Assistant Professor
Associate Director, ML@GT
School of Interactive Computing
College of Computing (Office: CCB 222)
Email: zkira at gatech dot edu
I am always looking for post-docs and Ph.D. students. See here for details
News
06/14/2019 Preprint: Manifold graphs for state of art semi-supervised learning! [project][arxiv]
03/12/2019 Program Committee of UAI 2019
03/02/2019 Oral CVPR paper. Congrats Chih-Yao! (work with Salesforce Research)
02/01/2019 Dataset released for our WACV PCB component detection paper! [download]
01/26/2019 Two ICRA/RA-L accepted papers. Congrats Jing-Dao and Angel!
01/03/2019 Journal paper on point cloud scene understanding
12/24/2018 Three ICLR accepted papers. Congrats Yen-Chang, Yen-Cheng, and Chih-Yao!
12/05/2018 Pytorch framework for continual/lifelong learning released! [github]
11/13/2018 NIPS Continual Learning Workshop paper
11/06/2018 WACV paper accepted. Congrats Albert!
10/29/2018 Teaching Deep Learning cross-listed undergraduate and graduate course.
09/18/2018 New ONR funding with Lu Feng (UVA), Pratap Tokekar (VT), and Ufuk Topcu (UT Austin).
09/12/2018 Journal paper on TS-LSTMs accepted
07/16/2018 Assistant Professor!
07/15/2018 Pytorch code release for our clustering work on github
06/16/2018 News article about new DARPA lifelong learning project
02/18/2018 CVPR paper on Higher-Order Object Interactions for Video Understanding.
01/29/2018 ICLR paper (in top 7% of reviews!) for Learning to Cluster paper
About Me
I am an Assistant Professor at the School of Interactive Computing in the College of Computing. I am also affiliated with the Georgia Tech Research Institute and serve as an Associate Director of ML@GT which is the machine learning center recently created at Georgia Tech. Previously I was a Research Scientist at SRI International Sarnoff in Princeton, and before that received my Ph.D. in 2010 with Professor Ron Arkin as my advisor.
I lead the RobotIcs Perception and Learning (RIPL) lab. My areas of research specifically focus on the intersection of learning methods for sensor processing and robotics, developing novel machine learning algorithms and formulations towards solving some of the more difficult perception problems in these areas. I am especially interested recently in unsupervised/semi-supervised methods, continual/lifelong learning, multi-modal fusion, and distributed perception.
