What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Computer vision
- Algorithm
His primary scientific interests are in Artificial intelligence, Computer vision, Multimedia, Data compression and Decoding methods.
His research combines Machine learning and Artificial intelligence.
His studies in Computer vision integrate themes in fields like Computational complexity theory, Video streaming and Multiview video plus depth.
His Multimedia research is multidisciplinary, incorporating elements of MPEG-21, Quality of experience and World Wide Web.
His biological study spans a wide range of topics, including Codec and Interpolation.
The various areas that Fernando Pereira examines in his Decoding methods study include Broadband networks, MPEG-4, Theoretical computer science and Speech recognition.
His most cited work include:
- Qualinet White Paper on Definitions of Quality of Experience (353 citations)
- Adaptive Hash-Based Side Information Exploitation for Efficient Wyner-Ziv Video Coding (67 citations)
- Fast rate distortion optimization for the emerging HEVC standard (62 citations)
What are the main themes of his work throughout his whole career to date?
Fernando Pereira mainly focuses on Artificial intelligence, Computer vision, Multimedia, Multiview Video Coding and Codec.
His Pattern recognition research extends to the thematically linked field of Artificial intelligence.
His study brings together the fields of Video quality and Computer vision.
His study focuses on the intersection of Multimedia and fields such as Standardization with connections in the field of Interoperability.
As a member of one scientific family, Fernando Pereira mostly works in the field of Multiview Video Coding, focusing on Coding tree unit and, on occasion, Context-adaptive binary arithmetic coding, Real-time computing and Rate–distortion optimization.
Rate–distortion theory is closely connected to Decoding methods in his research, which is encompassed under the umbrella topic of Codec.
He most often published in these fields:
- Artificial intelligence (46.87%)
- Computer vision (40.18%)
- Multimedia (19.20%)
What were the highlights of his more recent work (between 2014-2021)?
- Artificial intelligence (46.87%)
- Computer vision (40.18%)
- Light field (9.37%)
In recent papers he was focusing on the following fields of study:
Fernando Pereira spends much of his time researching Artificial intelligence, Computer vision, Light field, Lenslet and JPEG.
Artificial intelligence is closely attributed to Pattern recognition in his work.
His research ties Codec and Computer vision together.
His Codec research includes themes of Coding tree unit and Scalable Video Coding.
His Light field study combines topics from a wide range of disciplines, such as Pixel and Database.
His studies deal with areas such as Multimedia and Quality of experience as well as Point cloud.
Between 2014 and 2021, his most popular works were:
- Objective and subjective evaluation of light field image compression algorithms (36 citations)
- Optimizing Multiview Video Plus Depth Prediction Structures for Interactive Multiview Video Streaming (35 citations)
- The IST-EURECOM Light Field Face Database (31 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Computer vision
- Computer network
His main research concerns Artificial intelligence, Computer vision, Light field, JPEG and Facial recognition system.
He regularly ties together related areas like Machine learning in his Artificial intelligence studies.
His work investigates the relationship between Computer vision and topics such as Computational complexity theory that intersect with problems in Visual distortion, Multiview video plus depth, Decoding methods, Multiview Video Coding and Video streaming.
The study incorporates disciplines such as Non-local means and Pattern recognition in addition to Light field.
Fernando Pereira has included themes like Transform coding, Codec, Quality assessment and Interoperability in his JPEG study.
Quality of experience is closely connected to Octree in his research, which is encompassed under the umbrella topic of Transform coding.
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.
