• Publications
  • Influence
Fused-layer CNN accelerators
TLDR
Deep convolutional neural networks (CNN) are rapidly becoming the dominant approach to computer vision and a major component of many other pervasive machine learning tasks, such as speech recognition, natural language processing, and fraud detection. Expand
  • 262
  • 34
  • PDF
Building and Using A Scalable Display Wall System
TLDR
We describe our approach to research challenges in several specific research areas, including seamless tiling, parallel rendering, parallel data visualization, parallel MPEG decoding, layered multiresolution video input, multichannel immersive sound, user interfaces, application tools, and content creation. Expand
  • 227
  • 10
  • PDF
Garaph: Efficient GPU-accelerated Graph Processing on a Single Machine with Balanced Replication
TLDR
We present Garaph, a GPU-accelerated graph processing system on a single machine with secondary storage as memory extension. Expand
  • 33
  • 8
  • PDF
Scalable alignment of large-format multi-projector displays using camera homography trees
TLDR
This paper presents a vision-based geometric alignment system for aligning the projectors in an arbitrarily large display wall that achieves sub-pixel accuracy even on displays with hundreds of projectors. Expand
  • 184
  • 7
  • PDF
Improved two-dimensional DOA estimation algorithm for two-parallel uniform linear arrays using propagator method
TLDR
We propose an improved two-dimensional direction-of-arrival estimation algorithm for two-parallel uniform linear arrays using PM. Expand
  • 69
  • 7
Non-Convex Projected Gradient Descent for Generalized Low-Rank Tensor Regression
TLDR
In this paper we provide a general framework that provides theoretical guarantees for learning high-dimensional tensor regression models under different low-rank structural assumptions using the projected gradient descent algorithm applied to a potentially non-convex constraint set $\Theta$. Expand
  • 23
  • 6
  • PDF
Lagrange multipliers and maximum information leakage in different observational models
TLDR
This paper explores two fundamental issues in Language based security. Expand
  • 88
  • 5
  • PDF
A Scalable and Elastic Publish/Subscribe Service
TLDR
The rapid growth of sense-and-respond applications and the emerging cloud computing model present a new challenge: providing publish/subscribe as a scalable and elastic cloud service. Expand
  • 96
  • 4
  • PDF
Steerable interfaces for pervasive computing spaces
TLDR
This paper introduces a new class of interactive interfaces that can be moved around to appear on ordinary objects and surfaces anywhere in a space. Expand
  • 76
  • 4
  • PDF
Carbon dynamics of aboveground live vegetation of boreal mixedwoods after wildfire and clear-cutting
Live vegetation carbon (C) pool dynamics are central to understanding C sequestration of forest ecosystems. Despite its importance, how aboveground live C pools change with stand development inExpand
  • 24
  • 4
...
1
2
3
4
5
...