Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/142304
Title: Skeleton-based human action recognition with global context-aware attention LSTM networks
Authors: Liu, Jun
Wang, Gang
Duan, Ling-Yu
Abdiyeva, Kamila
Kot, Alex Chichung
Keywords: Engineering::Computer science and engineering
Issue Date: 2017
Source: Liu, J., Wang, G., Duan, L.-Y., Abdiyeva, K., & Kot, A. C. (2018). Skeleton-based human action recognition with global context-aware attention LSTM networks. IEEE Transactions on Image Processing, 27(4), 1586-1599. doi:10.1109/TIP.2017.2785279
Journal: IEEE Transactions on Image Processing
Abstract: Human action recognition in 3D skeleton sequences has attracted a lot of research attention. Recently, long short-term memory (LSTM) networks have shown promising performance in this task due to their strengths in modeling the dependencies and dynamics in sequential data. As not all skeletal joints are informative for action recognition, and the irrelevant joints often bring noise which can degrade the performance, we need to pay more attention to the informative ones. However, the original LSTM network does not have explicit attention ability. In this paper, we propose a new class of LSTM network, global context-aware attention LSTM, for skeleton-based action recognition, which is capable of selectively focusing on the informative joints in each frame by using a global context memory cell. To further improve the attention capability, we also introduce a recurrent attention mechanism, with which the attention performance of our network can be enhanced progressively. Besides, a two-stream framework, which leverages coarse-grained attention and fine-grained attention, is also introduced. The proposed method achieves state-of-the-art performance on five challenging datasets for skeleton-based action recognition.
URI: https://hdl.handle.net/10356/142304
ISSN: 1057-7149
DOI: 10.1109/TIP.2017.2785279
Rights: © 2017 IEEE. All rights reserved.
Fulltext Permission: none
Fulltext Availability: No Fulltext
Appears in Collections:EEE Journal Articles

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.