Yang Yi, Yang Sun, Saimei Yuan, Yiji Zhu, Mengyi Zhang and Wenjun Zhu
The purpose of this paper is to provide a fast and accurate network for spatiotemporal action localization in videos. It detects human actions both in time and space…
Abstract
Purpose
The purpose of this paper is to provide a fast and accurate network for spatiotemporal action localization in videos. It detects human actions both in time and space simultaneously in real-time, which is applicable in real-world scenarios such as safety monitoring and collaborative assembly.
Design/methodology/approach
This paper design an end-to-end deep learning network called collaborator only watch once (COWO). COWO recognizes the ongoing human activities in real-time with enhanced accuracy. COWO inherits from the architecture of you only watch once (YOWO), known to be the best performing network for online action localization to date, but with three major structural modifications: COWO enhances the intraclass compactness and enlarges the interclass separability in the feature level. A new correlation channel fusion and attention mechanism are designed based on the Pearson correlation coefficient. Accordingly, a correction loss function is designed. This function minimizes the same class distance and enhances the intraclass compactness. Use a probabilistic K-means clustering technique for selecting the initial seed points. The idea behind this is that the initial distance between cluster centers should be as considerable as possible. CIOU regression loss function is applied instead of the Smooth L1 loss function to help the model converge stably.
Findings
COWO outperforms the original YOWO with improvements of frame mAP 3% and 2.1% at a speed of 35.12 fps. Compared with the two-stream, T-CNN, C3D, the improvement is about 5% and 14.5% when applied to J-HMDB-21, UCF101-24 and AGOT data sets.
Originality/value
COWO extends more flexibility for assembly scenarios as it perceives spatiotemporal human actions in real-time. It contributes to many real-world scenarios such as safety monitoring and collaborative assembly.
Details
Keywords
Ninghua Sun and Lei Zeng
China's economic transition is essentially the process of China's institutional changes. During the changes, the appearance of institutional innovation is not regular; instead, it…
Abstract
Purpose
China's economic transition is essentially the process of China's institutional changes. During the changes, the appearance of institutional innovation is not regular; instead, it is intermittent and random. The purpose of this paper is to show that the fitful appearance of institutional innovation is the root of China's economic growth and fluctuations.
Design/methodology/approach
This paper constructs a real business cycle (RBC) model introducing the institutional factor expressed in the quantitative form under the dynamic stochastic general equilibrium (DSGE) framework by measuring China's institutional changes quantitatively.
Findings
By comparing the characteristics of the actual economic data with those of the simulated economic data, we find that this RBC model can explain 94.44%, 66.07%, 23.46%, 21.03% and 15.45% of the cyclical fluctuations in output, investment, labor, consumption and capital, respectively.
Originality/value
The impulse response analysis finds that the institutional shocks have a relatively long duration, lasting about 30 years, and decline slowly over time, while technological shocks decline relatively fast, lasting approximately ten years.