What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Computer vision
- Algorithm
Artificial intelligence, Algorithm, Digital watermarking, Computer vision and Pattern recognition are his primary areas of study.
His studies deal with areas such as Image quality, Theoretical computer science, Discrete cosine transform, Information hiding and Steganography as well as Algorithm.
His Discrete cosine transform study deals with JPEG intersecting with Steganalysis.
As a part of the same scientific study, Yun Q. Shi usually deals with the Digital watermarking, concentrating on Watermark and frequently concerns with Copy protection, Speech recognition and Adaptive filter.
His study on Image compression, Feature extraction and Image-based modeling and rendering is often connected to 2D computer graphics as part of broader study in Computer vision.
He has included themes like Histogram, Image, Distance measurement and Markov process in his Pattern recognition study.
His most cited work include:
- Reversible Watermarking Algorithm Using Sorting and Prediction (584 citations)
- A Markov process based approach to effective attacking JPEG steganography (320 citations)
- A Survey on Image Steganography and Steganalysis (299 citations)
What are the main themes of his work throughout his whole career to date?
Yun Q. Shi spends much of his time researching Artificial intelligence, Computer vision, Algorithm, Digital watermarking and Pattern recognition.
His studies in JPEG, Discrete cosine transform, Data compression, Steganalysis and Wavelet are all subfields of Artificial intelligence research.
Yun Q. Shi usually deals with JPEG and limits it to topics linked to Steganography and Hilbert–Huang transform.
His research integrates issues of Theoretical computer science, Information hiding, Embedding, Speech recognition and Interleaving in his study of Algorithm.
His Digital watermarking research incorporates elements of Watermark, Binary image, Robustness and Signal processing.
He combines subjects such as Contextual image classification, Thresholding and Standard test image with his study of Pattern recognition.
He most often published in these fields:
- Artificial intelligence (50.90%)
- Computer vision (34.68%)
- Algorithm (31.08%)
What were the highlights of his more recent work (between 2012-2017)?
- Artificial intelligence (50.90%)
- Algorithm (31.08%)
- Embedding (11.26%)
In recent papers he was focusing on the following fields of study:
His primary areas of study are Artificial intelligence, Algorithm, Embedding, Information hiding and Computer vision.
Much of his study explores Artificial intelligence relationship to Pattern recognition.
His study on Algorithm also encompasses disciplines like
- Steganography that connect with fields like Trellis modulation and Discrete cosine transform,
- Steganalysis that connect with fields like Feature and Artificial neural network.
His Embedding study integrates concerns from other disciplines, such as Histogram, Theoretical computer science and Line.
His Information hiding research is multidisciplinary, incorporating elements of Motion vector and Encryption.
Many of his research projects under Computer vision are closely connected to Uncompressed video with Uncompressed video, tying the diverse disciplines of science together.
Between 2012 and 2017, his most popular works were:
- Uniform Embedding for Efficient JPEG Steganography (146 citations)
- Data Hiding in Encrypted H.264/AVC Video Streams by Codeword Substitution (92 citations)
- Ensemble of CNNs for Steganalysis: An Empirical Study (87 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Computer vision
- Statistics
Yun Q. Shi mainly focuses on Algorithm, Theoretical computer science, Artificial intelligence, Embedding and Steganalysis.
Algorithm and Information hiding are commonly linked in his work.
His Information hiding study which covers Cryptography that intersects with Codec.
Yun Q. Shi undertakes interdisciplinary study in the fields of Artificial intelligence and Object detection through his works.
The study incorporates disciplines such as Trellis modulation and Discrete cosine transform in addition to Embedding.
Yun Q. Shi has researched Steganalysis in several fields, including Feature, Pooling, Artificial neural network, Feature vector and Convolutional neural network.
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.
