Scholar
Sindhu Hegde
Google Scholar ID: cD8J2-kAAAAJ
PhD Scholar, VGG, Oxford
Citations & Impact
Citations
197
H-index
8
i10-index
8
Publications
20
Co-authors
0
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- - Awarded the 2025 Google PhD Fellowship
- - Paper 'Understanding Co-speech Gestures in-the-wild' accepted to ICCV 2025 (ORAL)
- - Paper 'Scaling Multilingual Visual Speech Recognition' accepted to ICASSP 2025 (ORAL)
- - Paper 'GestSync: Determining who is speaking without a talking head' accepted to BMVC 2023 (ORAL)
Research Experience
- - AI Scientist at Rode Microphones, focusing on multimodal LLM-based research
- - Lead Data Scientist at Verisk Analytics
- - Completed Masters’ by Research (MS) at CVIT, IIIT Hyderabad, with a focus on exploiting the redundancies in vision and speech modalities for cross-modal generation
Education
- - PhD Student at the University of Oxford, supervised by Prof. Andrew Zisserman
- - Master’s by Research (MS) at Centre for Visual Information Technology (CVIT), IIIT Hyderabad, supervised by Prof. C V Jawahar (IIIT-H) and Prof. Vinay Namboodiri (University of Bath, UK)
- - Undergraduate studies at KLE Technological University, advised by Prof. Shankar Gangisetty and Prof. Uma Mudenagudi
Background
- Research interests include Computer Vision, Machine Learning, Deep Learning, Video Understanding, and Multi-modal Learning (Vision + Speech/Language). Her research focuses on understanding non-verbal communication (including co-speech gestures and lip-reading), video understanding, and self-supervised learning.
Miscellany
- Participated in the International Computer Vision Summer School (ICVSS) at Sicily, Italy, and had an incredible experience of learning from some of the most distinguished computer vision experts.
Co-authors