Learning Outcomes


After taking this course students will be able to:


-       Identify potential applications of recognition

-       Identify who would benefit from each application, who might be harmed, what the input data might look like, and the quality and nature of output needed.

-       Discuss the pros and cons of particular recognition tasks, benchmarks and metrics in the context of possible applications, and potentially define new ones.

-       Understand and describe the dominant technical approaches to various recognition problems : image classification, object detection, segmentation and pose estimation

-       Identify the current research challenges and their impact on the actual applications.


-       Identify potential applications of reconstruction, and describe benefits, harms, nature of input data and quality and nature of needed output

-       Derive equations describing image formation and various invariants thereof (e.g., epipolar constraint)

-       Describe the classical approaches based on estimating correspondence and define the key challenges involved.

-       Describe modern end-to-end approaches and their benefits and limitations.

-       Discuss the pros and cons of various representations of 3D shape

(Embodied cognition)

-       Define what computer vision means for embodied agent, and articulate how this is different from other applications previously encountered

-       Describe research challenges in computer vision for embodied agents, including those of learning, control and interaction with humans

(How to do computer vision research)

-       Concretely identify a research question of significance

-       Review prior work and crisply identify limitations

-       Design new solutions to address identified limitations

-       Evaluate and audit the proposed solution with the actual application and potential ethical considerations in mind.

-       Provide feedback and guidance to peer researchers.

-       Write a technical paper that can be accepted to a workshop or conference.