Deep Learning | KAIST MatriX

Tag: Deep Learning

Research Highlight

Imaging with Events: High-resolution High-quality HDR Imaging using Event Cameras

New algorithms have been developed to generate non-blurry, high-resolution, high-quality, and high-dynamic range intensity images using sparse event streams from an event camera, which is a new imaging sensor able to capture visual information with low latency even under extremely low illumination....read more

AI for Cooperative Robots Computer Vision Deep Learning Event Camera KI for Robotics (KIR) Machine Learning Super-resolution Super-resolution with Event Camera

Research Highlight

Development of Machine Reading Framework for Knowledge Base Population

The SWRC (Semantic Web Research Center, led by Prof. Choi) aims to construct and expand its knowledge base through self-machine-learning from unstructured big data (natural language), and to develop a novel technology to further verify the knowledge base....read more

AI Applications Deep Learning Information Extraction KI for Artificial Intelligence Knowledge Base

Research Highlight

Self-Supervised Learning to Distill Hierarchy in High-Dimensional Dynamic Systems

Prof. Han-Lim Choi’s research team has developed a learning framework to control a high-dimensional robotic system that distills underlying hierarchical structure in robot motion data. By learning high-level intentions as well as low-level control actions, the proposed framework enables adaptation of policy learned from a certain task to much more diverse sets of tasks. ...read more

AI for Cooperative Robots Deep Learning High-Dimensional Systems Interpretable AI KI for Robotics Reinforcement Learning Representation Learning Robust Intelligence Under Uncertainty

Research Highlight Top Story

Development of VR Sickness Assessment Deep Network Considering Exceptional Motion for VR Video

Viewing safety is one of the main issues in viewing virtual reality (VR) content. In particular, VR sickness can occur when watching immersive VR content. To deal with viewing safety for VR content, objective assessment of VR sickness is of great importance. In this work, based on a deep generative model, we propose a novel objective VR sickness assessment (VRSA) network to automatically predict VR sickness. The proposed method takes into account motion patterns of VR videos in which exceptional motion is a critical factor inducing excessive VR sickness in human motion perception. The proposed VRSA network consists of two parts, the VR video generator and VR sickness score predictor. For the evaluation of VRSA performance, we performed comprehensive experiments with 360° videos (stimuli), corresponding physiological signals, and subjective questionnaires. We demonstrated that the proposed VRSA achieved a high correlation with human perceptual score for VR sickness....read more

360-degree Video AI Applications Deep Learning Human Perception Image and Video sYstems (IVY) Laboratory KI for Artificial Intelligence Motion Mismatch Objective Assessment Virtual Reality (VR) VR Sickness

Research Highlight

Explainable AI can predict prognosis-specific genotype of brain tumor without invasive biopsy

Professor Bumseok Jeong has developed an explainable artificial intelligence model with high diagnostic performance that predicts the IDH genotype of gliomas; this is crucial in treatment planning and prognosis prediction....read more

Brain Imaging and Neuromodulation Computational Neuroscience Deep Learning KI for Health Science and Technology Laboratory of Computational Affective Neuroscience and Development Neuroimaging and Neuromodulation

Research Highlight

3-D Scene Graph: A Sparse and Semantic Representation of Physical Environments for Intelligent Agents

Professor Jong-Hwan Kim’s research team defined a 3-D scene graph, which represents physical environments in a sparse and semantic way....read more

3-D Scene Graph AI AI Applications ASIT RITL (Robot Intelligent Technology Lab) Deep Learning Environment Model Human Robot Interaction Intelligent Agent KI for Artificial Intelligence Robot Intelligence Scene Graph Scene Understanding

Research Highlight

Decision-Level Fusion Method for Emotion Recognition using Multimodal Emotion Recognition Information

We confirmed which combination of features of multi-modal emotion recognition achieves the highest accuracy....read more

AI Applications Deep Learning Facial Expression Recognition HRI Human Robot Interaction KAIST Institute for Artificial Intelligence

Research Highlight

Research and Development of AI-powered Autonomous Cars in Seoul for Smart Cities

Professor Hyunchul Shim’s automotive driving research team participated in a technology demonstration organized by the Ministry of Land, Infrastructure and Transport, Korea. The event was held on Yeongdong boulevard adjacent to COEX, Seoul on June 17^th. ...read more

Autonomous driving Deep Learning USRG(Unmanned System Research Group)

Research Highlight

Deep learning for accelerated ultrasound imaging

To accelerate US imaging systems, Prof Jong Chul Ye’s team designed a deep learning technique that improved acquisition speed without compromising the image quality....read more

B-mode Deep Learning Hankel matrix multi-line acquisition Ultrasound imaging

Research Highlight

Rapid Detection of Anthrax Spores using Artificial Intelligence and Holographic Microscopy

Combining holography with deep learning enables rapid optical screening of anthrax spores as well as other pathogens....read more

ADD Deep Learning Holography KIHST Optics

Copyright © 2015 KAIST MATRIX. All rights reserved.
291 Daehak-ro Yuseong-gu Daejeon, 34141, Republic of Korea
Partnered with KAIST Breakthroughs and KAIST Compass