Program Overview

CAP6412 – Spring 2020

Advanced Computer Vision (3 Credit Hours)

This is an Advanced Computer Vision course that exposes graduate students to cutting-edge research. In each class, one recent research paper related to active areas of current research, in particular employing Deep Learning, is discussed. Computer vision has been a very active area of research for many decades, and researchers have been working on solving important challenging problems. During the last few years, Deep Learning involving Artificial Neural Networks has been a disruptive force in computer vision. Employing deep learning, tremendous progress has been made in a very short time in solving difficult problems, and very impressive results have been obtained in image and video classification, localization, semantic segmentation, etc. New techniques, datasets, hardware, and software libraries are emerging almost every day. Deep Computer vision is impacting research in Robotics, Natural Language understanding, Computer Graphics, multi-modal analysis, etc.

Course Contents

The course will cover the following topics:

• Generative Adversarial Networks (GAN)
• Self-supervised Learning
• Semi and Unsupervised Learning
• Human Action and Activity Recognition
• Vision and Language

Textbook

There is no textbook for this class. Recent research papers will be discussed. A recommended supplemental textbook is:

• Ian Goodfellow, Yoshua Bengio, Aaron Courville. Deep Learning.

Meeting Format

The class will meet twice a week for a 75-minute lecture, taught by the instructor.

Grading Policy

The grading policy is as follows:

• Reports: 20%
• Presentation: 20%
• Attendance and Discussion: 20%
• Projects/Programs: 40%

Late Policy

The late policy is as follows:

• 0 for late Reports
• 20% off per day, up to 4 days, for Projects/Programs

Student Learning Outcomes

After the completion of the course, the students should be able to:

• Read and understand a research paper.
• Write a comprehensive review of the paper.
• Identify strong and weak points of the papers.
• Come up with their own ideas to solve the same problem, which may lead to their first research paper.
• Implement a known method or work and successfully complete an individual project.

Instructor Information

The instructor for this course is Dr. Yogesh S Rawat.

Office Hours

Office hours are:

• Wednesday and Thursday 2:00 PM to 3:00 PM
• By appointment

Presentations Review

Presentations review will be held on:

• Thursday 2:00 PM, HEC 241 (if presenting on the following Tuesday)
• Monday 2:30 PM, HEC 450 (if presenting on Thursday)

Presentation Rehearsal

Presentation rehearsal will be held on:

• Monday 2:00 PM, HEC 450 (if presenting on Tuesday)
• Tuesday 2:00 PM, HEC 356 (if presenting on Thursday)

Extra Discussion Session

An extra discussion session will be held on:

• Wednesdays 4:30 to 5:30, HEC 356 (as needed, will be announced in Tuesday's class)

Statement on Academic Integrity

The UCF Golden Rule will be observed in the class. Plagiarism and cheating of any kind on an examination, quiz, or assignment will result in at least an "F" for that assignment (and may, depending on the severity of the case, lead to an "F" for the entire course) and may be subject to appropriate referral to the Office of Student Conduct for further action.