Great work Gabe!
Incredible job, love the breakdown and can't wait to see what you make next!
NVIDIA has shared a nice article that shows the way 20th Century Fox uses deep learning to predict a film’s audience from trailers. The system is said to be trained on historical movie attendance records to “find non-trivial associations between the video trailer features, and future audiences choices after the movie releases in theatres or on streaming services”. The whole analysis focuses on extracting features like “color, illumination, faces, objects, and landscapes” to predict accurate attendance for existing movies, and the team plans to use for future movies.
“Video trailers are the single most critical element of the marketing campaigns for new films,” the Fox researchers stated in their paper. “They increase awareness among the general moviegoer population, communicate the plot of the movie, present the main characters, and reveal important hints about the story, the tone, and the cinematographic choices.”
Using NVIDIA Tesla P100 GPUs on the Google Cloud, with the cuDNN-accelerated TensorFlow deep learning framework, the researchers trained their convolutional neural network on hundreds of movie trailers released over the last years, as well as millions of attendance records.
For inference, the team uses the same GPUs used during training.
“By finding a suitable representation of these features, and by feeding them to a model that has access to historical movie attendance records, it is possible to find non-trivial associations between the video trailer features, and future audiences choices after the movie releases in theaters or on streaming services,” the researchers stated.
The neural network has the potential to assist movie producers and executives make real-world decisions at different stages of a marketing campaign, the researchers said.