Focalized contrastive view-invariant learning for self-supervised skeleton-based action recognition
Authors:
- Qianhui MenQMQianhui Men
- Edmond S.L. HoEHEdmond S.L. Ho
- Hubert P.H. ShumHSHubert P.H. Shum
- Howard LeungHLHoward Leung
- 31 March 2023
- journal article
- research article
- Published by Elsevier in Neurocomputing
- Vol. 537, 198-209
Abstract
No abstract availableKeywords
All Related Versions
Funding Information
- Engineering and Physical Sciences Research Council
- Royal Society (IES\R1\191147, IES\R2\181024)
- City University of Hong Kong (9678139)
- Ministry of Defence
- Defence and Security Accelerator
This publication has 48 references indexed in Scilit:
- Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks2017
- Ensemble Deep Learning for Skeleton-Based Action Recognition Using Temporal Sliding LSTM Networks2017
- Enhanced skeleton visualization for view invariant human action recognitionPattern Recognition, 2017
- A New Representation of Skeleton Sequences for 3D Action Recognition2017
- Deep Representation Learning for Human Motion Prediction and Classification2017
- NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis2016
- Learning motion manifolds with convolutional autoencoders2015
- Cross-View Action Modeling, Learning, and Recognition2014
- HOPC: Histogram of Oriented Principal Components of 3D Pointclouds for Action Recognition2014
- View invariant human action recognition using histograms of 3D joints2012