In recent years, deep learning has completely revolutionized the fields of computer vision, speech recognition and natural language processing. Despite breakthroughs in all three fields, one common barrier for training neural networks to solve real-world problems remains the amount of labeled training data that is required to train a model. In some domains, like video understanding, gathering real world data can be prohibitively expensive and time consuming in the absence of innovative solutions.
Video viewability is a top priority for video publishers who are under pressure to verify that their audience is actually watching advertisers' content. In a previous post How Deep Learning Video Sequence Drives Profits, we demonstrated why image sequences draw consumer attention. Advanced technologies such as Deep Learning are increasing video Viewability through identifying and learning which images make people stick to content. This content intelligence is the foundation for advancing video machine learning and improving overall video performance. In this post, we will explore some challenges in viewability and how deep learning is boosting video watch rates.
Loads of devices can preserve moments on camera, but what if you could capture situations that were about to happen? It's not as far-fetched as you might think. MIT CSAIL researchers have crafted a deep learning algorithm that can create videos showing what it expects to happen in the future. After extensive training (2 million videos), the AI system generates footage by pitting two neural networks against each other. One creates the scene by determining which objects are moving in still frames.
MIT has created a system that generates video based on still photos. MIT has used machine learning to create video from still images, and the results are pretty impressive. As you can see from the above image, there's a lot of natural form to the movement in the videos. The system "learns" types of videos (beach, baby, golf swing...) and, starting from still images, replicates the movements that are most commonly seen in those videos. So the beach video looks like it has crashing waves, for instance.
Can't pop-lock or Lindy Hop to save your life? Don't worry -- AI could soon make it look like you're a dance superstar. UC Berkeley researchers have developed a deep learning system that translates dance moves from a source video to less-than-experienced subjects. One algorithm creates a virtual skeleton to map poses, while two more algorithms square off against each other to both create the full picture and create a more realistic face for subjects as their virtual bodies twirl around. You do need the test subject to move around for a short while to get reference material, but the result is realistic enough to give an amateur the deftness of a ballet dancer.