When movie get flop it not only break the heart of movie makers but also break the chasflow of the production house and studio. Sometime production house or studio has to face bankruptcy. To avoid this big failure researchers from Fox Film Studio has come with a brilliant idea powered by Artificial Intelligence.
Fox Film Studio has developed AI powered algorithmic method that can predict what kind of audience will go to see a movie when it will released. The algorithms just do this only by analyzing movie trailers.
Trailers are very important for any upcoming movie. For audience they are the preview of any movie. Trailer gives hits to audience about storyline and what are the characters of movie. For marketing campaign and creating awareness trailers play a significant role.
And that’s why –if you make a perfect movie trailer, your movie is going to be a blockbuster.
In order to make a trailer which will loved by audience Fox Film Studio researcher built this machine learning method called Merlin Video.
Merlin Video method predicts what audiences will most likely watch a movies with the help of it’s trailer. Merlin analyze the features of the trailer such as illumination, color, faces, objects, and landscapes. After analyzing all this feature Merlin generates a dense representations of a trailer. With the help of attendance and demographic data Merlin accurately forecast the audience attendance for a movie. Merlin Video has a logistic regression layer that merges the distance-based Collaborative Filtering model to generate the probability of audience attendance.
The researchers had trained the convolutional neural network of Merlin Video on hundreds of movie trailers released in past with the millions of attendance records for each movies. By feeding appropriate representations to this neural networks, one can discover significant links between the features of the movie trailer and future audience preferences.
Merlin Video method use NVIDIA Tesla P100 GPUs on the Google Cloud, with the cuDNN-accelerated TensorFlow deep learning framework.
Merlin work well but this beauty hasn’t developed fully, it still carry some flaws. Merlin doesn’t capture temporal info.
The Fox Film Studio researchers are focusing on developing a system that uses both text and video features to predict a movie’s success.
Fox Film Studio work has published on ArXiv and was authored by Miguel Angel Campo-Rembado, SVP of Data Science & Analytics at Twentieth Century Fox Film Corp, and his team.
Have a great day, Enjoy !
For daily update subscribe to the Techgrabyte newsletter.
Read also, you may like it :