ECE 6554: Advanced Computer Vision Spring 2017
Course overview
 |
This is a graduate course in computer vision. The focus of the course will survey papers in a a broad range of topics in computer vision. The course goals will be to understand and analyze the strengths and weaknesses of the state-of-the-art techniques, and to identify interesting open questions and future directions. It should be of relevance to students interested in computer vision and machine learning. See the schedule for a list of topics we will cover. |
Lectures
Where: Room 220, Randolph Hall
When: Tuesday and Thursday 2:00 – 3:15 PM
Instructor: Jia-Bin Huang, 440 Whittemore Hall
Pre-requisite:
An introduction to computer vision or equivalent course. A machine learning or pattern recognition course is not required but may be beneficial.
Requirements
Class participation (5%)
Students will be required to read the assigned papers before each class and actively participate in discussions in class. If you are unable to attend a specific class, please let me know ahead of time via email. No laptops, cell phone or other distractions in class please.
Paper reviews (25%)
Students will need to read and write an one page review of the selected paper (marked as *) of the topic before the class. The recommended structure of the review is
Short summary of the paper
Main contributions
Strengths and weaknesses?
Are the experiments convincing?
How could the work be extended?
Additional comments, including unclear points, open research questions, and applications. The reviews should be posted on Piazza by 12:00 PM (noon) the day of the class (i.e. on Tuesdays and Thursdays).
Leading discussions (10%)
You will be assigned to lead discussion on the paper that you have read twice (estimated) during the semester. In one case you will be asked to argue in favor of the paper. In the other case you will be asked to argue against the paper. In each case, come prepared with 5 points of discussion (in favor or against the paper). You need not submit a review for the paper you are leading a discussion on.
Topic presentation (20%)
Each student will be asked to present the topic associated with a class once (estimated) over the course of the semester. Each topic presentation should be 30 minutes long. The recommended structure of the topic presentation is
High-level topic overview
Main motivation
Clear statement of the problem
Overview of the technical approach
Strengths/weaknesses of the approach
Overview of the experimental evaluation
Strengths/weaknesses of evaluation
Discussion: future direction, links to other work
The presenter needs to meet with the instructor 3 days prior the talk (i.e. Monday/Friday) with a complete set of slides for a dry run. You are free to use and modify external slides as part of your talk, but make sure that you cite the source.
Experiment presentation (10%)
Each student will be asked to present the experimental findings on a topic associated with a class once (estimated). Each experiment presentation should be 15 minutes long. The student need to implement/download the code for a main idea in a paper and evaluate it. The recommended experiments include
Experiment with different types of training/testing data sets
Evaluate sensitivity to important parameter settings
Show an example to analyze a strength/weakness of the approach
Show qualitative and quantitative results
Final project (30%)
Students can work individually or in pair on a research-oriented project to explore the state-of-the-art in computer vision. Some possibilities include
Extension of a technique studied in class
Analysis and empirical evaluation of an existing technique
In-depth comparison between two approaches
Design and evaluate a novel approach
See Final Project for more details.
General Information
Academic integrity
You are encouraged to discuss the course materials with the instructor and other students in the class. However, any work that you submit (including but not limited to homeworks, paper reviews, project reports) must be your own. Give proper citations if you use any code or data from anyone else.
The Undergraduate Honor Code pledge that each member of the university community agrees to abide by states: “As a Hokie, I will conduct myself with honor and integrity at all times. I will not lie, cheat, or steal, nor will I accept the actions of those who do.”
Students enrolled in this course are responsible for abiding by the Honor Code. A student who has doubts about how the Honor Code applies to any assignment is responsible for obtaining specific guidance from the course instructor before submitting the assignment for evaluation. Ignorance of the rules does not exclude any member of the University community from the requirements and expectations of the Honor Code. For additional information about the Honor Code, please visit: www.honorsystem.vt.edu.
The tenets of the Virginia Tech Graduate Honor Code will be strictly enforced in this course, and all assignments shall be subject to the stipulations of the Graduate Honor Code. For more information on the Graduate Honor Code, please refer to the GHS Constitution at this URL.
Disability-related academic adjustments
To obtain disability-related academic adjustments and/or auxiliary aids, students with disabilities must contact the course instructor and the Services for Students with Disabilities (SSD) as soon as possible. To contact SSD you may visit Suite 310 at Lavery Hall, or contact SSD via email ssd@vt.edu or here.
Similar courses
This course has been inspired by the following courses:
Object and Activity Recognition Seminar (Trevor Darrell, UC Berkeley)
Visual Learning and Recognition (Abhinav Gupta, CMU)
Visual Recognition (Kristen Grauman, UT Austin)
Advanced Computer Vision (Devi Parikh, Georgia Tech)