A Review on Intelligent Object Perception Methods Combining Knowledge-based Reasoning and Machine Learning

December 26, 2019 · The Cartographer · 🏛 AAAI Spring Symposium Combining Machine Learning with Knowledge Engineering

"No code URL or promise found in abstract"
"Title-pattern auto-detect: A Review on Intelligent Object Perception Methods Combining Knowledge-based Reasoning and Machine Le"

Evidence collected by the PWNC Scanner

Authors Filippos Gouidis, Alexandros Vassiliades, Theodore Patkos, Antonis Argyros, Nick Bassiliades, Dimitris Plexousakis arXiv ID 1912.11861 Category cs.CV: Computer Vision Cross-listed cs.AI, cs.LG Citations 13 Venue AAAI Spring Symposium Combining Machine Learning with Knowledge Engineering Last Checked 23 hours ago

Abstract

Object perception is a fundamental sub-field of Computer Vision, covering a multitude of individual areas and having contributed high-impact results. While Machine Learning has been traditionally applied to address related problems, recent works also seek ways to integrate knowledge engineering in order to expand the level of intelligence of the visual interpretation of objects, their properties and their relations with their environment. In this paper, we attempt a systematic investigation of how knowledge-based methods contribute to diverse object perception tasks. We review the latest achievements and identify prominent research directions.