Action Recognition With Spatio-Temporal Visual Attention on Skeleton Image Sequences

• Published in: IEEE transactions on circuits and systems for video technology Vol. 29; no. 8; pp. 2405 - 2415
• Main Authors: Yang, Zhengyuan, Li, Yuncheng, Yang, Jianchao, Luo, Jiebo
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.08.2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Action and activity recognition; Architecture; Artificial neural networks; Aspect ratio; Datasets; human analysis; Image enhancement; Image recognition; Image sequences; Joints (anatomy); Object recognition; Optical imaging; Performance enhancement; Representations; Semantics; Skeleton; Three-dimensional displays; Two dimensional displays; video understanding; visual attention; Visualization

Action recognition with 3D skeleton sequences became popular due to its speed and robustness. The recently proposed convolutional neural networks (CNNs)-based methods show a good performance in learning spatio-temporal representations for skeleton sequences. Despite the good recognition accuracy ach...