H
Hang Su
Researcher at University of Massachusetts Amherst
Publications - 18
Citations - 5244
Hang Su is an academic researcher from University of Massachusetts Amherst. The author has contributed to research in topics: Computer science & Convolutional neural network. The author has an hindex of 9, co-authored 12 publications receiving 4010 citations. Previous affiliations of Hang Su include Brown University.
Papers
More filters
Proceedings ArticleDOI
Multi-view Convolutional Neural Networks for 3D Shape Recognition
TL;DR: In this article, a CNN architecture is proposed to combine information from multiple views of a 3D shape into a single and compact shape descriptor, which can be applied to accurately recognize human hand-drawn sketches of shapes.
Posted Content
Multi-view Convolutional Neural Networks for 3D Shape Recognition
TL;DR: This work presents a standard CNN architecture trained to recognize the shapes' rendered views independently of each other, and shows that a 3D shape can be recognized even from a single view at an accuracy far higher than using state-of-the-art3D shape descriptors.
Proceedings ArticleDOI
SPLATNet: Sparse Lattice Networks for Point Cloud Processing
Hang Su,Varun Jampani,Deqing Sun,Subhransu Maji,Evangelos Kalogerakis,Ming-Hsuan Yang,Jan Kautz +6 more
TL;DR: A network architecture for processing point clouds that directly operates on a collection of points represented as a sparse set of samples in a high-dimensional lattice that outperforms existing state-of-the-art techniques on 3D segmentation tasks.
Journal ArticleDOI
The SUN Attribute Database: Beyond Categories for Deeper Scene Understanding
TL;DR: It is shown that when used as features for scene classification, zero shot learning, automatic image captioning, semantic image search, and parsing natural images, low dimensional scene attributes can compete with or improve on the state of the art performance.
Proceedings ArticleDOI
Pixel-Adaptive Convolutional Neural Networks
TL;DR: In this article, a pixel-adaptive convolution (PAC) operation is proposed, in which the filter weights are multiplied with a spatially varying kernel that depends on learnable, local pixel features.