Albert Boyang Li is a Senior Research Scientist at Baidu Research, where he conducts research on Artificial Intelligence and Machine Learning. He’s particularly interested in computational models for narrative structures, including visual and textual information. He believes story is a powerful tool for communication. His Computational Narrative Intelligence (CNI) aims to create intelligent machines that can understand and create stories, manage interactive narratives, and respond appropriately to stories told to them. In his talk, Albert addresses at these points:
1. The way viewers interact with TV shows and movies has changed little in the past 60 years or so.
2. Automatic understanding of video and story content would enable new interaction paradigms, such as intelligent fast-forwarding with summarization.
3. New algorithms can compute the versatility of actors and their similarity from metadata (paper submitted to AAAI 2018).
4. New algorithms can align video and textual data, which are abundant in the traditional production process but could not be jointly understood (paper published at CVPR 2018).