• Publications
  • Influence
AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks
An Attentional Generative Adversarial Network that allows attention-driven, multi-stage refinement for fine-grained text-to-image generation and for the first time shows that the layered attentional GAN is able to automatically select the condition at the word level for generating different parts of the image.
SilentSense: silent user identification via touch and movement behavioral biometrics
In this work, 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
Just FUN: a joint fountain coding and network coding approach to loss-tolerant information spreading
Experimental results demonstrate that the proposed joint FoUntain coding and Network coding approach achieves higher throughput than the existing schemes for multihop wireless networks.
Smoothing the energy consumption: Peak demand reduction in smart grid
This work proposes a set of appliance scheduling algorithms to minimize the peak power consumption under a fixed delay requirement, and minimize the delay under aFixed peak demand constraint.
Martian: Message Broadcast via LED Lights to Heterogeneous Smartphones
A new modulation scheme and link-layer protocols for improving the network data rate are proposed and implemented, which allows smooth communication from the LED lights to a group of smartphone embedded cameras.
Distributed Large-Scale Co-Simulation for IoT-Aided Smart Grid Control
The design and implementation of a novel co-simulator, which would effectively evaluate IoT-aided algorithms for scheduling the jobs of electrical appliances and is a powerful tool for utility companies and policy makers to commission novel IoT devices or methods in future smart grid infrastructure.
Vision and Challenges for Knowledge Centric Networking
This article presents the rationale for KCN, its benefits, related works and research opportunities, and proposes leveraging emerging machine learning or deep learning techniques to create aspects of knowledge to facilitate the designs.
Distributed link scheduling for throughput maximization under physical interference model
By leveraging the partition and shifting strategies and the pick-and-compare scheme, this paper presents the first distributed link scheduling algorithm that can achieve a constant fraction of the optimal capacity region subject to physical interference constraints in the linear power setting for multihop wireless networks.
Turbo Learning for Captionbot and Drawingbot
Experimental results on the COCO dataset demonstrate that the proposed turbo learning can significantly improve the performance of both CaptionBot and DrawingBot by a large margin.
Mechanism Design for Finding Experts Using Locally Constructed Social Referral Web
This work addresses the problem of distributed expert finding using chains of social referrals and profile matching with only local information in online social networks by designing a novel truthful efficient mechanism in which an expert-finding query will be relayed by intermediate users.