What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Algorithm
- Computer vision
Context-adaptive binary arithmetic coding, Scalable Video Coding, Algorithm, Computer vision and Artificial intelligence are his primary areas of study.
His Context-adaptive binary arithmetic coding study combines topics in areas such as Bitstream, Coding tree unit, Image compression and Computer engineering.
His Scalable Video Coding research includes themes of MPEG-4, Computer hardware, H.262/MPEG-2 Part 2, Real-time computing and Rate–distortion optimization.
His study focuses on the intersection of MPEG-4 and fields such as Computer architecture with connections in the field of Lossy compression and Network Abstraction Layer.
His work carried out in the field of Algorithm brings together such families of science as Entropy and Computer graphics.
His work in the fields of Motion compensation overlaps with other areas such as Data stream and Extension.
His most cited work include:
- Overview of the Scalable Video Coding Extension of the H.264/AVC Standard (3432 citations)
- Rate-constrained coder control and comparison of video coding standards (3164 citations)
- Context-based adaptive binary arithmetic coding in the H.264/AVC video compression standard (1442 citations)
What are the main themes of his work throughout his whole career to date?
Heiko Schwarz mostly deals with Algorithm, Artificial intelligence, Computer vision, Decoding methods and Context-adaptive binary arithmetic coding.
His study in the field of Data compression and Quantization also crosses realms of Data stream.
Heiko Schwarz interconnects Codec, Distortion and Pattern recognition in the investigation of issues within Artificial intelligence.
His Decoding methods research incorporates themes from Entropy and Encoding.
His Context-adaptive binary arithmetic coding research integrates issues from Coding tree unit, Variable-length code, Sub-band coding and Scalable Video Coding.
His studies deal with areas such as Computer architecture, Real-time computing, Computer engineering and Computer hardware as well as Scalable Video Coding.
He most often published in these fields:
- Algorithm (57.27%)
- Artificial intelligence (30.00%)
- Computer vision (25.00%)
What were the highlights of his more recent work (between 2018-2021)?
- Algorithm (57.27%)
- Data compression (16.36%)
- Random access (8.64%)
In recent papers he was focusing on the following fields of study:
Heiko Schwarz spends much of his time researching Algorithm, Data compression, Random access, Quantization and Decoding methods.
His Algorithm research incorporates elements of Artificial neural network and Algorithmic efficiency.
Heiko Schwarz combines subjects such as Image processing, Diffusion filter, Adaptive filter, Average bitrate and Quadtree with his study of Data compression.
His research integrates issues of Bitstream and Residual in his study of Quantization.
His Decoding methods study also includes fields such as
- Lossless compression together with Lossy compression,
- Motion compensation, which have a strong connection to Motion parameter.
In his study, Moving average is inextricably linked to Binary number, which falls within the broad field of Context-adaptive binary arithmetic coding.
Between 2018 and 2021, his most popular works were:
- An Intra Subpartition Coding Mode for VVC (16 citations)
- Intra Picture Prediction for Video Coding with Neural Networks (16 citations)
- DeepCABAC: A Universal Compression Algorithm for Deep Neural Networks (12 citations)
In his most recent research, the most cited papers focused on:
- Algorithm
- Artificial intelligence
- Computer vision
His primary areas of study are Algorithm, Quantization, Random access, Artificial neural network and Data compression.
His work on Decoding methods and Skip mode as part of general Algorithm research is frequently linked to Affine transformation, bridging the gap between disciplines.
His study looks at the relationship between Quantization and topics such as Entropy encoding, which overlap with Thresholding, Template matching and Codec.
His Random access research is multidisciplinary, incorporating perspectives in Algorithmic efficiency and Intra mode.
His Artificial neural network study incorporates themes from Binary number and Context-adaptive binary arithmetic coding.
His work deals with themes such as Transform coding and Distortion, which intersect with Data 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.
