P
Parth Shah
Researcher at Stanford University
Publications - 6
Citations - 752
Parth Shah is an academic researcher from Stanford University. The author has contributed to research in topics: Motion field & Haptic technology. The author has an hindex of 4, co-authored 5 publications receiving 417 citations.
Papers
More filters
Book ChapterDOI
The Marabou Framework for Verification and Analysis of Deep Neural Networks
Guy Katz,Derek A. Huang,Duligur Ibeling,Kyle D. Julian,Christopher Lazarus,Rachel Lim,Parth Shah,Shantanu Thakoor,Haoze Wu,Aleksandar Zeljić,David L. Dill,Mykel J. Kochenderfer,Clark Barrett +12 more
TL;DR: Marabou is an SMT-based tool that can answer queries about a network’s properties by transforming these queries into constraint satisfaction problems, and it performs high-level reasoning on the network that can curtail the search space and improve performance.
Proceedings ArticleDOI
Making Sense of Vision and Touch: Self-Supervised Learning of Multimodal Representations for Contact-Rich Tasks
Michelle A. Lee,Yuke Zhu,Krishnan Srinivasan,Parth Shah,Silvio Savarese,Li Fei-Fei,Animesh Garg,Jeannette Bohg +7 more
TL;DR: This work uses self-supervision to learn a compact and multimodal representation of sensory inputs, which can then be used to improve the sample efficiency of the policy learning of deep reinforcement learning algorithms.
Journal ArticleDOI
Motion-Based Object Segmentation Based on Dense RGB-D Scene Flow
TL;DR: In this article, an hourglass, deep neural network architecture is employed to estimate a dense 3D motion field, also known as scene flow, for scene segmentation and motion trajectories.
Posted Content
Making Sense of Vision and Touch: Self-Supervised Learning of Multimodal Representations for Contact-Rich Tasks
Michelle A. Lee,Yuke Zhu,Krishnan Srinivasan,Parth Shah,Silvio Savarese,Li Fei-Fei,Animesh Garg,Jeannette Bohg +7 more
TL;DR: In this paper, self-supervision is used to learn a compact and multimodal representation of sensory inputs, which can then be used to improve the sample efficiency of policy learning.
Journal ArticleDOI
Motion-based Object Segmentation based on Dense RGB-D Scene Flow
TL;DR: In this article, an hourglass, deep neural network architecture is employed to estimate scene flow and motion trajectories of rigidly moving objects in two consecutive RGB-D images, respectively.