Learning Snippet Relatedness Based on LSTM for Temporal Action Proposal Generation 


Vol. 45,  No. 6, pp. 975-978, Jun.  2020
10.7840/kics.2020.45.6.975


PDF Full-Text
  Abstract

Recent temporal action proposal generation approaches are based on temporal convolutional networks. In this paper, different from this, we propose to use LSTM for sequential modeling on actions. The propose method based on LSTM evaluates snippet relatedness to define temporal action intervals. Snippet relatedness indicates which snippets are included in the same action instance. By conducting experiments on the THUMOS-14 dataset, we demonstrate the superiority of the proposed method. We also analyze our method in diverse aspects.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Cite this article

[IEEE Style]

H. Eun, J. Moon, J. Park, C. Jung, C. Kim, "Learning Snippet Relatedness Based on LSTM for Temporal Action Proposal Generation," The Journal of Korean Institute of Communications and Information Sciences, vol. 45, no. 6, pp. 975-978, 2020. DOI: 10.7840/kics.2020.45.6.975.

[ACM Style]

Hyunjun Eun, Jinyoung Moon, Jongyoul Park, Chanho Jung, and Changick Kim. 2020. Learning Snippet Relatedness Based on LSTM for Temporal Action Proposal Generation. The Journal of Korean Institute of Communications and Information Sciences, 45, 6, (2020), 975-978. DOI: 10.7840/kics.2020.45.6.975.

[KICS Style]

Hyunjun Eun, Jinyoung Moon, Jongyoul Park, Chanho Jung, Changick Kim, "Learning Snippet Relatedness Based on LSTM for Temporal Action Proposal Generation," The Journal of Korean Institute of Communications and Information Sciences, vol. 45, no. 6, pp. 975-978, 6. 2020. (https://doi.org/10.7840/kics.2020.45.6.975)

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880