Shailza Sharma
- Position: Research Fellow
- Areas of expertise: My areas of expertise include computer vision, deep learning, and generative artificial intelligence.
- Email: S.Sharma@leeds.ac.uk
- Location: 7.28a Priestley Buiding
- Website: LinkedIn | Googlescholar | Researchgate | ORCID
Profile
I am a Research Fellow working on the DEEPVOLC project at the University of Leeds, where I develop deep learning models to forecast volcanic activity using spatio-temporal satellite data. My expertise spans computer vision, generative modeling, deep learning, and generative AI.
I hold a Ph.D. in Semantic and Depth-Aware Generative Adversarial Network for Image Super-Resolution.
Previously, as a Research Scientist at Kroop AI, I worked on a pioneering project to achieve lip-syncing in talking face videos of arbitrary identities to match target speech segments, utilizing advanced techniques in generative adversarial networks (GANs) and audio-visual alignment.
My research interests include generative modeling, convolutional neural networks (CNNs), GANs, super-resolution, deep fake analysis, and face hallucination. I am passionate about leveraging AI to address real-world challenges in diverse domains, from natural phenomena to human-centric applications.
Responsibilities
- Developing deep learning models for the DEEPVOLC project to forecast volcanic activity using spatio-
- temporal satellite data. Responsibilities include designing data pipelines, implementing advanced
- deep learning based architectures, and conducting large-scale training and testing on HPC systems.