• Publications
  • Influence
AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks
TLDR
We propose an Attentional Generative Adversarial Network (AttnGAN) that allows attention-driven, multi-stage refinement for fine-grained text-to-image generation. Expand
  • 459
  • 91
  • PDF
Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation
TLDR
We propose a novel Reinforced Cross-Modal Matching (RCM) approach that enforces cross-modal grounding both locally and globally via reinforcement learning (RL). Expand
  • 124
  • 24
  • PDF
SilentSense: silent user identification via touch and movement behavioral biometrics
TLDR
We present SilentSense, a framework to authenticate users silently and transparently by exploiting the user touch behavior biometrics and leveraging the integrated sensors to capture the micro-movement of the device caused by user's screen-touch actions. Expand
  • 181
  • 18
  • PDF
Object-Driven Text-To-Image Synthesis via Adversarial Training
TLDR
We propose Object-driven Attentive Generative Adversarial Newtorks (Obj-GANs) that allow attention-driven, multi-stage refinement for synthesizing complex images from text descriptions. Expand
  • 78
  • 15
  • PDF
Hierarchically Structured Reinforcement Learning for Topically Coherent Visual Story Generation
TLDR
We propose a hierarchically structured reinforcement learning approach to address the challenges of planning for generating coherent multi-sentence stories for the visual storytelling task. Expand
  • 39
  • 5
  • PDF
Smoothing the energy consumption: Peak demand reduction in smart grid
TLDR
We propose a set of appliance scheduling algorithms to minimize the peak power consumption under a bounded delay constraint and minimize the delay under a fixed peak demand constraint. Expand
  • 51
  • 4
  • PDF
Just FUN: a joint fountain coding and network coding approach to loss-tolerant information spreading
TLDR
This paper proposes a joint FoUntain coding and Network coding (FUN) approach to address the problem of information spreading over lossy communication channels. Expand
  • 33
  • 4
  • PDF
Generating Diverse and Accurate Visual Captions by Comparative Adversarial Learning
TLDR
We study how to generate captions that are not only accurate in describing an image but also discriminative across different images. Expand
  • 31
  • 3
  • PDF
Martian: Message Broadcast via LED Lights to Heterogeneous Smartphones
TLDR
We propose a new modulation scheme and design link-layer protocols for improving the network data rate. Expand
  • 8
  • 3
  • PDF
Distributed Large-Scale Co-Simulation for IoT-Aided Smart Grid Control
TLDR
We demonstrate the design and implementation of a novel co-simulator, which would effectively evaluate IoT-aided algorithms for scheduling the jobs of electrical appliances. Expand
  • 17
  • 2