What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Computer network
- Computer vision
His primary areas of investigation include Artificial intelligence, Multiview Video Coding, Scalable Video Coding, Computer vision and Data compression.
Thomas Wiegand has included themes like MPEG-4, Computer hardware, H.262/MPEG-2 Part 2, Real-time computing and Context-adaptive binary arithmetic coding in his Scalable Video Coding study.
He combines subjects such as IPTV, Multimedia, Computer architecture and MPEG-2 with his study of MPEG-4.
His work in Context-adaptive binary arithmetic coding tackles topics such as Rate–distortion optimization which are related to areas like Flexible Macroblock Ordering.
His Computer vision research includes themes of Signal and Computer graphics.
His research investigates the connection between Data compression and topics such as Image compression that intersect with issues in Network Abstraction Layer.
His most cited work include:
- Overview of the H.264/AVC video coding standard (7320 citations)
- Overview of the High Efficiency Video Coding (HEVC) Standard (5050 citations)
- Overview of the Scalable Video Coding Extension of the H.264/AVC Standard (3432 citations)
What are the main themes of his work throughout his whole career to date?
The scientist’s investigation covers issues in Algorithm, Artificial intelligence, Computer vision, Coding and Scalable Video Coding.
His Algorithm research is multidisciplinary, incorporating elements of Data stream and Encoder.
His Artificial intelligence research incorporates themes from Codec, Coding tree unit and Pattern recognition.
His work on Algorithmic efficiency as part of general Coding study is frequently linked to Subdivision, therefore connecting diverse disciplines of science.
His work deals with themes such as Computer network, Network packet, Multimedia, Real-time computing and Video quality, which intersect with Scalable Video Coding.
His Multiview Video Coding research focuses on Video compression picture types and how it connects with Uncompressed video.
He most often published in these fields:
- Algorithm (39.85%)
- Artificial intelligence (36.24%)
- Computer vision (28.65%)
What were the highlights of his more recent work (between 2016-2021)?
- Algorithm (39.85%)
- Coding (27.51%)
- Decoding methods (17.65%)
In recent papers he was focusing on the following fields of study:
His main research concerns Algorithm, Coding, Decoding methods, Artificial intelligence and Encoder.
His Algorithm research is multidisciplinary, incorporating perspectives in Data stream and Algorithmic efficiency.
His Coding research is multidisciplinary, relying on both Codec, Computer engineering, Residual and Random access.
The various areas that Thomas Wiegand examines in his Artificial intelligence study include Machine learning, Distortion, Computer vision and Pattern recognition.
His Data compression research incorporates elements of Artificial neural network, Adaptive filter, Diffusion filter and Image processing.
The Artificial neural network study which covers Context-adaptive binary arithmetic coding that intersects with Binary number.
Between 2016 and 2021, his most popular works were:
- Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessment (328 citations)
- Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models (286 citations)
- A Haar Wavelet-Based Perceptual Similarity Index for Image Quality Assessment (106 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Computer network
- Algorithm
Thomas Wiegand spends much of his time researching Artificial intelligence, Algorithm, Coding, Pattern recognition and Image quality.
Thomas Wiegand has researched Artificial intelligence in several fields, including Machine learning, Distortion and Computer vision.
Quantization, Decoding methods and Data compression are the core of his Algorithm study.
His Coding research integrates issues from Encoder, Wiener filter, Geometric transformation and Image pattern.
His work carried out in the field of Artificial neural network brings together such families of science as Frequency domain, Distributed computing, Binary number and Context-adaptive binary arithmetic coding.
The concepts of his Context-adaptive binary arithmetic coding study are interwoven with issues in Bitstream and Lossless compression.
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.
