Automatic trailer generation for movies using convolutional neural network.

In this paper, a new method for producing movie trailers is presented. In the proposed method, the problem is divided into two sub-problems: "genre identification" and "genre-based trailer production". To solve the first sub-problem, the poster image and subtitle text processing strategy has been used in which, a convolutional neural network (CNN) model has been used to extract features related to the movie genre from its poster image.

Dimensionless analysis-based permeability model of reinforced concrete under tension.

Water permeability of reinforced concrete is essential for transportation of ingress ions inside concrete structures. The coupling effect of permeability and loading presents a challenge for the experimental simulation of water-permeate reinforced concrete subjected to tension. This renders the development of the model based on dimensionless analysis, using a series of experimental tests from an innovative experimental system that allows simultaneous measurement of permeability and crack width.