• Publications
  • Influence
Discrete Signal Processing on Graphs
In social settings, individuals interact through webs of relationships. Each individual is a node in a complex network (or graph) of interdependencies and generates data, lots of data. We label theExpand
  • 923
  • 177
  • PDF
Visual Dialog
TLDR
We introduce the task of Visual Dialog, which requires an AI agent to hold a meaningful dialog with humans in natural, conversational language about visual content. Expand
  • 352
  • 62
  • PDF
Discrete Signal Processing on Graphs: Frequency Analysis
TLDR
We propose a definition of total variation for graph signals that naturally leads to a frequency ordering on graphs and defines low-, high-, and band-pass graph signals and filters. Expand
  • 501
  • 60
  • PDF
SPIRAL: Code Generation for DSP Transforms
TLDR
SPIRAL automatically generates high-performance code that is tuned to the given platform. Expand
  • 850
  • 50
  • PDF
Big Data Analysis with Signal Processing on Graphs: Representation and processing of massive data sets with irregular structure
TLDR
Analysis and processing of very large data sets, or big data, poses a significant challenge. Expand
  • 457
  • 27
  • PDF
Adversarial Geometry-Aware Human Motion Prediction
TLDR
We explore an approach to forecasting human motion in a few milliseconds given an input 3D skeleton sequence based on a recurrent encoder-decoder framework by incorporating local geometric structure constraints and regularizing predictions with plausible temporal smoothness and continuity from a global perspective. Expand
  • 79
  • 24
  • PDF
Adversarial Multiple Source Domain Adaptation
TLDR
We propose multisource domain adversarial networks (MDAN) that approach domain adaptation by optimizing task-adaptive generalization bounds. Expand
  • 132
  • 21
  • PDF
Visual Dialog
TLDR
We introduce the task of Visual Dialog, which requires an AI agent to hold a meaningful dialog with humans in natural, conversational language about visual content. Expand
  • 116
  • 20
Distributed Consensus Algorithms in Sensor Networks With Imperfect Communication: Link Failures and Channel Noise
TLDR
We show that A-ND represents the best of both worlds-zero bias and low variance-at the cost of a slow convergence rate; rescaling the weights balances the variance versus the rate of bias reduction (convergence rate). Expand
  • 590
  • 19
  • PDF
Gossip Algorithms for Distributed Signal Processing
TLDR
Gossip algorithms are attractive for in-network processing in sensor networks because they do not require any specialized routing, there is no bottleneck or single point of failure, and they are robust to unreliable wireless network conditions. Expand
  • 748
  • 16
  • PDF
...
1
2
3
4
5
...