Sindhu Hegde

WORK HISTORY

EDUCATION

ABOUT SINDHU HEGDE

I am a Machine Learning professional with an immense interest and enthusiasm in the areas of Computer Vision and AI. My primary research focus is in exploring the interaction between the different modalities such as vision, speech, and language. I am currently working on projects involving video understanding, and self-supervised learning with Prof. Andrew Zisserman @ VGG Oxford. I also work as an AI Scientist at Rode Microphones, focusing on multimodal LLM-based research.Prior to joining University of Oxford, I was a Lead Data Scientist at Verisk Analytics where I had the opportunity to work on multimodal and image forensics projects. Before that, I pursued Masters\' by Research (MS) at Centre for Visual Information Technology (CVIT), Hyderabad, supervised by Prof. C V Jawahar and Prof. Vinay Namboodiri (University of Bath, UK). My Masters\' research focused on exploiting the redundancies in vision and speech modalities for cross-modal generation.Over the course of my research journey, I have developed strong communication and writing skills, can excel under pressure, enjoy team work and can also effectively lead a team. I am a constant learner - I enjoy learning about new and emerging technologies. I love interacting and collaborating with people, it helps me to gain new perspectives!Research Areas: Machine learning | Deep Learning | Multi-modal Learning | Computer Vision | Video Understanding | Speech Processing | Natural Language ProcessingFrameworks/Tools: PyTorch | Keras | Tensorflow | OpenCV | Librosa | NLTK | LaTex