skip to main content
Language:
Search Limited to: Search Limited to: Resource type Show Results with: Show Results with: Search type Index

Skeleton-Based Human Action Recognition With Global Context-Aware Attention LSTM Networks

IEEE transactions on image processing, 2018-04, Vol.27 (4), p.1586 [Peer Reviewed Journal]

EISSN: 1941-0042 ;DOI: 10.1109/TIP.2017.2785279 ;PMID: 29324413

Digital Resources/Online E-Resources

Citations Cited by
  • Title:
    Skeleton-Based Human Action Recognition With Global Context-Aware Attention LSTM Networks
  • Author: Liu, Jun ; Wang, Gang ; Duan, Ling-Yu ; Abdiyeva, Kamila ; Kot, Alex C
  • Subjects: Algorithms ; Databases, Factual ; Human Activities - classification ; Humans ; Machine Learning ; Memory, Short-Term ; Models, Neurological ; Neural Networks (Computer) ; Pattern Recognition, Automated - methods
  • Is Part Of: IEEE transactions on image processing, 2018-04, Vol.27 (4), p.1586
  • Description: 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.
  • Publisher: United States
  • Language: English
  • Identifier: EISSN: 1941-0042
    DOI: 10.1109/TIP.2017.2785279
    PMID: 29324413
  • Source: MEDLINE
Back to results list
INSPIRE LIBRARY - TON DUC THANG UNIVERSITY (84-028) 37 755 057 Feedback
19 Nguyen Huu Tho St. Dist.7, HCM thuvien@tdtu.edu.vn

Copyright © 2017 INSPIRE LIBRARY - TON DUC THANG UNIVERSITY

Searching Remote Databases, Please Wait