J
Jiajun Wu
Researcher at Stanford University
Publications - 216
Citations - 13655
Jiajun Wu is an academic researcher from Stanford University. The author has contributed to research in topics: Computer science & Object (computer science). The author has an hindex of 48, co-authored 169 publications receiving 9618 citations. Previous affiliations of Jiajun Wu include Massachusetts Institute of Technology & Princeton University.
Papers
More filters
Proceedings Article
Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding
TL;DR: In this paper, a neural-symbolic visual question answering (NS-VQA) system first recovers a structural scene representation from the image and a program trace from the question and then executes the program on the scene representation to obtain an answer.
Proceedings ArticleDOI
Attention Clusters: Purely Attention Based Local Feature Integration for Video Classification
TL;DR: In this article, a local feature integration framework based on attention clusters was proposed, and a shifting operation was introduced to capture more diverse signals for video classification, which achieved state-of-the-art performance on three real-world video classification datasets.
Proceedings ArticleDOI
ChainQueen: A Real-Time Differentiable Physical Simulator for Soft Robotics
Yuanming Hu,Jiancheng Liu,Andrew Spielberg,Joshua B. Tenenbaum,William T. Freeman,Jiajun Wu,Daniela Rus,Wojciech Matusik +7 more
TL;DR: A real-time, differentiable hybrid Lagrangian-Eulerian physical simulator for deformable objects, ChainQueen, based on the Moving Least Squares Material Point Method (MLS-MPM), which can simulate deformable Objects with collisions and can be seamlessly incorporated into soft robotic systems.
Proceedings Article
Learning to See Physics via Visual De-animation
TL;DR: A paradigm for understanding physical scenes without human annotations is introduced that quickly recognizes the physical world state from appearance and motion cues, and has the flexibility to incorporate both differentiable and non-differentiable physics and graphics engines.
Posted Content
Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding
TL;DR: In this article, a neural-symbolic visual question answering (NS-VQA) system first recovers a structural scene representation from the image and a program trace from the question and then executes the program on the scene representation to obtain an answer.