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
Posted Content
Premise Selection for Theorem Proving by Deep Graph Embedding
TL;DR: In this article, a deep learning-based approach is proposed to select mathematical statements relevant for proving a given conjecture, which achieves state-of-the-art results on the HolStep dataset.
Journal ArticleDOI
Siamese Masked Autoencoders
TL;DR: Siamese Masked Autoencoders (SiamMAE) as discussed by the authors is a simple extension of MAE for learning visual correspondence from videos, which operates on pairs of randomly sampled video frames and asymmetrically masks them.
Journal Article
Entity and Event Extraction from Scratch Using Minimal Training Data.
Laura Wendlandt,Steve Wilson,Oana Ignat,Charles Welch,Li Zhang,Mingzhe Wang,Jia Deng,Rada Mihalcea +7 more
TL;DR: This work is building the first step of the overall system, which involves translating all the raw documents, as well as transcribing and translating audio and video data, and building a graph from all the entities, events, and relations.
Posted Content
Tangent Space Backpropagation for 3D Transformation Groups
Zachary Teed,Jia Deng +1 more
TL;DR: PyTorch as mentioned in this paper performs backpropagation in the tangent spaces of manifolds by exploiting the group structure of 3D transformations and performs back propagation in the groups SO(3), SE(3) and Sim(3).
Journal ArticleDOI
Infinite Photorealistic Worlds using Procedural Generation
Alexander R. E. Raistrick,Lahav Lipson,Zeyu Ma,Lingjie Mei,Mingzhe Wang,Yiming Zuo,Karhan K. Kayan,Hongyu Wen,Beining Han,Alejandro Newell,Hei Law,Ankit Goyal,Kaiyu Yang,Jia Deng +13 more
TL;DR: In Infinigen as discussed by the authors , a procedural generator of photorealistic 3D scenes of the natural world is presented, where every asset, from shape to texture, is generated from scratch via randomized mathematical rules, using no external source and allowing infinite variation and composition.