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
Deep Audio Priors Emerge From Harmonic Convolutional Networks
Zhoutong Zhang,Yunyun Wang,Chuang Gan,Jiajun Wu,Joshua B. Tenenbaum,Antonio Torralba,William T. Freeman +6 more
TL;DR: Harmonic Convolution is proposed, an operation that helps deep networks distill priors in audio signals by explicitly utilizing the harmonic structure within by engineering the kernel to be supported by sets of harmonic series, instead of local neighborhoods for convolutional kernels.
Posted Content
Learning Physical Graph Representations from Visual Scenes
Daniel M. Bear,Chaofei Fan,Damian Mrowca,Yunzhu Li,Seth Alter,Aran Nayebi,Jeremy Schwartz,Li Fei-Fei,Jiajun Wu,Joshua B. Tenenbaum,Daniel L. K. Yamins +10 more
TL;DR: It is shown that PSGNet outperforms alternative self-supervised scene representation algorithms at scene segmentation tasks, especially on complex real-world images, and generalizes well to unseen object types and scene arrangements.
Proceedings Article
Shape and material from sound
TL;DR: This paper builds machines to approximate human knowledge of the physical world by building an efficient, physics-based simulation engine, and presents an analysis-by-synthesis approach to infer properties of the falling object.
Journal ArticleDOI
3D Interpreter Networks for Viewer-Centered Wireframe Modeling
Jiajun Wu,Tianfan Xue,Joseph J. Lim,Yuandong Tian,Joshua B. Tenenbaum,Antonio Torralba,William T. Freeman,William T. Freeman +7 more
TL;DR: Wang et al. as mentioned in this paper proposed 3D-interpreter networks (3D-INN) to estimate 2D keypoint heatmaps and 3D object skeletons and poses from real images and synthetic 3D shapes.
Proceedings ArticleDOI
Vision-Based Manipulators Need to Also See from Their Hands
TL;DR: In this paper , the authors study how the choice of visual perspective affects learning and generalization in the context of physical manipulation from raw sensor observations and propose to regularize the third-person information stream via a variational information bottleneck.