activity
20172025
most citedTwo-Stream 3D Convolutional Neural Network for Skeleton-Based Action Recognition

111 citations · 117 across the 3 of their papers we have counts for

collaborators

5 papers

cs.CV20251 cited

TCPFormer: Learning Temporal Correlation with Implicit Pose Proxy for 3D Human Pose Estimation

Jiajie Liu, Mengyuan Liu, Hong Liu +1

Recent multi-frame lifting methods have dominated the 3D human pose estimation. However, previous methods ignore the intricate dependence within the 2D pose sequence and learn sing…

cs.CV2019

RefineDetLite: A Lightweight One-stage Object Detection Framework for CPU-only Devices

Chen Chen, Mengyuan Liu, Xiandong Meng +2

Previous state-of-the-art real-time object detectors have been reported on GPUs which are extremely expensive for processing massive data and in resource-restricted scenarios. Ther…

eess.IV2018

Self-Refining Deep Symmetry Enhanced Network for Rain Removal

Hong Liu, Hanrong Ye, Xia Li +3

Rain removal aims to remove the rain streaks on rain images. The state-of-the-art methods are mostly based on Convolutional Neural Network~(CNN). However, as CNN is not equivariant…

cs.CV20175 cited

Robust 3D Action Recognition through Sampling Local Appearances and Global Distributions

Mengyuan Liu, Hong Liu, Chen Chen

3D action recognition has broad applications in human-computer interaction and intelligent surveillance. However, recognizing similar actions remains challenging since previous lit…

cs.CV2017111 cited

Two-Stream 3D Convolutional Neural Network for Skeleton-Based Action Recognition

Hong Liu, Juanhui Tu, Mengyuan Liu

It remains a challenge to efficiently extract spatialtemporal information from skeleton sequences for 3D human action recognition. Although most recent action recognition methods a…