CV

Download resume (PDF) Publications

Experience

1. 2022 – Present

   Senior Researcher, Dolby Laboratories

   Multimodal Experiences Lab, Advanced Technology Group · San Francisco, CA

   • Transformer architectures that combine video, audio and text for moment retrieval and video question answering.
   • Open-world, event-level video scene graph generation for long-form content.
   • Submodular sampling for long-form video QA, and point-supervised online temporal action localization.
   • Agentic workflows that use video scene graphs for personalized content curation.
   • Lightweight, real-time audio-visual active speaker detection for mobile capture.
2. Summer 2021

   Research Intern, Google

   New York, NY

   • Using external knowledge to improve language models.
3. Summer 2020

   Data Science Research Intern, Adobe

   San Jose, CA

   • Generative models for lossless image compression.
4. 2016 – 2021

   Graduate Research Assistant, New York University and Iowa State University

   Advisor: Chinmay Hegde

   • Computational imaging, deep generative priors, adversarial ML, super-resolution and HDR imaging.
5. Summer 2018

   Research Intern, Mitsubishi Electric Research Laboratories

   Cambridge, MA

   • Algorithms for multi-modal active imaging.
6. 2015 – 2016

   Research Assistant, Indian Institute of Science

   • Compressed sensing and its application to ultrasound imaging.

Education

1. 2022

   Ph.D. in Electrical Engineering, New York University

2. 2019

   M.S. in Electrical Engineering, Iowa State University

3. 2015

   B.E. in Electrical and Electronics Engineering and M.Sc. in Physics, BITS Pilani, Goa

Research interests

Patent applications

• G. Jagatap, K. V. Gouthaman, J. Serra, A. Fanelli, D. Chandran, “System for audio-visual content trimming: highlight generation, moment retrieval and summarization for user generated content creators”, filed by Dolby Laboratories, 2024.
• G. Cengarle, D. Scaini, Y. Ma, Z. Li, G. Jagatap, B. Crockett, “Object extraction and lock in position for complex spatial scenes”, filed by Dolby Laboratories, 2024.
• A. Majee, G. Jagatap, D. Chandran, A. Fanelli, “SCOUT: Segment Curation for Optimal Understanding of Long-Form Videos”, filed by Dolby Laboratories, 2025.

Publications

23 papers and preprints, from NeurIPS and IEEE Transactions on Information Theory to ECCV and ACL. See the full list.

Media

• Unveiling the depths: transforming video with deep learning expertise, BITS Pilani