A Review on Intelligent Object Perception Methods Combining Knowledge-based Reasoning and Machine Learning
arXiv:1912.11861
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.
References in corpus (10)
- A Review of Relational Machine Learning for Knowledge Graphs
- Gated Graph Sequence Neural Networks
- Deep Learning for Generic Object Detection: A Survey
- A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms
- Visual Relationship Detection with Language Priors
- From Images to Sentences through Scene Description Graphs using Commonsense Reasoning and Knowledge
- Incorporating External Knowledge to Answer Open-Domain Visual Questions with Dynamic Memory Networks
- Scene Graph Generation with External Knowledge and Image Reconstruction
- Don't Just Listen, Use Your Imagination: Leveraging Visual Common Sense for Non-Visual Tasks
- Situation Recognition with Graph Neural Networks