no code implementations • 7 Aug 2022 • Hieu H. Pham, Louahdi Khoudour, Alain Crouzil, Pablo Zegers, Sergio A. Velastin
Human action recognition is an important application domain in computer vision.
no code implementations • 16 Jul 2019 • Huy Hieu Pham, Houssam Salmane, Louahdi Khoudour, Alain Crouzil, Pablo Zegers, Sergio A. Velastin
In the second, we deploy the Efficient Neural Architecture Search (ENAS) algorithm to find an optimal network architecture that is used for modeling the spatio-temporal evolution of the estimated 3D poses via an image-based intermediate representation and performing action recognition.
Ranked #80 on 3D Human Pose Estimation on Human3.6M
no code implementations • 8 Jul 2019 • Huy Hieu Pham, Houssam Salmane, Louahdi Khoudour, Alain Crouzil, Pablo Zegers, Sergio A. Velastin
We achieve promising results on real conditions of this dataset with the support of data augmentation and transfer learning techniques.
no code implementations • 26 Dec 2018 • Huy-Hieu Pham, Louahdi Khoudour, Alain Crouzil, Pablo Zegers, Sergio A. Velastin
In this paper we introduce a new skeleton-based representation for 3D action recognition in videos.
no code implementations • 18 Jul 2018 • Huy Hieu Pham, Louahdi Khoudour, Alain Crouzil, Pablo Zegers, Sergio A. Velastin
For learning and recognition tasks, we design and optimize new D-CNNs based on the idea of Inception Residual networks to predict actions from SPMFs.
no code implementations • 21 Mar 2018 • Huy-Hieu Pham, Louahdi Khoudour, Alain Crouzil, Pablo Zegers, Sergio A. Velastin
In this paper, we investigate and apply deep ResNets for human action recognition using skeletal data provided by depth sensors.
no code implementations • 21 Mar 2018 • Huy-Hieu Pham, Louahdi Khoudour, Alain Crouzil, Pablo Zegers, Sergio A. Velastin
Automatic human action recognition is indispensable for almost artificial intelligent systems such as video surveillance, human-computer interfaces, video retrieval, etc.
no code implementations • 31 Oct 2016 • Eder Santana, Matthew Emigh, Pablo Zegers, Jose C. Principe
We propose a convolutional recurrent neural network, with Winner-Take-All dropout for high dimensional unsupervised feature learning in multi-dimensional time series.
no code implementations • 25 Sep 2015 • Pablo Huijse, Pablo A. Estevez, Pavlos Protopapas, Jose C. Principe, Pablo Zegers
In this article we present an overview of machine learning and computational intelligence applications to TDA.