What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Telecommunications
- Statistics
Jungwon Lee mostly deals with Algorithm, Decoding methods, Communication channel, Very-long-baseline interferometry and Electronic engineering.
In his research, Encoding and Data stream is intimately related to Encoder, which falls under the overarching field of Algorithm.
His Decoding methods research includes themes of Hybrid automatic repeat request, Real-time computing, Coding and Polar.
His Communication channel course of study focuses on Modulation and Computer network, Fading, Additive white Gaussian noise, Single-pair high-speed digital subscriber line and Transmitter power output.
His studies deal with areas such as Astrometry, Remote sensing and Optics, Interferometry as well as Very-long-baseline interferometry.
His Electronic engineering study combines topics in areas such as Precoding, Signal-to-noise ratio, Matrix decomposition, Orthogonal frequency-division multiplexing and Transceiver.
His most cited work include:
- Display screen or portion thereof with transitional graphical user interface (200 citations)
- Fused DNN: A Deep Neural Network Fusion Approach to Fast and Robust Pedestrian Detection (185 citations)
- A game-theoretic approach to power allocation in frequency-selective gaussian interference channels (161 citations)
What are the main themes of his work throughout his whole career to date?
Jungwon Lee mainly focuses on Electronic engineering, Algorithm, Artificial intelligence, Communication channel and Signal.
His studies in Electronic engineering integrate themes in fields like Interference, Transmission, Orthogonal frequency-division multiplexing, Communications system and Transmitter.
As part of his studies on Algorithm, he often connects relevant areas like Theoretical computer science.
His Artificial intelligence research is multidisciplinary, incorporating elements of Computer vision and Pattern recognition.
His research on Communication channel concerns the broader Telecommunications.
The Decoding methods study combines topics in areas such as Detector, Hybrid automatic repeat request, MIMO, Real-time computing and Polar.
He most often published in these fields:
- Electronic engineering (25.34%)
- Algorithm (23.97%)
- Artificial intelligence (18.49%)
What were the highlights of his more recent work (between 2018-2021)?
- Artificial intelligence (18.49%)
- Computer vision (11.19%)
- Image (7.08%)
In recent papers he was focusing on the following fields of study:
Jungwon Lee mainly investigates Artificial intelligence, Computer vision, Image, Pattern recognition and Artificial neural network.
His work in Artificial intelligence tackles topics such as Residual which are related to areas like Adversarial system and Data mining.
In the subject of general Computer vision, his work in Field of view, Motion compensation and Superresolution is often linked to Merge, thereby combining diverse domains of study.
His research in Pattern recognition focuses on subjects like Image resolution, which are connected to Discriminative model and Cascade.
His Artificial neural network research integrates issues from Depth map, Single image, Speech enhancement, Kernel and Algorithm.
The Algorithm study which covers DUAL that intersects with Convolution.
Between 2018 and 2021, his most popular works were:
- Variable Rate Deep Image Compression With a Conditional Autoencoder (35 citations)
- NTIRE 2020 Challenge on Real-World Image Super-Resolution: Methods and Results (33 citations)
- T-GSA: Transformer with Gaussian-Weighted Self-Attention for Speech Enhancement (32 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Statistics
- Telecommunications
Jungwon Lee focuses on Artificial intelligence, Artificial neural network, Computer vision, Pattern recognition and Image.
The various areas that he examines in his Artificial intelligence study include Encoder and Residual.
Jungwon Lee interconnects Algorithm and Speech enhancement in the investigation of issues within Artificial neural network.
His work on Vector quantization as part of general Algorithm study is frequently linked to Compression ratio, therefore connecting diverse disciplines of science.
The study incorporates disciplines such as Autoencoder, Quantization, Codec and Image compression, JPEG 2000 in addition to Pattern recognition.
In general Image study, his work on Image processing often relates to the realm of Set, thereby connecting several areas of interest.
This overview was generated by a machine learning system which analysed the scientist’s
body of work. If you have any feedback, you can
contact us
here.
