Brendan Duke

Machine Learning Researcher

About me

I am a PhD student at the University of Toronto advised by Parham Aarabi, and a Research Scientist Team Lead at ModiFace, Inc. My research interests include machine learning, deep learning, and computer vision. At ModiFace I apply deep learning to the beauty tech space to create augmented reality (AR) virtual experiences.

I had the pleasure of completing my M.A.Sc. at the University of Guelph advised by Graham Taylor in the Machine Learning Research Group (MLRG). My master's thesis focused on attention and fusion operators in computer vision.

Previous to that I worked at AMD writing firmware for the AMD Secure Processor.


SSTVOS Architecture

SSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentation

Brendan Duke, Abdalla Ahmed, Christian Wolf, Parham Aarabi, Graham W. Taylor
CVPR 2021 Oral (4.3% acceptance rate)
paper / code

We introduce a Transformer-based approach to video object segmentation (VOS). Our method, called Sparse Spatiotemporal Transformers (SST), extracts per-pixel representations for each object in a video using sparse attention over spatiotemporal features.

LOHO Preview

LOHO: Latent Optimization of Hairstyles via Orthogonalization

Rohit Saha, Brendan Duke, Florian Shkurti, Graham W. Taylor, Parham Aarabi
CVPR 2021
paper / code

We propose Latent Optimization of Hairstyles via Orthogonalization (LOHO), an optimization-based approach using GAN inversion to infill missing hair structure details in latent space during hairstyle transfer. Using LOHO for latent space manipulation, users can synthesize novel photorealistic images by manipulating hair attributes either individually or jointly, transferring the desired attributes from reference hairstyles.