reasoning in intelligent systems: networks of plausible inference
Probabilistic reasoning in intelligent systems: networks of plausible inference
A Model of Saliency-Based Visual Attention for Rapid Scene Analysis
IEEE Transactions on Pattern Analysis and Machine Intelligence
An Introduction to Natural Computation
An Introduction to Natural Computation
Adaptive Behavior
Vision: A Computational Investigation into the Human Representation and Processing of Visual Information
Causal saliency effects during natural vision
Proceedings of the 2006 symposium on Eye tracking research & applications
Active Exploration Using Bayesian Models for Multimodal Perception
ICIAR '08 Proceedings of the 5th international conference on Image Analysis and Recognition
Comparing active vision models
Image and Vision Computing
Probabilistic Reasoning and Decision Making in Sensory-Motor Systems
Probabilistic Reasoning and Decision Making in Sensory-Motor Systems
Bayesian models of eye movement selection with retinotopic maps
Biological Cybernetics
Implementation and calibration of a Bayesian binaural system for 3D localisation
ROBIO '09 Proceedings of the 2008 IEEE International Conference on Robotics and Biomimetics
Operations for learning with graphical models
Journal of Artificial Intelligence Research
Bayesian real-time perception algorithms on GPU
Journal of Real-Time Image Processing
Active vision for sociable robots
IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans
Learning-based modeling of multimodal behaviors for humanlike robots
Proceedings of the 2014 ACM/IEEE international conference on Human-robot interaction
Hi-index | 0.00 |
In this article, we present a hierarchical Bayesian framework for multimodal active perception, devised to be emergent, scalable and adaptive. This framework, while not strictly neuromimetic, finds its roots in the role of the dorsal perceptual pathway of the human brain. Its composing models build upon a common spatial configuration that is naturally fitting for the integration of readings from multiple sensors using a Bayesian approach devised in previous work. The framework presented in this article is shown to adequately model human-like active perception behaviours, namely by exhibiting the following desirable properties: high-level behaviour results from low-level interaction of simpler building blocks; seamless integration of additional inputs is allowed by the Bayesian Programming formalism; initial 'genetic imprint' of distribution parameters may be changed 'on the fly' through parameter manipulation, thus allowing for the implementation of goal-dependent behaviours (i.e. top-down influences).