Action Recognition Network Using Stacked Short-Term Deep Features and Bidirectional Moving Average
Action recognition requires the accurate analysis of action elements in the form of a video clip and a properly ordered sequence of the elements. To solve the two sub-problems, it is necessary to learn both spatio-temporal information and the temporal relationship between different action elements....
Main Authors: | Jinsol Ha, Joongchol Shin, Hasil Park, Joonki Paik |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-06-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/11/12/5563 |
Similar Items
-
MODIFIED MOVING-AVERAGE METHOD IN PROBLEMS OF SHORT-TERM FORECASTING OF TECHNICAL AND ECONOMIC INDICATORS IN HIGH-TECHNOLOGY ENTERPRISES
by: Igor I. KOVALENKO, et al.
Published: (2016-02-01) -
New modified exponentially weighted moving average-moving average control chart for process monitoring
by: Khanittha Talordphop, et al.
Published: (2022-12-01) -
A Predictive Study of Electricity Consumption Fluctuations Using the Autoregressive-Moving-Average Models: Wilaya of Medea as a Case Study (2011-2017)
by: Chermat Tahar, et al.
Published: (2019-03-01) -
Nonparametric mixed exponentially weighted moving average-moving average control chart
by: Muhammad Ali Raza, et al.
Published: (2024-03-01) -
On designing new mixed modified exponentially weighted moving average - exponentially weighted moving average control chart
by: Khanittha Talordphop, et al.
Published: (2023-06-01)