J
Jana Kosecka
Researcher at George Mason University
Publications - 166
Citations - 10467
Jana Kosecka is an academic researcher from George Mason University. The author has contributed to research in topics: Object detection & Motion estimation. The author has an hindex of 45, co-authored 155 publications receiving 9087 citations. Previous affiliations of Jana Kosecka include Austrian Institute of Technology & University of Pennsylvania.
Papers
More filters
Posted Content
SLAW: Scaled Loss Approximate Weighting for Efficient Multi-Task Learning.
Michael Crawshaw,Jana Kosecka +1 more
TL;DR: SLAW as discussed by the authors balances learning between tasks by estimating the magnitudes of each task's gradient without performing any extra backward passes, which matches the performance of the best existing methods while being much more efficient.
Journal ArticleDOI
Synthetic Smartwatch IMU Data Generation from In-the-wild ASL Videos
TL;DR: In this paper , a wrist orientation estimation module was proposed to account for wrist rotations by carefully incorporating hand joint positions, and an acceleration and gyro prediction module leveraged the orientation for transformation while capturing the contributions of hand movements and shape.
Object recognition using strangeness and transduction
TL;DR: A simple and efficient feature selection algorithm to deal with irrelevant and background features and a new non-parametric weak leaner employed in the boosting framework and the Open Set Transductive Confidence Machine-k Nearest Neighbor algorithm for open set recognition using strangeness are presented.
Journal ArticleDOI
Comparison of Model-Free and Model-Based Learning-Informed Planning for PointGoal Navigation
TL;DR: In this paper , the authors compare the state-of-the-art Deep Reinforcement Learning based approaches with Partially Observable Markov Decision Process (POMDP) formulation of the point goal navigation problem.
Journal ArticleDOI
American Sign Language Recognition Using an FMCW Wireless Sensor (Student Abstract)
TL;DR: This research team proposes the use of a novel wireless sensor (Frequency-Modulated Continuous-Wave Radar) to help bridge the gap in communication between ASL users and non-users.