I am a 4th year graduate student at the University of Washington, advised by
Dieter Fox and
Previously, I graduated from Washington University in St. Louis, where I worked as an undergraduate
researcher with Robert Pless.
I am researching using convolutional neural networks (CNNs) and recurrent neural networks (RNNs) for real-time object tracking in video data. In my research, I am developing fast and robust algorithms with the eventual goal of fully tracking laboratory procedures to reduce errors in experiments and increase reproducibility. I am also working on visual planning for robots using simulation environments and a combination of reinforcement learning and supervised learning.
IQA: Visual Question Answering in Interactive Environments
Daniel Gordon, Aniruddha Kembhavi, Mohammad Rastegari, Joseph Redmon, Dieter Fox, Ali Farhadi
Accepted to Computer Vision and Pattern Recognition 2018
Re3 : Real-Time Recurrent Regression Networks for Visual Tracking of Generic Objects
Daniel Gordon, Ali Farhadi, Dieter Fox
Robotics and Automation Letters 2018
AI2-THOR: An Interactive 3D Environment for Visual AI
Eric Kolve, Roozbeh Mottaghi, Daniel Gordon, Yuke Zhu, Abhinav Gupta, Ali Farhadi
Technical Report 2017
Visual Semantic Planning using Deep Successor Representations
Daniel Gordon*, Yuke Zhu*, Eric Kolve, Dieter Fox, Li Fei-Fei, Abhinav Gupta, Roozbeh Mottaghi, Ali Farhadi
International Conference on Computer Vision 2017
Collaborative imaging of urban forest dynamics: augmenting re-photography to visualize changes over time.
Ruth West, Abby Halley, Jarlath O'Neil-Dunne, Daniel Gordon, and Robert Pless.
IS&T/SPIE Electronic Imaging International Society for Optics and Photonics 2013.
Ruth West, Abby Halley, Daniel Gordon, Jarlath O'Neil-Dunne, and Robert Pless.
SIGGRAPH 2013 Studio Talks
I previously organized a seminar on using deep learning in practice. In it, we discussed how to apply modern techniques to solve real research problems. We also explored the effectiveness of various methods. More information, as well as slides, videos, and code are posted on the seminar website.