Work

Action Recognition Based on Joint Trajectory Maps Using Convolutional Neural Networks

Year: 2016

Type: conference-paper

Abstract: Recently, Convolutional Neural Networks (ConvNets) have shown promising performances in many computer vision tasks, especially image-based recognition. How to effectively use ConvNets for video-based recognition is still an open problem. In this paper, we propose a compact, effective yet simple method to encode spatio-temporal information carried in 3D skeleton sequences into multiple 2D images, referred to as Joint Trajectory Maps (JTM), and ConvNets are adopted to exploit the discriminative features for real-time human action recognition. The proposed method has been evaluated on three public benchmarks, i.e., MSRC-12 Kinect gesture dataset (MSRC-12), G3D dataset and UTD multimodal human action dataset (UTD-MHAD) and achieved the state-of-the-art results.

Source: ACM International Conference on Multimedia (ACM MM)

DOI: 10.1145/2964284.2967191

Authors: Pichao Wang, Zhaoyang Li, Yonghong Hou, Wanqing Li

Institutions: University of Wollongong, Tianjin University

Language: English

Topic: Human Pose and Action Recognition

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: National Natural Science Foundation of China

Award: 用户体验质量驱动的立体视频可靠传输理论与技术研究