chanaaro [at] usc [dot] edu  /  Los Angeles, CA

I am a first-year PhD student in computer science at the University of Southern California (USC), advised by Fei Sha.

Before joining ShaLab at USC, I earned a master's degree in robotics from the University of Pennsylvania and a bachelor's degree in electrical engineering from the University of Maryland, College Park.

I have also spent time at Google as an engineering intern on the Android Camera team.

Google Scholar  /  LinkedIn  /  Twitter



My research interests include machine learning and computer vision.

Egocentric Basketball Motion Planning from a Single First-Person Image

Gedas Bertasius, Aaron Chan, Jianbo Shi

CVPR 2018   pdf / arXiv / video

We introduce an unsupervised basketball ghosting model that generates plausible basketball behavior sequences from a single first-person image. Our model can be used to predict future behavior and improve player decision-making in basketball (and potentially other sports).

Learning an Egocentric Basketball Ghosting Model using Wearable Cameras and Deep Convolutional Networks

Gedas Bertasius, Aaron Chan, Jianbo Shi

SSAC 2018   pdf / poster

This paper was one of the twelve selected as a poster in the 2018 MIT Sloan Sports Analytics Conference (SSAC) Research Paper Competition and is based on our CVPR 2018 paper "Generating a Goal-Oriented Basketball Behavior from a Single First-Person Image."

6-DoF Object Pose from Semantic Keypoints

Georgios Pavlakos, Xiaowei Zhou, Aaron Chan, Konstantinos G. Derpanis, Kostas Daniilidis

ICRA 2017   pdf / arXiv / project page / code / video

We propose a method for estimating the 6-DoF pose of an object from a single image by localizing the object's semantic keypoints and fitting these keypoints to a deformable shape model.

Scalable Vision System for Mouse Homecage Ethology

Ghadi Salem, Jonathan Krynitsky, Brett Kirkland, Eugene Lin, Aaron Chan, Simeon Anfinrud, Sarah Anderson, Marcial Garmendia-Cedillos, Rhamy Belayachi, Juan Alonso-Cruz, Joshua Yu, Anthony Iano-Fletcher, George Dold, Tom Talbot, Alexxai V. Kravitz, James B. Mitchell, Guanhang Wu, John U. Dennis, Monson Hayes, Kristin Branson, Thomas Pohida

ACIVS 2016   pdf / project page / video

Our fully-automated system for video-based lab mouse behavior analysis can make drug-efficacy, animal model development, and phenotyping studies much more efficient.

Website design by Jon Barron.