Not stated in source
2018 Needs review
Deep learning for action recognition and prediction
Abstract
This thesis proposes novel deep leaning solutions for real-world applications, including action recognition and prediction from videos. The first part leverages Convolutional Neural Networks (CNN) to learn deep spatial-temporal information of skeleton sequences for action recognition. The second part presents three new methods based on CNN and Recurrent Neural Networks for action prediction. The last part of this thesis presents a new feature extraction method based on CNN for better person reidentification. Extensive experiments have shown the superiority of the proposed methods compared to state of-the-art methods for action recognition, action prediction and person re-identification.
Keywords
Not available
Specialisations
Similar theses
- Video-based similar gesture action recognition using deep learning and GAN-based approaches Di Wu · University of Technology Sydney · 2019
- Deep learning approaches for yield prediction and crop disease recognition Luning Bi · Iowa State University · 2022
- Deep Learning Methods for Human Action Recognition Zeqi Yu · Auckland University of Technology · 2021
- DeepSR a Deep Learning Neural Network for Speech Reading Basuki Winoto · Harvard University · 2020
- Deep learning with synthetic, temporal, and adversarial supervision Ankush Gupta · University of Oxford · 2018
- Deep Learning-Based Text Detection and Recognition Qingqing Wang · University of Technology Sydney · 2020
