Augmented Skeleton Based Contrastive Action Learning with Momentum LSTM for Unsupervised Action Recognition
Authors:
- Haocong RaoHRHaocong Rao
- Shihao XuSXShihao Xu
- Xiping HuXHXiping Hu
- Jun ChengJCJun Cheng
- Bin HuBHBin Hu
Top Cited Papers
- 1 August 2021
- journal article
- research article
- Published by Elsevier in Information Sciences
- Vol. 569, 90-109
Abstract
No abstract availableKeywords
All Related Versions
Funding Information
- National Natural Science Foundation of China
This publication has 9 references indexed in Scilit:
- A Comparative Review of Recent Kinect-Based Action Recognition AlgorithmsIEEE Transactions on Image Processing, 2019
- NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity UnderstandingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2019
- Early Action Prediction by Soft RegressionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2018
- Unsupervised Hierarchical Dynamic Parsing and Encoding for Action RecognitionIEEE Transactions on Image Processing, 2017
- Skeletal Quads: Human Action Recognition Using Joint Quadruples2014
- Extracting and composing robust features with denoising autoencoders2008
- Challenges in real-life emotion annotation and machine learning based detectionNeural Networks, 2005
- Unsupervised Learning2004
- Long Short-Term MemoryNeural Computation, 1997