The 20th Century Fox teamed up with IBM Research to create the world’s first cognitive movie trailer with the help of the AI bot IBM Watson. It chose 10 moments out of the horror flick Morgan and then a human editor stitched them to come up with a trailer.
The IBM Watson is getting better every day. Last time, we heard about it when it detected a rare form of leukemia in a patient’s body and when it was used to drive a bus. Now, doctor IBM Watson is preparing for a Hollywood debut. The supercomputer IBM Watson was used to create the trailer of the 20th Century Fox horror movie Morgan.
For a scary movie, an important thing is how a person digests it. “Our team was faced with the challenge of not only teaching a system to understand, “what is scary”, but then to create a trailer that would be considered “frightening and suspenseful” by a majority of viewers,” writes Michael Zimmerman for IBM.
Over 100 horror movie trailers were fed to the IBM Watson in order to give IBM Watson the “feel” of a horror movie. Though in reality, it is just some binary numbers for the AI bot.
The trailer videos were segmented into small moments on which IBM Watson performed an analysis of audio, video, and how each scene was composed. It helped Watson detect what scenes were depicting, for example, a frightened person or an eerie moment.
After watching the 90-minute Morgan, IBM Watson came up with 10 moments (6-minutes of total length) that “would be the best candidate for the trailer”.
The final trailer, however, required the help of a human as the AI-bot didn’t have editing capabilities. “Our system could select the moments, but it’s not an editor. We partnered with a resident IBM filmmaker to arrange and edit each of the moments together into a comprehensive trailer.”
An average time of ten to thirty days is required for the creation of a movie trailer. The editing team manually analyses every moment of the movie that could become a part of the trailer. The eligible candidates are then stitched together in such a way that it gives an overview of the movie. Watson’s involvement shrunk down the whole process to a matter of around 24 hours.
“Reducing the time of a process from weeks to hours –that is the true power of AI.”
For a scary movie, an important thing is how a person digests it. “Our team was faced with the challenge of not only teaching a system to understand, “what is scary”, but then to create a trailer that would be considered “frightening and suspenseful” by a majority of viewers,” writes Michael Zimmerman for IBM.
Over 100 horror movie trailers were fed to the IBM Watson in order to give IBM Watson the “feel” of a horror movie. Though in reality, it is just some binary numbers for the AI bot.
The trailer videos were segmented into small moments on which IBM Watson performed an analysis of audio, video, and how each scene was composed. It helped Watson detect what scenes were depicting, for example, a frightened person or an eerie moment.
After watching the 90-minute Morgan, IBM Watson came up with 10 moments (6-minutes of total length) that “would be the best candidate for the trailer”.
The final trailer, however, required the help of a human as the AI-bot didn’t have editing capabilities. “Our system could select the moments, but it’s not an editor. We partnered with a resident IBM filmmaker to arrange and edit each of the moments together into a comprehensive trailer.”
An average time of ten to thirty days is required for the creation of a movie trailer. The editing team manually analyses every moment of the movie that could become a part of the trailer. The eligible candidates are then stitched together in such a way that it gives an overview of the movie. Watson’s involvement shrunk down the whole process to a matter of around 24 hours.
“Reducing the time of a process from weeks to hours –that is the true power of AI.”
The combination of machine intelligence and human expertise is a powerful one. This research investigation is simply the first of many into what we hope will be a promising area of machine and human creativity. We don’t have the only solution for this challenge, but we’re excited about pushing the possibilities of how AI can augment the expertise and creativity of individuals.
