Cognitive Computing of Visual and Auditory Information (Reports of China’s Basic Research)

Reports of China’s Basic Research Editorial Board
	Editor-in-Chief
	Associate Editors
	Editors
Preface to the Series
Preface
	Embracing the New Era of Artificial Intelligence
Contributors
Contents
1 Program Overview
	1.1 Program Introduction
	1.2 Overall Scientific Objectives
	1.3 Core Scientific Issues
	1.4 Program Layout
	1.5 Comprehensive Integration
	1.6 Situation of Interaction Between Disciplines
	1.7 Significant Progress
2 “Cognitive Computing of Visual and Auditory Information”: State of the Art
	2.1 Research Status
	2.2 Development Tendency
		2.2.1 Cognitive Computing Theories and Methods for Visual and Auditory Information Based on Neuromorphic Computing
		2.2.2 Enhancing Perception of Visual and Auditory Information in Cognitive Computing Systems
		2.2.3 Improved Ability of Discovering Knowledge in Big Data
		2.2.4 Enhanced Ability of Natural Language Comprehension
		2.2.5 Man-in-the-Loop, Human–Computer Cooperation and Hybrid Augmented Intelligence
		2.2.6 Development of More Powerful and Reliable Autonomous Smart Cars (Robots)
		2.2.7 Study of Driving Brain with Selective Attention Memory Mechanism
		2.2.8 Theoretical Capabilities and Limitations of Cognitive Computing for Visual and Auditory Information
		2.2.9 Advances in Hardware Architecture Design for Cognitive Computing of Visual and Auditory Information
	2.3 Trend of Field Development
3 Major Research Achievements
	3.1 Leaping Development of Basic Theories of Cognitive Computing
		3.1.1 Creation and Development of “Global-First” Object-Based Attention Theory
		3.1.2 Research on Visual Computing Models and Methods Inspired by Biological Cognitive Mechanism and Characteristics
	3.2 Breakthroughs in Key Technologies of the Brain-Computer Interface
		3.2.1 Research on Key Technologies and Applications of the Bidirectional Multidimensional Brain-Computer Interface
		3.2.2 Research on Theory and Key Technology of Intuitive Bionic Manipulation of Intelligent Prostheses Based on the Brain-Computer Interface
	3.3 Breakthroughs in Visual Information Processing
		3.3.1 Statistical Learning Method for Visual Attention Based on Scene Understanding
		3.3.2 Supporting the Recognition and Understanding of Traffic Signs for Driverless Vehicles
		3.3.3 Graphics and Text Detection, Recognition and Under-Standing of Traffi Signs Under Complex Conditions
	3.4 Leaping Development of Natural Language Processing
		3.4.1 Research on Semantic Calculation Methods for Chinese Text Comprehension
		3.4.2 Theoretical and Methodological Research on Integration Between Human-Like Hearing Mechanism and Deep Learning
		3.4.3 Research on Theory and Technology of Speech Separation, Content Analysis and Understanding in Multi-person and Multi-party Dialogue
	3.5 Breakthroughs in Theory and Technology Research of Multi-modal Information Processing
	3.6 Breakthroughs in Key Technology and Platform of Autonomous Vehicles
		3.6.1 Theory, Method and Integration and Comprehensive Experimental Platform of Autonomous Vehicle
		3.6.2 Key Technology Integration and Comprehensive Verification Platform for Driverless Vehicles Based on Visual and Auditory Cognitive Mechanism
		3.6.3 Intelligent Test Evaluation and Environment Design of Driverless Vehicles
4 Outlook
	4.1 Deficiencies and Strategic Needs
		4.1.1 Deficiencies Needs
		4.1.2 Strategic Needs
	4.2 Ideas and Suggestions for In-Depth Study
		4.2.1 The Ideas of In-Depth Research
		4.2.2 Suggestions for the Next Step
References
Index