LogisticsWhere: Zoom Instructor: Yuxiong Wang TA: Amnon Attali Practice presentation: Zoom UpdatesOverviewSummary: This course will cover advanced research topics in computer vision, with emphasis on recognition tasks and deep learning. Building on the introductory materials in CS 543 (Computer Vision), this course will prepare graduate students in both the theoretical foundations of computer vision and the state-of-the-art approaches to building real-world computer vision systems. We will investigate data sources, model architectures, and learning algorithms that are useful for understanding and manipulating visual data. This course will start by focusing on representation and reasoning for large amounts of data (images, videos, 3D point clouds, associated tags, text, gps-locations, etc). We will then in particular discuss recent efforts towards visual learning and reasoning with less human supervision. Students will be required to read, present, critique, and discuss research papers and perform a related research project. By the end of the course, students will be able to understand and implement the state-of-the-art algorithms as well as identify important open questions and future research directions. Students will be also ready to conduct research in computer vision and its relevant domains such as robotics. Prerequisites: Awards: At the end of the course, we will vote for:
People
Academic Integrity Policy
Credits and AcknowledgmentI gratefully thank Abhinav Gupta, Lana Lazebnik, Alyosha Efros, James Hays, and Judy Hoffman for borrowing much of their course design and slides. |