V
Varun Ganapathi
Researcher at Google
Publications - 26
Citations - 2149
Varun Ganapathi is an academic researcher from Google. The author has contributed to research in topics: Deep learning & Mobile device. The author has an hindex of 12, co-authored 25 publications receiving 2073 citations. Previous affiliations of Varun Ganapathi include Stanford University.
Papers
More filters
Book ChapterDOI
Autonomous Inverted Helicopter Flight via Reinforcement Learning
Andrew Y. Ng,Adam Coates,Mark Diel,Varun Ganapathi,Jamie Schulte,Ben Tse,Eric Berger,Eric Liang +7 more
TL;DR: A successful application of reinforcement learning to designing a controller for sustained inverted flight on an autonomous helicopter, using a stochastic, nonlinear model of the helicopter’s dynamics.
Proceedings ArticleDOI
Real time motion capture using a single time-of-flight camera
TL;DR: This paper derives an efficient filtering algorithm for tracking human pose using a stream of monocular depth images and describes a novel algorithm for propagating noisy evidence about body part locations up the kinematic chain using the un-scented transform.
Proceedings ArticleDOI
Real-time identification and localization of body parts from depth images
TL;DR: Experiments show that the interest points in conjunction with a boosted patch classifier are significantly better in detecting body parts in depth images than state-of-the-art sliding-window based detectors.
Proceedings Article
Efficient Structure Learning of Markov Networks using L_1-Regularization
TL;DR: This paper provides a computationally efficient method for learning Markov network structure from data based on the use of L1 regularization on the weights of the log-linear model, which achieves considerably higher generalization performance than the more standard L2-based method (a Gaussian parameter prior or pure maximum-likelihood learning).
Book ChapterDOI
Real-time human pose tracking from range data
TL;DR: This paper derives an algorithm for tracking human pose in real-time from depth sequences based on MAP inference in a probabilistic temporal model by modeling the constraint that the observed subject cannot enter free space, the area of space in front of the true range measurements.