Multimodal Video Understanding for Speeding Up Video Creation
In this talk, we will discuss a set of multimodal technologies that can help accelerate video editing and creation workflows. First, we will review core models that help users organize content based on video semantics and cinematographic properties. Second, we will dive into models that can help content creators to create engaging video sequences. We will conclude the talk by pointing out challenges, research opportunities, and a brainstorming session on how generative technologies can transform the video creation industry.
Limited seats available, so please sign up to make sure that we can reserve you a spot.