Goal

To develop machines that have the following capabilities.

Achieve deep understanding of scenes and events through joint parsing and cognitive reasoning about appearance, geometry, functions, physics, causality, intents and belief of agents, and use joint and long-ranged reasoning to fill the performance gap with human vision.

Represent visual knowledge in probabilistic compositional models across the spatial, temporal, and causal hierarchies augmented with rich relations, which are task-oriented, support efficient task-dependent inference from an agent’s perspective, and preserve uncertainties.

Acquire massive visual commonsense through web scale continuous lifelong learning from heterogeneous sources through weakly supervised HCI and dialogue with humans.

Understand human needs and values to interact with humans effectively and answer human queries about what, who, where, when, why and how in storylines through Turing tests.

Team

Principal Investigator

Song-Chun Zhu
Professor of Statistics and Computer Science
UCLA

Director of the UCLA Center for Vision, Cognition, Learning and Autonomy

Research Interest:
Computer Vision, Statistical Learning, Cognition, AI, Robot Autonomy

Members in the US

	Martial Hebert Professor of Robotics Carnegie Mellon University Director of the CMU Robotics Institute Research Interest: Computer Vision, Robotics and AI
	Abhinav Gupta Assistant Professor Carnegie Mellon University Research Interest: Computer Vision and Lifelong learning
	Nancy Kanwisher Walter A. Rosenblith Professor of Cognitive Neuroscience Department of Brain and Cognitive Sciences MIT Research Interest: Cognitive Neuroscience
	Josh Tenenbaum Professor of Computational Cognitive Science Department of Brain and Cognitive Sciences MIT Research Interest: Cognitive modeling for perception, learning, reasoning in humans and machine
	Fei-Fei Li Associate Professor of Computer Science Stanford University Director of the Stanford Artificial Intelligence Lab Research Interest: Computer Vision, Neurosciences, and Artificial Intelligence
	David Forsyth Professor of Computer Science University of Illinois at Urbana-Champaign Research Interest: Machine Learning, Graphics
	Derek Hoiem Associate Professor of Computer Science University of Illinois at Urbana-Champaign Research Interest: General visual scene understanding
	Brian Scholl Professor of Psychology and Cognitive Science Yale University Chair of the Cognitive Science Program Director of the Yale Perception & Cognition Laboratory Research Interest: Perception of Causality, Animacy, and Intentionality

Members in the UK

	Philip Torr Professor of Engineering University of Oxford Director of Torr Vision Group Research Interest: Computer Vision and Machine Learning
	Philippe Schyns Professor of Visual Cognition University of Glasgow Director of the Institute of Neuroscience and Psychology Research Interest: Rapid Scene Perception, Task-dependent categorization
	Andrew Glennerster Professor of Visual Neuroscience University of Reading Research Interest: 3D Scene Perception in high-fidelity immersive reality
	Ales Leonardis Chair Professor of Robotics University of Birmingham Co-Director of Computational Neuroscience and Cognitive Robotics Centre Research Interest: Computer Vision, Compositional Modeling, and Cognitive Robotics