Perceptual context in cognitive hierarchies

DOI10.1007/978-3-030-22102-7_16zbMATH Open1444.68208arXiv1801.02270OpenAlexW2964313317MaRDI QIDQ2185477FDOQ2185477

Michael Thielscher, David Rajaratnam, Bernhard Hengst, Claude Sammut, Maurice Pagnucco

Publication date: 4 June 2020

Abstract: Cognition does not only depend on bottom-up sensor feature abstraction, but also relies on contextual information being passed top-down. Context is higher level information that helps to predict belief states at lower levels. The main contribution of this paper is to provide a formalisation of perceptual context and its integration into a new process model for cognitive hierarchies. Several simple instantiations of a cognitive hierarchy are used to illustrate the role of context. Notably, we demonstrate the use context in a novel approach to visually track the pose of rigid objects with just a 2D camera.

Full work available at URL: https://arxiv.org/abs/1801.02270

Recommendations

• scientific article; zbMATH DE number 1755769
• Context, computation, and optimal ROC performance in hierarchical models
• Contextual priming for object detection
• scientific article; zbMATH DE number 1755786
• A variational model for context-driven effects in perception and cognition

Mathematics Subject Classification ID

Cognitive psychology (91E10) Knowledge representation (68T30) Machine vision and scene understanding (68T45)

Cited In (6)

• Title not available (Why is that?)
• Modeling and Using Context
• Modeling and Using Context
• Title not available (Why is that?)
• Title not available (Why is that?)
• The structure of perceptual categories

This page was built for publication: Perceptual context in cognitive hierarchies

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2185477)