
My research lies at the intersection of computational mathematics and machine learning for applications to large-scale real world problems. My central research is to develop new data-driven algorithmic techniques that allow computers to gain high-level understanding from vast amounts of data, this, with the aim of aiding the decisions of users. These methods are based on mathematical modelling and machine learning methods.
Keywords: Applied Mathematics
Computational Mathematics
Inverse problems
Image Analysis
Graph Learning
Machine Learning.
Publications
Superpixel Contracted Graph-Based Learning for Hyperspectral Image Classification
– IEEE Transactions on Geoscience and Remote Sensing
(2020)
58,
4180
(doi: 10.1109/TGRS.2019.2961599)
Tuning-free plug-and-play proximal algorithm for inverse imaging problems
– 37th International Conference on Machine Learning Icml 2020
(2020)
PartF168147-14,
10089
Dim the Lights! -- Low-Rank Prior Temporal Data for Specular-Free Video
Recovery
(2019)
GraphX$^\mathbf{\small NET } -$ Chest X-Ray Classification Under Extreme Minimal Supervision
– Lecture Notes in Computer Science
(2019)
11769,
504
(doi: 10.1007/978-3-030-32226-7_56)
RainFlow: Optical Flow Under Rain Streaks and Rain Veiling Effect
– 2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019)
(2019)
00,
7303
(doi: 10.1109/ICCV.2019.00740)
Variational Multi-Task MRI Reconstruction: Joint Reconstruction,
Registration and Super-Resolution
(2019)
Semi-Supervised Learning with Graphs: Covariance Based Superpixels For Hyperspectral Image Classification
– 2019 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2019)
(2019)
00,
592
(doi: 10.1109/IGARSS.2019.8898189)
Mirror, Mirror, on the Wall, Who's Got the Clearest Image of Them All?-A Tailored Approach to Single Image Reflection Removal
– IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
(2019)
28,
6185
(doi: 10.1109/tip.2019.2923559)
Energy Models for Better Pseudo-Labels: Improving Semi-Supervised
Classification with the 1-Laplacian Graph Energy
(2019)
ReTouchImg: Fusioning from-local-to-global context detection and graph data structures for fully-automatic specular reflection removal for endoscopic images.
– Comput Med Imaging Graph
(2019)
73,
39
- <
- 4 of 5