J
Jia Deng
Researcher at Princeton University
Publications - 158
Citations - 110718
Jia Deng is an academic researcher from Princeton University. The author has contributed to research in topics: Computer science & Object detection. The author has an hindex of 50, co-authored 148 publications receiving 73461 citations. Previous affiliations of Jia Deng include University of Michigan & Carnegie Mellon University.
Papers
More filters
Proceedings Article
Strongly Incremental Constituency Parsing with Graph Neural Networks
Kaiyu Yang,Jia Deng +1 more
TL;DR: This article proposed a transition-based parser called attach-juxtapose, which represents a partial sentence using a single tree, and each action adds exactly one token into the partial tree.
Proceedings ArticleDOI
Learning to Generate 3D Training Data Through Hybrid Gradient
Dawei Yang,Jia Deng +1 more
TL;DR: This work proposes a new method that optimizes the generation of 3D training data based on what it calls "hybrid gradient", which parametrize the design decisions as a real vector, and combines the approximate gradient and the analytical gradient to obtain the hybrid gradient of the network performance with respect to this vector.
Book ChapterDOI
A Unified Framework of Surrogate Loss by Refactoring and Interpolation.
Lanlan Liu,Mingzhe Wang,Jia Deng +2 more
TL;DR: UniLoss as discussed by the authors is a unified framework to generate surrogate losses for training deep networks with gradient descent, reducing the amount of manual design of task-specific surrogate losses, which can optimize for different tasks and metrics using one unified framework.
Posted Content
PackIt: A Virtual Environment for Geometric Planning
Ankit Goyal,Jia Deng +1 more
TL;DR: PackIt is presented, a virtual environment to evaluate and potentially learn the ability to do geometric planning, where an agent needs to take a sequence of actions to pack a set of objects into a box with limited space.
Posted Content
Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline
TL;DR: PointNet++ as mentioned in this paper uses auxiliary factors like different evaluation schemes, data augmentation strategies, and loss functions, which are independent of the model architecture, to make a large difference in performance.