Knowledge Representation, Reasoning and Learning for Understanding Scenes and Events
The MURI team consists of leaders in human and computer vision, AI and reasoning, cognitive science, and statistical machine learning, with a common agenda and global vision. The objective is to develop automated computer vision systems that are capable of the following:
- Understanding objects, scenes and events from images and videos in uncertain environments;
- Reasoning about the functions and roles of objects, the goals and intents of the agents in the scenes;
- Predicting the outcomes of unfolding events; and finally
- Answering the human queries centered on the: “who”, “what”, “when”, “where”, and “why” of a given scene.
This work is supported by the Office of Naval Research grant N000141010933