University of Cambridge > Talks.cam > Microsoft Research Cambridge, public talks > Rendering Eyes for Eye-Tracking

Rendering Eyes for Eye-Tracking

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Microsoft Research Cambridge Talks Admins.

This event may be recorded and made available internally or externally via http://research.microsoft.com. Microsoft will own the copyright of any recordings made. If you do not wish to have your image/voice recorded please consider this before attending

Eyes and their movements convey our attention and communicate social and emotional information. Recent large-scale supervised methods for eye-tracking require time-consuming data collection and manual annotation, which can be unreliable. In this talk I’ll describe how we instead used computer graphics to rapidly synthesize a varied, realistic, and cleanly-labelled dataset of eye-images from a collection of high-resolution head scans. I will then describe how we used the dataset to train an eye-region deformable model (CLNF), and a multimodal convolutional neural network for appearance-based gaze estimation. Finally I’ll discuss some future work for generating more varied synthetic datasets, and also getting eye-tracking to work robustly over large areas in-the-wild.

This talk is part of the Microsoft Research Cambridge, public talks series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2019 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity