Skeleton-Based Online Action Prediction Using Scale Selection Network

• Published in: IEEE transactions on pattern analysis and machine intelligence Vol. 42; no. 6; pp. 1453 - 1467
• Main Authors: Liu, Jun, Shahroudy, Amir, Wang, Gang, Duan, Ling-Yu, Kot, Alex C.
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.06.2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Action prediction; dilated convolution; Microsoft Windows; Pattern recognition; Real-time systems; scale selection; Skeleton; skeleton data; sliding window; Task analysis; Three-dimensional displays; Videos

Action prediction is to recognize the class label of an ongoing activity when only a part of it is observed. In this paper, we focus on online action prediction in streaming 3D skeleton sequences. A dilated convolutional network is introduced to model the motion dynamics in temporal dimension via a...