activity
20172022
most citedSkeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gates

9 citations · 12 across the 4 of their papers we have counts for

collaborators

5 papers

cs.CV20222 cited

Revisiting Deep Semi-supervised Learning: An Empirical Distribution Alignment Framework and Its Generalization Bound

Feiyu Wang, Qin Wang, Wen Li +2

In this work, we revisit the semi-supervised learning (SSL) problem from a new perspective of explicitly reducing empirical distribution mismatch between labeled and unlabeled samp…

cs.GT20201 cited

A Hybrid Simulation-based Duopoly Game Framework for Analysis of Supply Chain and Marketing Activities

Dong Xu, Chao Meng, Qingpeng Zhang +2

A hybrid simulation-based framework involving system dynamics and agent-based simulation is proposed to address duopoly game considering multiple strategic decision variables and r…

cs.SE2020

Dynamic Scheduling and Workforce Assignment in Open Source Software Development

Hui Xi, Dong Xu, Young-Jun Son

A novel modeling framework is proposed for dynamic scheduling of projects and workforce assignment in open source software development (OSSD). The goal is to help project managers…

eess.IV2018

DVC: An End-to-end Deep Video Compression Framework

Guo Lu, Wanli Ouyang, Dong Xu +3

Conventional video compression approaches use the predictive coding architecture and encode the corresponding motion information and residual information. In this paper, taking adv…

cs.CV20179 cited

Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gates

Jun Liu, Amir Shahroudy, Dong Xu +2

Skeleton-based human action recognition has attracted a lot of research attention during the past few years. Recent works attempted to utilize recurrent neural networks to model th…