activity
20172021
most citedSTFNets: Learning Sensing Signals from the Time-Frequency Perspective with Short-Time Fourier Neural Networks

71 citations · 162 across the 9 of their papers we have counts for

collaborators

12 papers

cs.SI2021

DyDiff-VAE: A Dynamic Variational Framework for Information Diffusion Prediction

Ruijie Wang, Zijie Huang, Shengzhong Liu +7

This paper describes a novel diffusion model, DyDiff-VAE, for information diffusion prediction on social media. Given the initial content and a sequence of forwarding users, DyDiff…

cs.DC2021

CrossRoI: Cross-camera Region of Interest Optimization for Efficient Real Time Video Analytics at Scale

Hongpeng Guo, Shuochao Yao, Zhe Yang +2

Video cameras are pervasively deployed in city scale for public good or community safety (i.e. traffic monitoring or suspected person tracking). However, analyzing large scale vide…

cs.LG20201 cited

Scheduling Real-time Deep Learning Services as Imprecise Computations

Shuochao Yao, Yifan Hao, Yiran Zhao +6

The paper presents an efficient real-time scheduling algorithm for intelligent real-time edge services, defined as those that perform machine intelligence tasks, such as voice reco…

cs.LG20202 cited

ControlVAE: Tuning, Analytical Properties, and Performance Analysis

Huajie Shao, Zhisheng Xiao, Shuochao Yao +3

This paper reviews the novel concept of controllable variational autoencoder (ControlVAE), discusses its parameter tuning to meet application needs, derives its key analytic proper…

cs.LG2020

A Spherical Hidden Markov Model for Semantics-Rich Human Mobility Modeling

Wanzheng Zhu, Chao Zhang, Shuochao Yao +2

We study the problem of modeling human mobility from semantic trace data, wherein each GPS record in a trace is associated with a text message that describes the user's activity. E…

cs.LG20205 cited

DynamicVAE: Decoupling Reconstruction Error and Disentangled Representation Learning

Huajie Shao, Haohong Lin, Qinmin Yang +3

This paper challenges the common assumption that the weight , in -VAE, should be larger than in order to effectively disentangle latent factors. We demonstrate that -V…