I’m an Assistant Professor in the Carlson Center for Imaging Science at the Rochester Institute of Technology. I direct the Machine and Neuromorphic Perception Laboratory (a.k.a., kLab) at RIT.
I use machine learning, especially deep learning, to solve problems in computer vision. My lab primarily studies task-driven scene understanding and lifelong machine learning. My recent work has focused on visual question answering (VQA) and incremental learning in deep networks. In the past I have worked on semantic segmentation, object recognition, object detection, active vision, object tracking, and more. Beyond machine learning, I also have a strong background in eye tracking, primate vision, and theoretical neuroscience.
2017/11: Adobe Research has given my lab a gift of $22,000. Thank you Adobe Research!
2017/11: Won a $33,000 NGA Phase 1 SBIR with our collaborators at Intelligent Automation, Inc. to do target detection.
2017/11: My lab’s paper on measuring catastrophic forgetting was accepted to AAAI-2018!
2017/10: I was an invited speaker at the ICCV-2017 Workshop on Closing the Loop between Vision and Language.
2017/08: Our new VQA dataset, TDIUC, is now publicly available.
2017/08: Our RIT-18 dataset for multispectral semantic segmentation is now publicly available.
2017/08: Teaching the course Deep Learning for Vision.
2017/07: My paper with Dhireesha Kudithipudi’s lab on video classification was accepted to ICRC-2017.
2017/07: Our paper analyzing VQA algorithms using TDIUC was accepted to ICCV-2017.
2017/06: My first robotics paper, which is on using deep learning for detecting good grasps, was accepted to IROS-2017.
2017/06: My lab’s critical review paper on the state of VQA was accepted by the journal CVIU.
2017/05: I am co-organizing the ICCV-2017 workshop on Mutual Benefits of Cognitive and Computer Vision (MBCC).
2017/02: I’m an area chair for ICIP-2017.
2017/01: Teaching IMGS 682 – Image Processing for Computer Vision.
2016/12: Our paper on self-taught deep learning models for semantic segmentation of hyperspectral images was accepted to IEEE TGRS.
2016/08: Teaching IMGS 789 – Deep Learning for Vision.
2016/06: Our paper on Answer-Type Prediction for Visual Question Answering appeared at CVPR-2016.
2016/05: I won the RIT College of Science Rising Star Award.
2016/04: Our web-app for Visual Question Answering has launched: http://www.askimage.org/
2016/03: Our paper on using gnostic fields and saliency for tracking appeared at WACV-2016.
2016/01: Started teaching IMGS 682 – Image Processing for Computer Vision.
2015/08: Started as an assistant professor at RIT. My lab: http://klab.cis.rit.edu/
2015/07: The VAIS dataset for ship classification is now available for download.
2015/07: Our paper on combining hierarchical ICA with Gnostic Fields appeared at COGSCI-2015.
2015/06: Our paper on the VAIS dataset for ship classification appeared at the CVPR-2015 Perception Beyond the Visible Spectrum workshop.
2015/01: Our paper on the Multi-Fixation Pattern Analysis, a new method for analyzing eye movement data, appeared in Vision Research.
Outreach & Service
For over 15 years, I’ve endeavored to promote diversity in graduate education. I’m currently a faculty mentor for the RIT McNair and LSAMP Scholars programs, which are aimed at preparing first-generation college students and members of underrepresented minority groups for graduate school. I’ve given multiple talks at the California Forum for Diversity and at several California State Universities to help undergraduates obtain a better idea of how to get into a Ph.D. program and what is expected of them once they are accepted. During my Ph.D., I was a mentor to high school students at The Preuss School, which serves low income students.
I was General Chair for the 5th Annual inter-Science of Learning Center Conference (iSLC), which was held April 21-23, 2012. The meeting was sponsored by the National Science Foundation (NSF) and more than 100 scientists attended.
I grew up in a tiny town in rural Oklahoma, where I first began to explore artificial intelligence in 1996 by creating “bots” to play online multiplayer computer games in high school. As an undergraduate at Oklahoma State University, I double majored in philosophy and computer science. Subsequently, I earned a M.S. in computer science from the University of Southern California (USC) , with an emphasis in artificial intelligence and neuroscience while working with Michael Arbib, an early pioneer in computational neuroscience and neural networks. I then went on to earn a Ph.D. in computer science at the University of California, San Diego (UCSD), where I was a member of Gary Cottrell’s research group. Afterwards, I became a Caltech Postdoctoral Scholar, where I worked at NASA’s Jet Propulsion Laboratory (JPL) as part of the Maritime and Aerial Perception group in the Robotics and Mobility Section. After eight months, JPL hired me as a Research Technologist, where I helped develop artificial vision systems for autonomous robots using deep learning. In August 2015, I joined the Chester F. Carlson Center for Imaging Science at RIT as an Assistant Professor.