AIR Weekly Seminar: Arsha Nagrani

Speaker: Arsha Nagrani

Talk Title: "Video Understanding in the Age of Large MLMs"

Abstract: What makes understanding videos so challenging for large multimodal language models, such as Gemini and GPT4? We will dive into some of the challenges, including fun new tasks, datasets, evaluations and models, covering recently accepted papers at CVPR & NeurIPS.

Bio: Arsha Nagrani is a Staff Research Scientist at Google DeepMind. She obtained her PhD from the VGG group in the University of Oxford with Andrew Zisserman, where her thesis received the ELLIS PhD Award. Prior to that, she received her BA and MEng degrees from the University of Cambridge, UK. Her work has been recognised by a Best Student Paper Award at Interspeech, an Outstanding Paper Award at ICASSP, a Google PhD Fellowship and a Townsend Scholarship, and has been covered by news outlets such as The New Scientist, MIT Tech review and Verdict. Her research is focused on machine learning techniques for video understanding, and she is currently working on Gemini.