activity
20172022
most citedSkeleton-based Action Recognition Using LSTM and CNN

28 citations · 36 across the 5 of their papers we have counts for

collaborators

5 papers

cs.CV2022

FT-HID: A Large Scale RGB-D Dataset for First and Third Person Human Interaction Analysis

Zihui Guo, Yonghong Hou, Pichao Wang +3

Analysis of human interaction is one important research topic of human motion analysis. It has been studied either using first person vision (FPV) or third person vision (TPV). How…

cs.CV20217 cited

Trear: Transformer-based RGB-D Egocentric Action Recognition

Xiangyu Li, Yonghong Hou, Pichao Wang +3

In this paper, we propose a \textbf{Tr}ansformer-based RGB-D \textbf{e}gocentric \textbf{a}ction \textbf{r}ecognition framework, called Trear. It consists of two modules, inter-fra…

cs.CV2020

Transformer Guided Geometry Model for Flow-Based Unsupervised Visual Odometry

Xiangyu Li, Yonghong Hou, Pichao Wang +3

Existing unsupervised visual odometry (VO) methods either match pairwise images or integrate the temporal information using recurrent neural networks over a long sequence of images…

cs.CV20201 cited

SAR-NAS: Skeleton-based Action Recognition via Neural Architecture Searching

Haoyuan Zhang, Yonghong Hou, Pichao Wang +2

This paper presents a study of automatic design of neural network architectures for skeleton-based action recognition. Specifically, we encode a skeleton-based action instance into…

cs.CV201728 cited

Skeleton-based Action Recognition Using LSTM and CNN

Chuankun Li, Pichao Wang, Shuang Wang +2

Recent methods based on 3D skeleton data have achieved outstanding performance due to its conciseness, robustness, and view-independent representation. With the development of deep…