What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Computer vision
- Algorithm
His main research concerns Artificial intelligence, Computer vision, Data compression, Pattern recognition and Scalable Video Coding.
His study explores the link between Artificial intelligence and topics such as Macroblock that cross with problems in Rate–distortion optimization.
Computer vision is a component of his Motion compensation, Quarter-pixel motion, Motion estimation, Image processing and Pixel studies.
Feng Wu combines subjects such as Codec and Lossy compression with his study of Data compression.
His Scalable Video Coding study integrates concerns from other disciplines, such as Multiview Video Coding, Reference frame, Real-time computing, Bitstream and Computer network.
His studies deal with areas such as Coding tree unit, Distributed source coding and Context-adaptive binary arithmetic coding as well as Multiview Video Coding.
His most cited work include:
- Compressive data gathering for large-scale wireless sensor networks (501 citations)
- Efficient Parallel Framework for HEVC Motion Estimation on Many-Core Processors (344 citations)
- Background Prior-Based Salient Object Detection via Deep Reconstruction Residual (329 citations)
What are the main themes of his work throughout his whole career to date?
His primary areas of study are Artificial intelligence, Computer vision, Algorithm, Pattern recognition and Decoding methods.
His Artificial intelligence research focuses on Data compression, Motion compensation, Iterative reconstruction, Pixel and Image resolution.
He has researched Motion compensation in several fields, including Motion vector, Reference frame and Block-matching algorithm.
Image compression, Motion estimation, Transform coding, Image processing and Wavelet transform are subfields of Computer vision in which his conducts study.
Feng Wu has included themes like Multiview Video Coding, Scalable Video Coding and Sub-band coding in his Coding tree unit study.
His work in Scalable Video Coding addresses issues such as Real-time computing, which are connected to fields such as Computer network.
He most often published in these fields:
- Artificial intelligence (59.47%)
- Computer vision (42.41%)
- Algorithm (24.73%)
What were the highlights of his more recent work (between 2017-2021)?
- Artificial intelligence (59.47%)
- Pattern recognition (16.90%)
- Computer vision (42.41%)
In recent papers he was focusing on the following fields of study:
Artificial intelligence, Pattern recognition, Computer vision, Convolutional neural network and Algorithm are his primary areas of study.
His Pattern recognition research includes themes of Face and Feature.
His Upsampling, Motion compensation and Superresolution study, which is part of a larger body of work in Computer vision, is frequently linked to Process, bridging the gap between disciplines.
His Motion compensation course of study focuses on Motion estimation and Reference frame.
His Convolutional neural network research also works with subjects such as
- Pixel and related Interpolation,
- Image compression which intersects with area such as Wavelet.
His Algorithm study integrates concerns from other disciplines, such as Motion vector and Discrete cosine transform.
Between 2017 and 2021, his most popular works were:
- An Iterative BP-CNN Architecture for Channel Decoding (121 citations)
- Towards Optimal Power Control via Ensembling Deep Neural Networks (75 citations)
- Convolutional Neural Network-Based Block Up-Sampling for Intra Frame Coding (68 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Computer vision
- Algorithm
Feng Wu focuses on Artificial intelligence, Convolutional neural network, Computer vision, Pattern recognition and Algorithm.
His Artificial intelligence study frequently draws connections between related disciplines such as Natural language processing.
Feng Wu has included themes like JPEG, Filter, Pixel, Deep learning and Image compression in his Convolutional neural network study.
His work in the fields of Depth map and Image translation overlaps with other areas such as Process, Thermal and Invariant.
In his study, Image quality, Ringing and Lossy compression is inextricably linked to Coding gain, which falls within the broad field of Pattern recognition.
The Algorithm study combines topics in areas such as Interpolation, Theoretical computer science, Algorithmic efficiency and Discrete cosine transform.
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.
