Associate Research Professor in the Robotics Institute,
School of Computer Science;
Courtesy Professor in the Electrical and Computer Engineering (ECE) department;
Director of the Master of Science Computer Vision (MSCV) Program
Carnegie Mellon University
Research Fellow in the Institute of Industrial Science at the
University of Tokyo
Research Interests: computer vision, human activity forecasting, first-person vision, inverse reinforcement learning, deep learning, assistive technologies for the blind
(July 2019) CMU students: I will be hiring at all levels in the Fall. Please contact me during orientation week to setup a brief intervew.
(July 2019) Postdoc position available in computer vision, inverse reinforcement learning or accessibility.
Associate Research Professor at CMU (2019-present)
MSCV Program Director (2018-present)
Assistant Research Professor at CMU (2016-2019)
Systems Scientist at CMU (2013-2016)
Postdoctoral Research Fellow at CMU with Martial Hebert and Drew Bagnell (2011-2013)
Jyokyo (Research Associate / Assistant Professor) at UEC Tokyo (2008-2011)
Visiting scholar at UCSD with Serge Belongie (2010)
University of Tokyo (MS 2005, PhD 2008)
Engineer at KLA-Tencor (2000-2003)
University of Southern California (BS, Electrical Engineering 2000)
Aug. 2019 3 Papers Accepted to ICCV 2019!
Feb. 2019 Paper on Network Compression using BO accepted to ICLR 2019!
Dec. 2018 Two papers accepted to CHI2019!
Dec. 2018 Cognitive Assistance Lab website updated!
Nov. 2018 Two papers accepted to WACV2019!
Sep. 2018 Two papers accepted to CORL 2018!
Jul. 2018 Two papers accepted to ECCV2018!
Jul. 2018 Paper on Deep Image Hashing accepted to BMVC 2018!
May. 2018 Paper on Network Compression using RL accepted to ICLR 2018!
Jan. 2018 4 papers accepted to WACV 2018!
Nov. 2017 2 papers accepted to AAAI 2018!
Oct. 2017 Paper awarded Marr Prize honorable mention at ICCV!
Jul. 2017 Two papers accepted to ICCV 2017!
Apr. 2017 Paper on Multi-Agent Forecasting accepted to CVPR 2017!
Feb. 2017 Best Paper Honorable Mention at CHI 2017!
|Online Inverse Reinforcement Learning for First-Person Vision|
|Navigation for the Blind|
|First-person Vision Activity Recognition|
|Learning Actions Maps|
|Game Theoretic Multi-Agent Forecasting|
|Forecasting Wide Receiver Trajectories|
|Pedestrian Detection by Synthesis|
|Visual Grasp Analysis|
|Hand Detection and Analysis|
Facebook Reality Labs
Highmark / Allegheny General Hospital