What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Algebra
The scientist’s investigation covers issues in Artificial intelligence, Pattern recognition, Convolutional neural network, Feature extraction and Machine learning.
His research on Artificial intelligence often connects related areas such as Computer vision.
His Computer vision research is multidisciplinary, incorporating perspectives in Variety and Representation.
His Pattern recognition study combines topics from a wide range of disciplines, such as Function, Optimization problem, Eigenvalues and eigenvectors and Linear subspace.
His Feature extraction research incorporates themes from Anticipation and Benchmark.
Many of his research projects under Machine learning are closely connected to Multi-task learning, Set and Spice with Multi-task learning, Set and Spice, tying the diverse disciplines of science together.
His most cited work include:
- Unsupervised Visual Domain Adaptation Using Subspace Alignment (823 citations)
- SPICE: Semantic Propositional Image Caption Evaluation (641 citations)
- Modeling video evolution for action recognition (411 citations)
What are the main themes of his work throughout his whole career to date?
Basura Fernando spends much of his time researching Artificial intelligence, Pattern recognition, Machine learning, Image and Set.
His work in Artificial intelligence is not limited to one particular discipline; it also encompasses Computer vision.
Basura Fernando has included themes like Subspace topology and Pooling in his Pattern recognition study.
His work investigates the relationship between Subspace topology and topics such as Linear subspace that intersect with problems in Function and Eigenvalues and eigenvectors.
His study in the field of Supervised learning is also linked to topics like Function, Frame and Set.
The concepts of his Image study are interwoven with issues in Information retrieval and Natural language processing.
He most often published in these fields:
- Artificial intelligence (78.43%)
- Pattern recognition (40.20%)
- Machine learning (25.49%)
What were the highlights of his more recent work (between 2019-2021)?
- Artificial intelligence (78.43%)
- Machine learning (25.49%)
- Frame (8.82%)
In recent papers he was focusing on the following fields of study:
His primary scientific interests are in Artificial intelligence, Machine learning, Frame, Action recognition and Inference.
His studies deal with areas such as Computer vision and Natural language processing as well as Artificial intelligence.
His work carried out in the field of Natural language processing brings together such families of science as Representation and Benchmark.
Basura Fernando has researched Machine learning in several fields, including Robot and Machine translation.
His Feature study incorporates themes from Discriminative model, Pattern recognition and Face.
His Latent variable study combines topics in areas such as Structure, Image, Closed captioning and Regularization.
Between 2019 and 2021, his most popular works were:
- Hallucinating Unaligned Face Images by Multiscale Transformative Discriminative Networks (16 citations)
- Semantic Face Hallucination: Super-Resolving Very Low-Resolution Face Images with Supplementary Attributes (14 citations)
- Weakly Supervised Gaussian Networks for Action Detection (10 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Algebra
His main research concerns Artificial intelligence, Frame, Machine learning, Discriminative model and Pattern recognition.
Basura Fernando performs multidisciplinary studies into Artificial intelligence and Gaussian in his work.
The Discriminative model study combines topics in areas such as Upsampling and Face.
His Artificial neural network study combines topics from a wide range of disciplines, such as Pixel, Hallucinating and Pattern recognition.
His Image resolution research integrates issues from Feature, Interpolation, Facial recognition system, Feature extraction and Iterative reconstruction.
His study on Machine translation is intertwined with other disciplines of science such as Task analysis, Function and Data modeling.
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.
