JM Chaquet, EJ Carmona… - Computer Vision and …, 2013 - Elsevier
Vision-based human action and activity recognition has an increasing importance among the computer vision community with applications to visual surveillance, video retrieval and …
In recent years, there has been a proliferation of works on human action classification from depth sequences. These works generally present methods and/or feature representations …
We propose a function-based temporal pooling method that captures the latent structure of the video sequence data-eg, how frame-level features evolve over time in a video. We show …
Human activity recognition is central to many practical applications, ranging from visual surveillance to gaming interfacing. Most approaches addressing this problem are based on …
X Zhang, Y Wang, M Gou… - Proceedings of the …, 2016 - openaccess.thecvf.com
In this paper we propose a new framework to compare and classify temporal sequences. The proposed approach captures the underlying dynamics of the data while avoiding …
Most popular deep models for action recognition split video sequences into short sub- sequences consisting of a few frames; frame-based features are then pooled for recognizing …
H Wang, C Yuan, W Hu, C Sun - Pattern Recognition, 2012 - Elsevier
In this paper, we propose a new supervised classification method based on a modified sparse model for action recognition. The main contributions are three-fold. First, a novel …
Sparsity-based representations have recently led to notable results in various visual recognition tasks. In a separate line of research, Riemannian manifolds have been shown …
PK Singh, S Kundu, T Adhikary, R Sarkar… - … Methods in Engineering, 2021 - Springer
Abstract Human Action Recognition (HAR) has achieved a remarkable milestone in the field of computer vision. Apart from its varied applications in human–computer interactions …